1. A method of tying a reinforcing bar, the method comprising:

acquiring a plurality of point cloud images of the steel bar operation surface at different time points, wherein two point cloud images acquired at two adjacent time points in the different time points have an overlapping area;

determining target rebar node coordinates of the rebar operation surface from the point cloud images;

and binding the steel bar operation surface according to the target steel bar node coordinates.

2. The method of claim 1, wherein the point cloud data acquisition device is controlled to acquire a plurality of point cloud images of the rebar operation surface according to the photographing coordinates, and wherein before the plurality of point cloud images of the rebar operation surface are acquired at different time points, the method further comprises:

and determining the photographing coordinates of the point cloud data acquisition equipment according to the visual field parameters of the point cloud data acquisition equipment and the size parameters of the steel bar operation surface, wherein under the photographing coordinates, the plurality of point cloud images comprise the whole steel bar operation surface, and the photographing coordinates are multiple.

3. The method of claim 1, wherein determining the target rebar node coordinates from the plurality of point cloud images comprises:

performing point cloud segmentation on the plurality of point cloud images to obtain point cloud data of the steel bar operation surface;

carrying out XOY plane projection on the point cloud data of the steel bar operation surface to obtain a binary image of the point cloud data of the steel bar operation surface;

obtaining a first initial steel bar node coordinate of the steel bar operation surface based on the binary image;

cutting the binary image to obtain a plurality of images comprising the first initial steel bar node coordinates;

correcting the first initial reinforcing steel bar node coordinates based on the multiple images to obtain second initial reinforcing steel bar node coordinates;

and 3D reducing the second initial reinforcing steel bar node coordinate to obtain the target reinforcing steel bar node coordinate, wherein the target reinforcing steel bar node coordinate is a coordinate under a 3D point cloud coordinate system.

4. The method of claim 3, wherein deriving first initial rebar node coordinates for the rebar operational face based on the binary map comprises:

determining horizontal lines and vertical lines in the binary image based on a Hough transform algorithm;

clustering the transverse lines and the vertical lines to obtain a plurality of transverse line clusters and a plurality of vertical line clusters;

and determining the coordinates of the intersection points of the average lines of the transverse line clusters and the average lines of the vertical line clusters as the coordinates of the first initial rebar node.

5. The method of claim 4, wherein modifying the first initial rebar node coordinates based on the plurality of images to obtain second initial rebar node coordinates comprises:

calculating to obtain a white point histogram of horizontal and vertical coordinates in the plurality of images;

and determining the coordinates of the second initial steel bar nodes according to the white point histogram.

6. The method of claim 1, wherein prior to tying the rebar operational face according to the target rebar node coordinates, the method further comprises:

calculating the distance between any two nodes in the target reinforcing steel bar nodes;

and carrying out duplicate removal processing on the target steel bar node coordinates according to the distance between any two nodes.

7. The method of claim 5, wherein binding the rebar manipulation surface according to the target rebar node coordinates comprises:

counting the number of lines and the number of columns where the target steel bar nodes are located;

determining a binding angle and/or a binding path of the target reinforcing steel bar node according to the number of the rows and the number of the columns of the target reinforcing steel bar node;

and controlling a binding robot to bind the target steel bar nodes according to the binding angles and/or binding paths.

8. The method of claim 7, wherein determining the binding angle of the target rebar node according to the number of rows and the number of columns the target rebar node is located in comprises:

and determining the binding angle of the target reinforcing steel bar node according to the parity of the number of the rows where the target reinforcing steel bar node is located and the number of the columns where the target reinforcing steel bar node is located.

9. The method of claim 7, wherein prior to controlling a banding robot to band the target rebar node according to the banding angle and/or banding path, the method further comprises:

calculating to obtain the size parameters of the transverse bar and the vertical bar at the node of the target reinforcing steel bar;

and determining the wire feeding length and the number of binding turns of the binding robot according to the size parameters of the transverse ribs and the vertical ribs.

10. A reinforcement bar binding apparatus, comprising:

the acquisition unit is used for acquiring a plurality of point cloud images of the steel bar operation surface at different time points, wherein two point cloud images acquired at two adjacent time points in the different time points have an overlapping area;

the determining unit is used for determining target steel bar node coordinates of the steel bar operation surface from the point cloud images;

and the binding unit is used for binding the steel bar operation surface according to the target steel bar node coordinates.

Background

The assembly building technology allows a large number of operations to be transferred from the site to the factory, where the components are fabricated and then assembled on site at the construction site. At present, the proportion of the assembly type building in the new building area is continuously increased, a reinforcement binding technology is taken as an important operation node in the assembly type building, and the reinforcement node (the intersection point of a transverse reinforcement and a vertical reinforcement) is bound by a metal wire by the reinforcement binding technology to form a firm reinforcement cage.

It should be noted that, the processing to the reinforcement still needs the manual hand to tie up the rifle and carry out the ligature to the reinforcing bar node in present assembled building, and this kind of traditional mode of working exists intensity of labour big, ties up inefficiency, ties up the dynamics inequality, can lead to the unqualified condition of reinforcement bar tying often appearing. The most outstanding technical problem is that the accuracy of the existing reinforcement bar binding technology in identifying reinforcement bar nodes is not enough, and the binding efficiency is low due to the fact that binding is missed easily.

Disclosure of Invention

The invention provides a steel bar binding method and a steel bar binding device, which are used for solving the technical problems that the accuracy of the conventional steel bar binding technology in identifying steel bar binding points is not enough, and binding leakage is easy to occur, so that the binding efficiency is low in the prior art.

According to a first aspect of the present invention, there is provided a method of lashing reinforcing bars, the method comprising: acquiring a plurality of point cloud images of the steel bar operation surface at different time points, wherein two point cloud images acquired at two adjacent time points in the different time points have an overlapping area; determining target steel bar node coordinates of the steel bar operation surface from the point cloud images; and binding the steel bar operation surface according to the target steel bar node coordinates.

Further, the method comprises the following steps of controlling a point cloud data acquisition device to acquire a plurality of point cloud images of the steel bar operation surface according to the photographing coordinates, wherein before the plurality of point cloud images of the steel bar operation surface are acquired at different time points, the method further comprises the following steps: and determining the photographing coordinates of the point cloud data acquisition equipment according to the visual field parameters of the point cloud data acquisition equipment and the size parameters of the steel bar operation surface, wherein under the photographing coordinates, the plurality of point cloud images comprise the whole steel bar operation surface, and the photographing coordinates are a plurality.

Further, determining the coordinates of the target rebar node from the plurality of point cloud images comprises: performing point cloud segmentation on the plurality of point cloud images to obtain point cloud data of the steel bar operation surface; carrying out XOY plane projection on the point cloud data of the steel bar operation surface to obtain a binary image of the point cloud data of the steel bar operation surface; obtaining a first initial steel bar node coordinate of the steel bar operation surface based on the binary image; cutting the binary image to obtain a plurality of images including the first initial steel bar node coordinates; correcting the first initial reinforcing steel bar node coordinates based on the multiple images to obtain second initial reinforcing steel bar node coordinates; and 3D restoring the second initial reinforcing steel bar node coordinate to obtain a target reinforcing steel bar node coordinate, wherein the target reinforcing steel bar node coordinate is a coordinate under a 3D point cloud coordinate system.

Further, obtaining the first initial rebar node coordinates of the rebar operation surface based on the binary map comprises: determining horizontal lines and vertical lines in the binary image based on a Hough transform algorithm; clustering the transverse lines and the vertical lines to obtain a plurality of transverse line clusters and a plurality of vertical line clusters; and determining the coordinates of the intersections of the average lines of the transverse line clusters and the average lines of the vertical line clusters as the coordinates of the first initial rebar node.

Further, the correction processing of the first initial rebar node coordinates based on the multiple images to obtain second initial rebar node coordinates includes: calculating to obtain a white point histogram of horizontal and vertical coordinates in a plurality of images; and determining the coordinates of the second initial steel bar nodes according to the white point histogram.

Further, before binding the steel bar operation surface according to the target steel bar node coordinates, the method further comprises the following steps: calculating the distance between any two nodes in the target steel bar nodes; and carrying out duplicate removal processing on the coordinates of the target reinforcing steel bar nodes according to the distance between any two nodes.

Further, binding the steel bar operation surface according to the target steel bar node coordinates comprises: counting the number of lines and the number of columns where the target steel bar nodes are located; determining a binding angle and/or a binding path of the target reinforcing steel bar node according to the number of the rows and the number of the columns of the target reinforcing steel bar node; and controlling the binding robot to bind the target steel bar node according to the binding angle and/or the binding path.

Further, determining the binding angle of the target reinforcing steel bar node according to the number of rows and the number of columns of the target reinforcing steel bar node comprises: and determining the binding angle of the target reinforcing steel bar node according to the number of the rows where the target reinforcing steel bar node is located and the parity of the number of the columns where the target reinforcing steel bar node is located.

Further, before controlling the binding robot to bind the target steel bar node according to the binding angle and/or the binding path, the method further comprises the following steps: calculating to obtain the size parameters of the transverse bar and the vertical bar at the node of the target reinforcing bar; and determining the wire feeding length and the number of binding turns of the binding robot according to the size parameters of the transverse ribs and the vertical ribs.

According to a second aspect of the present invention, there is provided a reinforcement bar binding apparatus comprising: the acquisition unit is used for acquiring a plurality of point cloud images of the steel bar operation surface at different time points, wherein two point cloud images acquired at two adjacent time points in the different time points have an overlapping area; the determining unit is used for determining target steel bar node coordinates of the steel bar operation surface from the point cloud images; and the binding unit is used for binding the steel bar operation surface according to the target steel bar node coordinates.

The invention provides a binding method and a binding device for reinforcing steel bars, wherein the method comprises the following steps: acquiring a plurality of point cloud images of the steel bar operation surface at different time points, wherein two point cloud images acquired at two adjacent time points in the different time points have an overlapping area; determining target steel bar node coordinates of the steel bar operation surface from the point cloud images; and binding the steel bar operation surface according to the target steel bar node coordinates. The problem of among the prior art, current reinforcement technique is not enough in the accuracy of discerning reinforcement point, appears leaking easily and ties and lead to the technique that ligature is inefficient.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 is a flowchart of a method of binding reinforcing bars according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of positions of a point cloud camera and a steel bar handling surface according to an embodiment of the present invention;

fig. 3 (fig. 3-1 to fig. 3-4) is a schematic diagram illustrating the effect of coarse positioning of the rebar junction according to the embodiment of the invention;

fig. 4 (fig. 4-1 to 4-3) is a schematic view illustrating an effect of fine positioning of a rebar junction according to an embodiment of the present invention;

FIG. 5 is a schematic view of a reinforcement angle according to an embodiment of the present invention;

fig. 6 to 7 are schematic views illustrating the calculation of the size of the reinforcing bar according to the embodiment of the present invention; and

fig. 8 is a schematic view of a reinforcing bar binding apparatus according to an embodiment of the present invention.

Detailed Description

In order to make the above and other features and advantages of the present invention more apparent, the present invention is further described below with reference to the accompanying drawings. It is understood that the specific embodiments described herein are for purposes of illustration only and are not intended to be limiting.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that the specific details need not be employed to practice the present invention. In other instances, well-known steps or operations are not described in detail to avoid obscuring the invention.

Example one

As shown in fig. 1, the present invention provides a method of binding reinforcing bars, which may include:

step S11, collecting a plurality of point cloud images of the steel bar operation surface at different time points, wherein two point cloud images collected at two adjacent time points in the different time points have an overlapping area.

Specifically, in the present scheme, a point cloud data collecting device may be used to collect a point cloud image of a steel bar operation surface, the point cloud data collecting device may be a 3D point cloud camera, the steel bar operation surface may be a steel bar cage, the steel bar cage may be a vertical formwork, the steel bar cage includes a plurality of intersections of horizontal steel bars and vertical steel bars, the plurality of intersections are steel bar nodes, that is, steel bar nodes for controlling automatic binding in the present scheme, and with reference to fig. 2, the point cloud camera may be disposed in front of the steel bar operation surface, and the point cloud camera collects a plurality of images of the steel bar operation surface, and in the present scheme, the point cloud camera collects a plurality of images for the steel bar operation surface according to different times, and may collect a plurality of images from the leftmost side to the rightmost side of the steel bar operation surface in sequence at different time points, and it should be noted that, in the collected plurality of images, two point cloud images acquired at two adjacent time points have an overlapping region, for example, a first image is acquired at a first time point, a second image is acquired at a second time point, and a third image is acquired at a third time point, the second time point is later than the first time point, and the third time point is later than the second time point, wherein the first image and the second image include the overlapping region, and the second image and the third image have the overlapping region, optionally, the overlapping region may be set, for example, the overlapping range overlap is 50 mm.

And step S13, determining the node coordinates of the target steel bars of the steel bar operation surface from the point cloud images.

Specifically, in the scheme, after a plurality of point cloud images of the steel bar operation surface are collected by the point cloud camera, the images can be sent to the upper computer, the upper computer determines coordinates of target steel bar nodes in the steel bar operation surface according to the plurality of point cloud images, and it needs to be explained that the coordinates of the target steel bar nodes are the corresponding steel bar nodes in the steel bar operation surface bound in the scheme, namely the points where the transverse steel bars and the vertical steel bars are crossed.

And step S15, binding the steel bar operation surface according to the target steel bar node coordinates.

Specifically, after the upper computer determines the coordinates of the target steel bar nodes according to the point cloud images, the coordinates of the target steel bar nodes can be sent to the binding robot (the mechanical arm with the steel bar binding head), the binding robot binds the steel bar operation surface, and it needs to be explained that the binding robot can automatically use the metal wires to wind the steel bar nodes.

Through the steps, this scheme is at the in-process of control point cloud camera gathering the reinforcement operation face, not only gather a whole image or many whole images, but control point cloud camera gathers many images of reinforcement operation face at different time points, moreover, be provided with the overlapping image between two liang of images of adjacent time point, then carry out the discernment of reinforcement node again, can guarantee that the whole of reinforcement operation face is all gathered, make the discernment of reinforcement node can not appear omitting, therefore, this scheme has solved current reinforcement technique and has discerned reinforcement point's accuracy not enough, appear leaking easily and tie up and lead to the technical problem that ligature efficiency is low, this scheme has guaranteed the coverage rate of ligature, need not artifical benefit and ties up, the manpower has been saved in a large number.

Optionally, the method may further include, before the step S11 of collecting the plurality of point cloud images of the steel bar operating surface at different time points, controlling the point cloud data collecting device to collect the plurality of point cloud images of the steel bar operating surface according to the photographing coordinates:

step S09, determining the photographing coordinates of the point cloud data acquisition equipment according to the visual field parameters of the point cloud data acquisition equipment and the size parameters of the steel bar operation surface, wherein under the photographing coordinates, a plurality of point cloud images comprise the whole steel bar operation surface, and the photographing coordinates are multiple.

Specifically, in the scheme, the shooting coordinates (shooting point positions) of the point cloud data acquisition equipment can be determined according to the visual field parameters of the point cloud data acquisition equipment and the size parameters of the steel bar operation surface, the visual field parameters of the point cloud data acquisition equipment can be the shooting distance range of the point cloud camera, the width and the height of the shooting visual field, and the size parameters of the steel bar operation surface can be the width and the height of the steel bar cage. According to the scheme, the coordinates of the photographing point are calculated through the visual field of the point cloud camera and the size of the steel bar operation surface, so that the point cloud photographed by the point cloud camera can cover the whole steel bar operation surface under the condition that the precision meets the requirement. The point cloud camera is connected with the mechanical arm and can be driven to freely move to different photographing coordinates to photograph.

It should be noted that above-mentioned arm both can drive a point cloud camera and remove and shoot, also can drive the ligature head and carry out the ligature to the different nodes of steel reinforcement cage, and all arms that appear in this scheme all can be same arm, and is concrete, and the camera can be fixed at the arm end, and the ligature head also is fixed at the arm end, and the task of shooing and ligature task can be the action of same arm at different times.

The specific calculation process about the photographing coordinates may be as follows:

the shooting view parameters of the camera are as follows: the shooting distance range is [800mm, 2000mm]The width of the imaging field is [500mm, 1360mm ]]The height of the shooting field is [350mm, 860mm]The width W of the reinforcement cage (i.e. the reinforcement operating surface) to be bound is 1200mm, and the height H is 2700 mm. Firstly, determining a shooting distance and a shooting posture of a camera, wherein according to the size of a rated working range of a mechanical arm of the camera and the size of a visual field of the camera, the shooting distance d can be selected to be 1000mm, the shooting posture of the camera is the horizontal z-axis of the camera and is vertical to a steel bar operation plane (a steel bar cage is a vertical mold), and a schematic position diagram of a shooting surface of the camera and the steel bar operation plane is shown in fig. 2. Then, the visual field of the camera on the steel bar operation surface is calculated, and when the shooting distance d is 1000mm in the scheme, the shooting visual field width w of the current camera on the steel bar operation surface can be calculated according to the shooting visual field parameters of the camera_cAnd a height h_cThe calculation formula may be (1-1).

Then, the coordinates of the photographing point are calculated, and the overlapping range overlap of two adjacent point cloud images can be preset to be 50 mm. The abscissa of the shot point can be shown by the following formula (1-2).

[x_b，(x_b+stride_x)，(x_b+stride_x×2)，......，(x_b+stride_x×n)] (1-2)

In the formula (1-2), x_bThe abscissa of the initial shot point of the lower left corner, stride_xStep size stride for lateral movement_x＝w_cOverlap, n is the number of lateral movements,the ordinate of the shooting point can be calculated by the following formula (1-3) in the same way:

[y_b，(y_b+stride_y)，(y_b+stride_y×2)，......，(y_b+stride_y×m)] (1-3)

in the formula (1-3), y_bThe ordinate of the initial shot point at the lower left corner, stride_yStep size stride for longitudinal movement_y＝h_cOverlap, m being the number of longitudinal movementsAccording to the abscissa of the photographing point in the formula (1-2) and the ordinate of the photographing point in the formula (1-3), the coordinates of all the photographing points can be obtained as shown in the formula (1-4), and all the photographing points are sequenced and then transmitted to the camera mechanical arm in sequence for photographing.

(x_b，y_b)，(x_b+stride_x，y_b)，(x_b+stride_x×2，y_b)，...，(x_b+stride_x×n，y_b)， (x_b，y_b+stride_y)，(x_b+stride_x，y_b+stride_y)，(x_b+stride_x×2，y_b+stride_y)，...，(x_b+stride_x×n，y_b+stride_y)， (x_b，y_b+stride_y×2)，(x_b+stride_x，y_b+stride_y×2)，(x_b+stride_x×2，y_b+stride_y×2)，...，(x_b+stride_x×n，y_b+stride_y×2)， ........， (x_b，y_b+stride_y×m)，(x_b+stride_x，y_b+stride_y×m)，(x_b+stride_x×2，y_b+stride_y×m)，...，(x_b+stride_x×n，y_b+stride_y×m) (1-4)。

It should be noted that the horizontal movement step length and the vertical movement step length may be horizontal displacement or vertical displacement in which the camera is driven by the camera mechanical arm after a photo is taken each time, that is, the camera mechanical arm drives the camera to be located at different shooting points (shooting position coordinates) through the horizontal displacement and the vertical displacement, and then the camera is driven by the camera mechanical arm to shoot a plurality of different point cloud images with overlapping areas.

Optionally, the step S13 of determining the coordinates of the target rebar node from the plurality of point cloud images includes:

and S131, performing point cloud segmentation on the plurality of point cloud images to obtain point cloud data of the steel bar operation surface.

Specifically, in the scheme, a target operation surface (namely a steel bar operation surface) is subjected to point cloud area segmentation, redundant background point clouds can be effectively removed, and the target operation surface is segmented, wherein the point cloud segmentation of the target operation surface can be realized by adopting a distance threshold method, the scheme can be segmented according to a z coordinate range of the point cloud as the shooting pose of a shooting point is fixed and the plane of the shooting point is parallel to the target operation surface, and in the scheme, the range of the z coordinate is [ d-60mm, d +60mm ]]Where d is the distance taken, i.e. a point p in the point cloud_c(x, y, z) if z is e [ d-60mm, d +60mm]If not, all the points are retained, and the final retained points are the segmentation result, namely the point cloud p of the target operation surface_n＝(x_n，y_n，z_n) And n is the number of the cloud midpoints of the target operation surface points.

And S132, performing XOY plane projection on the point cloud data of the steel bar operation surface to obtain a binary image of the point cloud data of the steel bar operation surface.

Specifically, in the scheme, the projection of the point cloud image of the steel bar operation surface on the XOY plane can be calculated, the point cloud data of the steel bar operation surface is projected on the XOY plane, and a mask binary image of the steel bar operation surface is obtained. In the projection binary image of the point cloud of the steel bar operating surface on the XOY plane, the wide calculation method of the binary image can be obtained by the following formula (1-5), and the high calculation method of the binary image can be obtained by the following formula (1-6).

w＝max(X)-min(X)，X＝[x₀，x₁，......，x_n] (1-5)

h＝max(Y)-min(Y)，Y＝[y₀，y₁，......，y_n] (1-6)

And step S133, obtaining a first initial steel bar node coordinate of the steel bar operation surface based on the binary image.

Specifically, in this scheme, the two-value graph obtained through projection may be subjected to coarse positioning of the steel bar node to obtain the first initial steel bar node coordinate, where it should be noted that the first initial steel bar node coordinate is only the steel bar node coordinate after the coarse positioning, and does not represent the position coordinate at which the final scheme controls the binding robot to perform actual binding.

And S134, cutting the binary image to obtain a plurality of images including the first initial rebar node coordinates.

Specifically, in this scheme, the binary image may be clipped to obtain a plurality of images including a first initial rebar node coordinate, and the pair of images may be a plurality of node small images including a plurality of first initial rebar node coordinates.

Step S135, performing correction processing on the first initial rebar node coordinates based on the multiple images to obtain second initial rebar node coordinates.

Specifically, in the present solution, the coordinates of the first initial rebar node subjected to coarse positioning in step S133 and step S134 may be further precisely positioned (locally corrected) through the plurality of node small images, and it should be noted that, in the present invention, for fine positioning of the rebar node, pixel-by-pixel calculation is performed on each node small image based on the node local small image, so as to ensure the accuracy of node positioning, that is, in this way, coarse positioning is performed before fine positioning is performed, so that the positioning accuracy of the rebar node can be improved.

And S136, performing 3D reduction on the second initial reinforcing steel bar node coordinate to obtain a target reinforcing steel bar node coordinate, wherein the target reinforcing steel bar node coordinate is a coordinate under a 3D point cloud coordinate system.

Specifically, in the present embodiment, the second initial rebar node coordinate obtained in the above step, that is, the position coordinate p in the operation surface projection binary image_m＝(x_m，y_m) Wherein m is the number of nodes, and the position p of the node under the 3D point cloud coordinate system can be calculated_cm＝(x_cm，y_cm，z_cm) Wherein x is_cm＝x_m+min(X)， y_cm＝y_mmin(Y)，z_cmSatisfying x e [ x ] in the cloud of the target operation surface points_cm-15，x_cm+15]And y belongs to [ y ∈ [_cm-15，y_cm+15]The method reduces the node coordinates of the steel bars into the 3D point cloud through the above method, namely, the node coordinates of the target steel bars under the 3D point cloud coordinate system are finally obtained, it needs to be noted that in the method, for the steel bar operation surface to be bound, the detection and positioning of the steel bar nodes are completed based on the 3D point cloud image, the precision is high, the error is small, the quality and the stability of the binding of the steel bars are greatly improved, wherein for the positioning of the steel bar nodes, the method of calculating the x coordinate on the 2D projection of the point cloud and then reducing the y coordinate into the 3D image to calculate the z coordinate is adopted, the algorithm complexity is low, the calculated amount is small, and the speed is high.

Optionally, the obtaining of the first initial rebar node coordinate of the rebar operation surface based on the binary map in step S131 may include:

step 1311, horizontal lines and vertical lines in the binary image are determined based on the hough transform algorithm.

Step S1312 clusters the horizontal lines and the vertical lines to obtain a plurality of horizontal line clusters and a plurality of vertical line clusters.

Step 1313, determining coordinates of intersections of the average lines of the transverse line clusters and the average lines of the vertical line clusters as first initial rebar node coordinates.

Specifically, in the above steps S1311 to S1313, first, all the straight lines a in the projection binary image are detected by using the hough transform algorithm_nx+b_ny+c_nWhere n is the number of straight lines, the inclination of the straight lines can be found from the equation of the straight lines, as shown in the following equations (1 to 7).

The solution may then divide the line into a plurality of horizontal and vertical lines, i.e. if the angle of inclination abs (angle) of the line_n)∈[0°，15°]The straight line is a horizontal line if the inclination abs (angle) of the straight line_n)∈[75°，90°]Then the line is a vertical line. Then, all horizontal lines and vertical lines are clustered according to the distance to obtain a plurality of horizontal line clusters and vertical line clusters, wherein the clustering calculation of the horizontal line clusters is thatWhen delta y is less than 50, the cluster is marked as the same horizontal line cluster, and the cluster calculation of the vertical line cluster is carried out in the same wayAnd when the delta x is less than 50, marking as the same vertical line cluster, and then calculating the average line of each cluster by the scheme. Finally, calculating to obtain the intersection point of the horizontal line cluster mean line and the vertical line cluster mean line, namely the node p_m＝(x_m，y_m) And m is the number of nodes. Referring to fig. 3, fig. 3-1 to 3-4 are schematic diagrams illustrating the effect of coarse positioning of a rebar node according to an embodiment of the present invention, fig. 3-1 is a projected binary diagram, fig. 3-3 is a plurality of horizontal clusters and a plurality of vertical clusters after clustering, and fig. 3-4 is an average line and a plurality of vertical clusters of the plurality of horizontal clustersThe mean line of the line cluster, fig. 3-2 is a node formed by crossing the mean lines of a plurality of horizontal line clusters and the mean lines of a plurality of vertical line clusters, i.e. the first initial rebar node. It should be noted that, in the application, for the rough positioning of the steel bar nodes, the traditional image processing method is adopted, and the method of Hough transform straight line detection and then calculating the intersection point of the horizontal line and the vertical line is realized, so that the calculation speed is high, the hardware cost required by the algorithm is low, and the binding speed and efficiency can be effectively guaranteed.

Optionally, in step S135, the correcting the first initial rebar node coordinate based on the multiple images to obtain a second initial rebar node coordinate includes:

step S1351, a histogram of white point numbers of horizontal and vertical coordinates in the plurality of images is calculated.

And step S1352, determining the coordinates of the second initial steel bar nodes according to the white point histogram.

Specifically, in the present solution, the steps S1351 to S1352 are a precise positioning process of the node of the steel bar (i.e., the fine positioning), and the present solution corrects the local position of the node detected by the coarse positioning in step S131, and the present solution can cut out a plurality of small graphs including the node position subjected to the coarse positioning from the original binary graph (the white area in the graph is the area where the steel bar is located), and then calculate a white point histogram of horizontal and vertical coordinates in the node small graphs, wherein the white point histogram of the vertical coordinates counts the number of white pixels in each row in the node small graphs, and the white point histogram of the similar horizontal coordinates is the number of white pixels in each row. And then, respectively finding points A, B, C and D in the two histograms, and respectively calculating central lines of AB and CD, wherein the central point (the central point where the horizontal and vertical ribs are intersected) where the two central lines are intersected is the corrected node position. Fig. 4 shows a schematic diagram of a local correction process, fig. 4-1 to 4-3 in fig. 4 show an effect schematic diagram of fine positioning of a steel bar node according to an embodiment of the present invention, where positions of two nodes in fig. 4-1 after coarse positioning are compared with positions of nodes after fine positioning, fig. 4-2 are horizontal white point statistical histograms, fig. 4-3 are vertical white point statistical histograms, and a point at a cross intersection in fig. 4-1 is a corrected node position (i.e., a second initial steel bar node coordinate).

Optionally, before the step S15 of binding the reinforcement operating surface according to the target reinforcement node coordinates, the method provided by the present application may further include:

step S141, calculating a distance between any two nodes in the target rebar node.

And S142, performing duplicate removal processing on the coordinates of the target steel bar nodes according to the distance between any two nodes.

Specifically, in the scheme, after three-dimensional space coordinate transformation is performed on nodes in all point clouds, the node position coordinates in the camera coordinate system are converted into the coordinate system where the mechanical arm is located. And calculating the distance between every two nodes under a coordinate system where the mechanical arm is located, and if the distance is too small, considering that the two nodes are repeated, performing duplicate removal treatment in a way of taking the mean value of the two nodes and then reserving the mean value. The specific steps can be as follows: firstly, converting node position coordinates in a camera coordinate system into a coordinate system of a mechanical arm, fixing a known 3D point cloud camera at the tail end of the mechanical arm, and calibrating an eye-to-hand transformation matrix by hands and eyes to obtain a notationMechanical arm pose for recording photographing point during photographingThen node p_cmThe calculation formula converted to the coordinates in the base coordinate system of the robot arm may be as follows (1-8).

Then, the nodes under the mechanical arm coordinate system are deduplicated, all the nodes are clustered according to an Euclidean distance formula (1-9), and the distance is less than a threshold value thre_dThen it is judged as an overlap point, and the coordinates of the overlap point position are averaged to be the coordinates of the current overlap node and updated, for example, point p_b1,p_b2Two points are overlapped points, and then the current node coordinate is according to the following formula(1-10) updating is performed and the overlapped two points are removed.

It should be noted that, in the invention, all nodes to be banded are deduplicated, and the 3D spatial euclidean distance between nodes is used as the measurement of node overlapping, so that duplicate nodes can be effectively removed, duplicate banding is avoided, and the banding efficiency is effectively improved.

Optionally, the step S15 of binding the reinforcement operating surface according to the target reinforcement node coordinates may include:

and step S151, counting the number of lines and the number of columns where the target steel bar node is located.

And S152, determining the binding angle and/or binding path of the target reinforcing steel bar node according to the number of the rows and the number of the columns of the target reinforcing steel bar node.

And S153, controlling the binding robot to bind the target steel bar node according to the binding angle and/or the binding path.

Specifically, the line number and the line number of each node can be determined according to the coordinate of a target steel bar node, then the binding angle and/or the binding path of the target steel bar node can be determined according to different line numbers and line numbers of the nodes, it needs to be noted that, in combination with fig. 5, the binding angle is an angle for binding when the steel bar node is bound by iron wires by a steel bar binding robot, the angle can be 45 degrees, 135 degrees and 45 degrees, it needs to be noted that binding the nodes by different binding angles can make a steel bar cage after binding firmer, optionally, the binding path of a steel bar operation surface can be determined according to different line numbers and line numbers of the nodes, the path can be a moving path of the steel bar binding robot, the scheme can sort all the nodes according to the line number according to the coordinate of each node, the sequenced nodes are sequentially transmitted to the mechanical arm end of the binding robot for binding, and it should be noted that the binding path can be arranged in front of and behind (for example, the sixth row and the first column are bound from bottom to top, then the fifth row and the first column … are bound to the first column and then the first row and the second column are bound, and the second row and the second column … are bound), or arranged in front of and behind, and for a plurality of nodes to be bound, the nodes are preferably sequenced in rows and then in rows, and are sequentially transmitted to the mechanical arm end one by one for binding, so that the displacement of the mechanical arm for completing all node task binding is minimum, and the binding efficiency can be greatly improved.

Optionally, the step S152 of determining the binding angle of the target reinforcing steel bar node according to the number of rows where the target reinforcing steel bar node is located and the number of columns where the target reinforcing steel bar node is located may include:

step S1521, determining the binding angle of the target reinforcing steel bar node according to the number of rows where the target reinforcing steel bar node is located and the parity of the number of columns where the target reinforcing steel bar node is located.

Specifically, in this scheme, can align all ligature nodes according to ranks and arrange, record the line number and the column number at each node place, thereby in order to reach the all opposite ligature effect more firm of ligature direction of current node and its four adjacent nodes, this scheme can confirm the ligature angle of target reinforcing bar node according to the line number at target reinforcing bar node place and the parity of the column number at place, confirm the example of ligature angle according to the parity of line number, column number as shown in table 1 below:

TABLE 1 node Angle Lashing rules

Serial number	Column count parity	Row number parity	Binding angle
				1	Magic card	Magic card	45 degree
2	Magic card	Doll	135 degree
				3	Doll	Magic card	135 degree
4	Doll	Doll	45 degree

It should be noted that, in the application, the planning of binding angles of the bound nodes follows the rule that the binding angles of each node and the adjacent upper, lower, left and right nodes are different, so that the whole steel bar operation surface after binding is firmer, and the risk of steel bar sliding is reduced.

Optionally, before controlling the binding robot to bind the target reinforcing steel bar node according to the binding angle and/or the binding path in step S153, the method provided by the present application may further include:

and step A, calculating to obtain the size parameters of the transverse bar and the vertical bar at the node of the target reinforcing steel bar.

And step B, determining the wire feeding length and the number of binding turns of the binding robot according to the size parameters of the transverse ribs and the vertical ribs.

Specifically, in this scheme, can estimate the thickness size (thickness size) of the horizontal muscle of each reinforcing bar node and perpendicular muscle to give the arm of reinforcement robot, the arm can control send a length and the number of revolutions when ligaturing the hand according to the size of reinforcing bar, guarantees that all node ligatures of different reinforcing bar sizes are all compliant. The calculation steps of the size parameters of the horizontal bars and the vertical bars at the target reinforcing steel bar nodes in the step a may be as follows:

according to the embodiment, the horizontal and vertical coordinate white point histogram of the reinforcement node binary graph is obtained in the step S1351, and then the horizontal coordinate histogram can calculate the thickness of the horizontal bar, and the thickness of the vertical bar can be calculated according to the vertical coordinate histogram. Referring to fig. 6 and 7, fig. 6 to 7 are schematic diagrams of the calculation of the size of the steel bar, points B and C are found on the white point statistical histogram of the ordinate, and then the average value in the intervals (a, B) and (C, D) is calculated, i.e. the size of the transverse bar of the current node. It should be noted that, in this application, the thickness size of the horizontal muscle and the thin muscle of each waiting to ligature node is estimated, and then according to the size self-adaptation adjustment ligature steel wire of horizontal vertical muscle and the rotatory number of turns of steel wire for the ligature success rate is higher, and the ligature elasticity is moderate, can ensure steel reinforcement's quality.

Example two

The present invention also provides a reinforcement bar binding apparatus, which can be used for executing the method of the first embodiment, as shown in fig. 8, and the apparatus can include: the acquisition unit 80 is configured to acquire a plurality of point cloud images of the rebar operation surface at different time points, where two point cloud images acquired at two adjacent time points of the different time points have an overlapping region. And the determining unit 82 is used for determining the target steel bar node coordinates of the steel bar operation surface from the point cloud images. And the binding unit 84 is used for binding the steel bar operation surface according to the target steel bar node coordinates.

Specifically, in this scheme, the point cloud data acquisition device 80 may be configured to receive a point cloud image of a rebar operation surface acquired by the point cloud data acquisition device, the point cloud data acquisition device may be a 3D point cloud camera, the rebar operation surface may be a rebar cage, the rebar cage may be a formwork erection device, the rebar cage includes a plurality of intersections of transverse rebars and vertical rebars, the intersections are rebar nodes, that is, rebar nodes requiring automatic binding control in this scheme, and with reference to fig. 2, the point cloud camera may be disposed in front of the rebar operation surface, and the point cloud camera acquires a plurality of images of the rebar operation surface, where in this scheme, the point cloud camera acquires a plurality of images for the rebar operation surface according to different times, and may acquire a plurality of images from the leftmost side to the rightmost side of the rebar operation surface at different time points in sequence, and it is further required to explain that, in the plurality of acquired images, two point cloud images acquired at two adjacent time points have an overlapping region, for example, a first image is acquired at a first time point, a second image is acquired at a second time point, and a third image is acquired at a third time point, the second time point is later than the first time point, and the third time point is later than the second time point, wherein the first image and the second image include the overlapping region, and the second image and the third image have the overlapping region, which may be set, for example, the overlapping range overlap is 50 mm. After the point cloud camera collects a plurality of point cloud images of the steel bar operation surface, the point cloud camera can send the images to an upper computer, the upper computer determines coordinates of target steel bar nodes in the steel bar operation surface according to the point cloud images, and it needs to be explained that the coordinates of the target steel bar nodes are the steel bar nodes bound in the steel bar operation surface in the scheme, namely the crossing points of the transverse steel bars and the vertical steel bars. After the upper computer determines the coordinates of the target steel bar nodes according to the point cloud images, the coordinates of the target steel bar nodes can be sent to a binding robot (a mechanical arm with a steel bar binding function), the binding robot binds the steel bar operation surface, and it needs to be explained that the binding robot can automatically use a metal wire to wind the steel bar nodes.

Through each unit in the above-mentioned device, this scheme is at the in-process of control point cloud camera gathering the reinforcement operation face, not only gather a whole image or many whole images, but control point cloud camera gathers many images of reinforcement operation face at the time point of difference, and, be provided with the overlapping image between two liang of images of adjacent time point, then carry out the discernment of reinforcement node again, can guarantee that the whole of reinforcement operation face is all gathered, make the discernment of reinforcement node can not appear omitting, therefore, this scheme has solved current reinforcement technique and has discerned the accuracy of reinforcement point not enough, the easy technical problem that the hourglass is tied up and is leaded to inefficiency appears, the coverage rate of ligature has been guaranteed to this scheme, need not artifical the benefit and ties up, the manpower has been saved in a large number.

It will be understood that the specific features, operations and details described herein with respect to the method of the present invention may be similarly applied to the apparatus or system of the present invention, or vice versa. In addition, each step of the method of the present invention described above may be performed by a respective component or unit of the device or system of the present invention.

It should be understood that the various modules/units of the apparatus of the present invention may be implemented in whole or in part by software, hardware, firmware, or a combination thereof. The modules/units may be embedded in the processor of the computer device in the form of hardware or firmware or independent from the processor, or may be stored in the memory of the computer device in the form of software for being called by the processor to execute the operations of the modules/units. Each of the modules/units may be implemented as a separate component or module, or two or more modules/units may be implemented as a single component or module.

In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored thereon computer instructions executable by the processor, the computer instructions, when executed by the processor, instructing the processor to perform the steps of the method of the invention. The computer device may broadly be a server, a terminal, or any other electronic device having the necessary computing and/or processing capabilities. In one embodiment, the computer device may include a processor, memory, a network interface, a communication interface, etc., connected by a system bus. The processor of the computer device may be used to provide the necessary computing, processing and/or control capabilities. The memory of the computer device may include non-volatile storage media and internal memory. An operating system, a computer program, and the like may be stored in or on the non-volatile storage medium. The internal memory may provide an environment for the operating system and the computer programs in the non-volatile storage medium to run. The network interface and the communication interface of the computer device may be used to connect and communicate with an external device through a network. Which when executed by a processor performs the steps of the method for charging a battery of the invention.

The invention may also be embodied as a computer readable storage medium having stored thereon a computer program which, when executed by a processor, causes the steps of a method of an embodiment of the invention to be performed. In one embodiment, the computer program is distributed across a plurality of computer devices or processors coupled by a network such that the computer program is stored, accessed, and executed by one or more computer devices or processors in a distributed fashion. A single method step/operation, or two or more method steps/operations, may be performed by a single computer device or processor or by two or more computer devices or processors. One or more method steps/operations may be performed by one or more computer devices or processors, and one or more other method steps/operations may be performed by one or more other computer devices or processors. One or more computer devices or processors may perform a single method step/operation, or perform two or more method steps/operations.

It will be appreciated by those of ordinary skill in the art that the method steps of the present invention may be directed to associated hardware, such as a computer device or processor, for performing the steps of the present invention by a computer program, which may be stored in a non-transitory computer readable storage medium, which when executed causes the steps of the present invention to be performed. Any reference herein to memory, storage, databases, or other media may include non-volatile and/or volatile memory, as appropriate. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (prom), electrically programmable ROM (eprom), electrically erasable programmable ROM (eeprom), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, hard disk, solid state disk, and the like. Examples of volatile memory include Random Access Memory (RAM), external cache memory, and the like.

The respective technical features described above may be arbitrarily combined. Although not all possible combinations of features are described, any combination of features should be considered to be covered by the present specification as long as there is no contradiction between such combinations.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.