1. The intelligent mapping data information processing method is characterized by comprising the following steps:

s1, acquiring original mapping data, wherein the original mapping data comprise a primary remote sensing image and a secondary remote sensing image, and the primary remote sensing image and the secondary remote sensing image are acquired by an unmanned aerial vehicle at set time intervals in the flying process of the unmanned aerial vehicle above a target land area according to a set flying route;

s2, respectively preprocessing the primary remote sensing image and the secondary remote sensing image to obtain a preprocessed primary remote sensing image and a preprocessed secondary remote sensing image;

s3, performing aerial triangulation operation on the preprocessed primary remote sensing images to obtain coordinate information of the primary remote sensing images, and splicing the preprocessed primary remote sensing images according to the obtained coordinate information to obtain spliced primary area images;

carrying out aerial triangulation operation on the preprocessed secondary remote sensing images to obtain coordinate information of the secondary remote sensing images, and splicing the preprocessed secondary remote sensing images according to the obtained coordinate information to obtain spliced secondary area images;

s4, performing fusion processing based on the primary area image and the secondary area image to obtain a target area remote sensing image;

s5, two-dimensional graph drawing or three-dimensional reconstruction is carried out based on the target area remote sensing image, and a target land area mapping result is obtained.

2. The method for processing the intelligent mapping data information according to claim 1, wherein in step S1, the target land area is provided with image control points, the unmanned aerial vehicle flies above the target land area according to the set parameters such as the flight route, the flight altitude and the flight speed, and the remote sensing image of the target land area is acquired through a five-vision shooting technology.

3. The method for processing the information of the intelligent mapping data according to claim 2, wherein in step S2, the preprocessing the primary remote sensing image and the secondary remote sensing image respectively includes: and respectively carrying out at least one of noise reduction filtering, image enhancement, image registration, set correction, tone adjustment and distortion correction processing on the primary remote sensing image and the secondary remote sensing image to obtain the preprocessed primary remote sensing image and the preprocessed secondary remote sensing image.

4. The intelligent mapping data information processing method according to claim 3, wherein step S3 includes: and mapping the primary remote sensing images to a set standard coordinate system according to image control points in the primary remote sensing images, and splicing the primary remote sensing images based on the standard coordinate system to obtain spliced primary region images.

And mapping the secondary remote sensing images to a set standard coordinate system according to image control points in the secondary remote sensing images, and splicing the secondary remote sensing images based on the standard coordinate system to obtain spliced secondary region images.

5. The intelligent mapping data information processing method according to claim 4, wherein step S4 includes: and fusing the primary region image and the secondary region image based on a set standard coordinate system to obtain a target region remote sensing image.

6. The method for processing the information on the intelligent mapping data according to claim 5, wherein in step S4, the process of fusing the primary region image and the secondary region image based on the set standard coordinate system includes:

converting each pixel point in the primary area image and the secondary area image into a standard coordinate system for representation, wherein each coordinate point corresponds to one pixel point in the area image;

performing fusion processing according to the same coordinate points in the primary area image and the secondary area image to obtain a target area remote sensing image, wherein the adopted fusion processing function is as follows:

in the formula, h₃(i, j) represents the gray value at the corresponding coordinate (i, j) in the target area remote sensing image after fusion processing, h₁(i, j) and h₂(i, j) represents the gray level at the corresponding coordinates (i, j) in the primary-area image and the secondary-area image, respectively, and H1 represents the set gray level difference threshold, where H1 ∈ [40,60 ]]R is 1 or 2, corresponding to the primary and secondary region images, σ_1-5×5(x, y) and σ_2-5×5(x, y) represents the mean square error of the gray scale of each coordinate in the 5 × 5 range centered at the coordinate (i, j) in the primary area image and the secondary area image, respectively.

7. The intelligent mapping data information processing method of claim 6, wherein in step S5, the target land area mapping result includes a two-dimensional mapping image of the target land area or a three-dimensional model of the target land area.

Background

The land surveying and mapping is based on computer technology, photoelectric technology, network communication technology, space science and information science, takes a Global Positioning System (GPS), Remote Sensing (RS) and a Geographic Information System (GIS) as technical cores, and obtains the graph and the sub-information reflecting the current situation of the ground from the existing characteristic points and boundary lines of the ground through a measuring means for planning design and administrative management of engineering construction. The unmanned aerial vehicle surveying and mapping technology has the characteristics of flexibility, high efficiency, rapidness, fineness, accuracy, low operation cost, wide application range, short production period and the like, and is widely applied to the land surveying and mapping process.

In the prior art, a remote sensing image of a land surveying and mapping area to be carried out is acquired in real time, quickly and comprehensively by an unmanned aerial vehicle carrying camera, the acquired remote sensing image is processed by applying technologies such as target positioning and tracking, digital aerial photogrammetry, quick sequential image splicing, three-dimensional reconstruction and the like based on a data processing system, and a two-dimensional or three-dimensional land surveying and mapping result is manufactured according to a standard. However, at present, land surveying and mapping are completed by processing image data acquired by an unmanned aerial vehicle, and the quality of a land surveying and mapping result finally acquired by the unmanned aerial vehicle is greatly influenced by the quality of original image data.

Disclosure of Invention

The invention aims to provide an intelligent surveying and mapping data information processing method aiming at the technical problem that the land surveying and mapping effect is affected due to the fact that the remote sensing image data acquired by an unmanned aerial vehicle is poor in processing effect.

The purpose of the invention is realized by adopting the following technical scheme:

the invention discloses an intelligent mapping data information processing method, which comprises the following steps:

s1, acquiring original mapping data, wherein the original mapping data comprise a primary remote sensing image and a secondary remote sensing image, and the primary remote sensing image and the secondary remote sensing image are acquired by an unmanned aerial vehicle at set time intervals in the flying process of the unmanned aerial vehicle above a target land area according to a set flying route;

s2, respectively preprocessing the primary remote sensing image and the secondary remote sensing image to obtain a preprocessed primary remote sensing image and a preprocessed secondary remote sensing image;

s3, performing aerial triangulation operation on the preprocessed primary remote sensing images to obtain coordinate information of the primary remote sensing images, and splicing the preprocessed primary remote sensing images according to the obtained coordinate information to obtain spliced primary area images;

carrying out aerial triangulation operation on the preprocessed secondary remote sensing images to obtain coordinate information of the secondary remote sensing images, and splicing the preprocessed secondary remote sensing images according to the obtained coordinate information to obtain spliced secondary area images;

s4, performing fusion processing based on the primary area image and the secondary area image to obtain a target area remote sensing image;

s5, two-dimensional graph drawing or three-dimensional reconstruction is carried out based on the target area remote sensing image, and a target land area mapping result is obtained.

In an optional implementation manner, in step S1, an image control point is set on the target land area, the unmanned aerial vehicle flies above the target land area according to the set parameters such as the flight path, the flight altitude, and the flight speed, and a remote sensing image of the target land area is acquired through a five-vision shooting technique.

In an optional embodiment, in step S2, the preprocessing the primary remote sensing image and the secondary remote sensing image respectively includes: and respectively carrying out at least one of noise reduction filtering, image enhancement, image registration, set correction, tone adjustment and distortion correction processing on the primary remote sensing image and the secondary remote sensing image to obtain the preprocessed primary remote sensing image and the preprocessed secondary remote sensing image.

In an alternative embodiment, step S3 includes: mapping the primary remote sensing images to a set standard coordinate system according to image control points in the primary remote sensing images, and splicing the primary remote sensing images based on the standard coordinate system to obtain spliced primary region images;

mapping the secondary remote sensing images to a set standard coordinate system according to image control points in the secondary remote sensing images, and splicing the secondary remote sensing images based on the standard coordinate system to obtain spliced secondary area images;

in an alternative embodiment, step S4 includes: and fusing the primary region image and the secondary region image based on a set standard coordinate system to obtain a target region remote sensing image.

In an alternative embodiment, in step S5, the target land area mapping result includes a two-dimensional mapping image of the target land area or a three-dimensional model of the target land area.

The invention has the beneficial effects that: the method comprises the steps of processing original mapping data collected by the unmanned aerial vehicle based on a data processing system, wherein remote sensing images collected successively are subjected to preprocessing and splicing processing to obtain two regional images obtained by different time nodes, meanwhile, fusion processing is carried out based on the two regional images to obtain a target regional remote sensing image, a target land regional mapping result is further obtained based on the target regional remote sensing image, and reliability and effect of land mapping based on the unmanned aerial vehicle remote sensing image are improved.

Drawings

The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.

FIG. 1 is a flowchart of an exemplary embodiment of an intelligent mapping data information processing method of the present invention.

Detailed Description

The invention is further described in connection with the following application scenarios.

Referring to fig. 1, an intelligent mapping data information processing method includes:

s1, acquiring original mapping data by the data processing system, wherein the original mapping data comprises a primary remote sensing image and a secondary remote sensing image, and the primary remote sensing image and the secondary remote sensing image are acquired by the unmanned aerial vehicle at set time intervals in the flying process of the unmanned aerial vehicle successively above a target land area according to a set flight route;

s2, the data processing system respectively preprocesses the primary remote sensing image and the secondary remote sensing image to obtain a preprocessed primary remote sensing image and a preprocessed secondary remote sensing image;

the data processing system of S3 carries out aerial triangulation operation to the preprocessed primary remote sensing images to obtain coordinate information of the primary remote sensing images, and carries out splicing processing to the preprocessed primary remote sensing images according to the obtained coordinate information to obtain spliced primary area images;

the data processing system carries out aerial triangulation operation on the preprocessed secondary remote sensing images to obtain coordinate information of the secondary remote sensing images, and carries out splicing processing on the preprocessed secondary remote sensing images according to the obtained coordinate information to obtain spliced secondary area images;

s4, the data processing system performs fusion processing based on the primary area image and the secondary area image to obtain a target area remote sensing image;

and S5, the data processing system performs two-dimensional graphic drawing or three-dimensional reconstruction based on the target area remote sensing image to obtain the mapping result of the target land area.

The method is completed based on a data processing system, wherein the data processing system can be built on an intelligent terminal or a server, and can also be built based on a cloud computing platform, and the method is not particularly limited herein.

In the above embodiment, the original mapping data collected by the unmanned aerial vehicle is processed based on the data processing system, wherein the remote sensing images collected successively are preprocessed and spliced to obtain two regional images obtained at different time nodes, and meanwhile, the target regional remote sensing image is obtained based on the fusion processing of the two regional images, and the mapping result of the target land region is further obtained based on the target regional remote sensing image, so that the influence of the sudden factors (such as cloud cover and shadow influence caused by flying objects, or shielding influence of other flying objects (such as flying birds) received in the collecting process of the unmanned aerial vehicle) on the region in the remote sensing image collecting process can be effectively avoided, and the reliability and the effect of land mapping based on the remote sensing image of the unmanned aerial vehicle can be improved.

In an optional implementation manner, in step S1, an image control point is set on the target land area, the unmanned aerial vehicle flies above the target land area according to the set parameters such as the flight path, the flight altitude, and the flight speed, and a remote sensing image of the target land area is acquired through a five-vision shooting technique.

In one scenario, the route plan set therein is an S-route.

The unmanned aerial vehicle adopts Phantom 4RTK unmanned aerial vehicle, and the unmanned aerial vehicle flying height is 35-350m, and wherein the unmanned aerial vehicle is carried with five cameras.

The unmanned aerial vehicle flies over the target land area twice successively and respectively completes shooting at two different time nodes at a set time period so as to respectively obtain a primary remote sensing image and a secondary remote sensing image, and the acquired primary remote sensing image and the acquired secondary remote sensing image are transmitted to a data processing system.

As a preferred embodiment, the interval between the two time nodes may be set to 5 minutes to 24 hours.

In an optional embodiment, in step S2, the preprocessing the primary remote sensing image and the secondary remote sensing image respectively includes: and respectively carrying out at least one of noise reduction filtering, image enhancement, image registration, set correction, tone adjustment, distortion correction and the like on the primary remote sensing image and the secondary remote sensing image to obtain the preprocessed primary remote sensing image and the preprocessed secondary remote sensing image.

In one embodiment, in step S2, the image enhancement processing on the primary remote sensing image and the secondary remote sensing image specifically includes:

carrying out multi-scale lifting wavelet transform on a target image to obtain a low-frequency wavelet coefficient and a high-frequency wavelet coefficient of the target image, wherein the target image comprises a primary remote sensing image and/or a secondary remote sensing image;

carrying out filtering enhancement processing on the obtained high-frequency wavelet coefficient, wherein the adopted filtering enhancement processing function is as follows:

in the formula (I), the compound is shown in the specification,representing the high-frequency wavelet coefficients after filter enhancement_j,kRepresenting the acquired high-frequency wavelet coefficient, T representing a set threshold, delta representing a set filter adjustment factor, sgn (·) representing a sign function;

performing lifting wavelet inverse transformation based on the high-frequency wavelet coefficient after the filtering enhancement processing and the obtained low-frequency wavelet coefficient to obtain a filtered remote sensing image;

processing the filtered remote sensing image by adopting a Canny edge detection operator, detecting edge information in the image, and dividing the filtered remote sensing image into an edge part and a non-edge part, wherein the edge part comprises a set of edge pixel points, and the non-edge part comprises combination of non-edge pixel points;

and carrying out smooth enhancement processing on the obtained non-edge part, wherein the adopted smooth enhancement function is as follows:

in the formula (I), the compound is shown in the specification,representing the gray value at the pixel (x, y) after the smooth enhancement process, h (x, y) representing the gray value at the pixel (x, y) in the non-edge portion,it is indicated that no edge pixel exists for the pixel points within the 3 x 3 range centered on the pixel (x, y),indicating that edge pixels exist in pixels within a range of 3 × 3 with the pixel (x, y) as the center;represents the gray average value of non-edge pixel points within 3 x 3 range with the pixel (x, y) as the center,represents the gray average value of the edge pixel points within 3 x 3 range with the pixel (x, y) as the center,represents the mean square error of the gray levels of the pixel points within a range of 3 x 3 with the pixel (x, y) as the center,showing the mean square error of gray scale of edge pixel points within a 3 x 3 range with the pixel (x, y) as the center, and beta represents a set adjustment factor, wherein the beta belongs to [0.9,1.1 ]]；Represents a truncated function ofWhen the temperature of the water is higher than the set temperature, when in useWhen the temperature of the water is higher than the set temperature,when in use When the temperature of the water is higher than the set temperature,

and reconstructing the non-edge part after the smooth enhancement processing and the obtained edge part to obtain a preprocessed target image.

The embodiment provides a technical scheme for enhancing the primary remote sensing image and the secondary remote sensing image, which is beneficial to improving the quality of the remote sensing images, removing noise interference received in the process of acquiring the remote sensing images, enhancing the detail part in the remote sensing images and improving the overall and detail display effect of the remote sensing images.

In an alternative embodiment, step S3 includes: mapping the primary remote sensing images to a set standard coordinate system according to image control points in the primary remote sensing images, and splicing the primary remote sensing images based on the standard coordinate system to obtain spliced primary region images;

mapping the secondary remote sensing images to a set standard coordinate system according to image control points in the secondary remote sensing images, and splicing the secondary remote sensing images based on the standard coordinate system to obtain spliced secondary area images;

in an alternative embodiment, step S4 includes: and fusing the primary region image and the secondary region image based on a set standard coordinate system to obtain a target region remote sensing image.

In an alternative embodiment, in step S4, the performing a fusion process on the primary region image and the secondary region image based on the set standard coordinate system specifically includes:

converting each pixel point in the primary area image and the secondary area image into a standard coordinate system for representation, wherein each coordinate point corresponds to one pixel point in the area image;

performing fusion processing according to the same coordinate points in the primary area image and the secondary area image to obtain a target area remote sensing image, wherein the adopted fusion processing function is as follows:

in the formula, h₃(i, j) represents the gray value at the corresponding coordinate (i, j) in the target area remote sensing image after fusion processing, h₁(i, j) and h₂(i, j) represents the gray level at the corresponding coordinates (i, j) in the primary-area image and the secondary-area image, respectively, and H1 represents the set gray level difference threshold, where H1 ∈ [40,60 ]]R is 1 or 2, corresponding to the primary and secondary region images, σ_1-5×5(x, y) and σ_2-5×5(x, y) represents the mean square error of the gray scale of each coordinate in the 5 × 5 range centered at the coordinate (i, j) in the primary area image and the secondary area image, respectively.

In the above embodiment, a technical scheme for performing fusion processing based on a primary area image and a secondary area image is provided, wherein it is considered that when one of the primary acquisition processes is affected by an unexpected factor, the affected position of the primary acquisition process shows a large gray level difference in two area images, so a fusion processing function is provided, which can screen a region with a large gray level difference (the region affected by the unexpected factor), wherein for the part with the large gray level difference, adaptive fusion processing is performed based on the characteristics of a land remote sensing image, the region is effectively affected by the unexpected factor in the fusion process, which is helpful for restoring the real land condition, and the accuracy and effect of land mapping are improved.

In an alternative embodiment, in step S5, the target land area mapping result includes a two-dimensional mapping image of the target land area or a three-dimensional model of the target land area.

And aiming at the obtained remote sensing image of the target area, two-dimensional graph drawing or three-dimensional reconstruction can be carried out according to actual needs, and a corresponding land surveying and mapping result is obtained.

From the above description of embodiments, it is clear for a person skilled in the art that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code or any appropriate combination thereof. For a hardware implementation, a processor may be implemented in one or more of the following units: an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a processor, a controller, a microcontroller, a microprocessor, other electronic units designed to perform the functions described herein, or a combination thereof. For a software implementation, some or all of the procedures of an embodiment may be performed by a computer program instructing associated hardware. In practice, the program may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a computer. Computer-readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.

Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be analyzed by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.