1. A method for analyzing a violation by a locomotive attendant, comprising:

acquiring a monitoring video of a locomotive attendant in the locomotive running process;

detecting key areas in each video frame image of the monitoring video, wherein the key areas comprise key areas of a human body and key areas of the cab;

and determining the violation behaviors of the locomotive crew members according to the key area, wherein the violation behaviors are prohibited behaviors in driving.

2. The method of claim 1, wherein determining the locomotive crew violation based on the critical area comprises:

determining the driving behaviors of the locomotive crew in each video frame image according to the key area, wherein the driving behaviors comprise designated violation behaviors or non-designated violation behaviors, and the designated violation behaviors comprise off-duty behaviors, behaviors of illegally using electronic equipment, head-bias chatting behaviors or abnormal opening behaviors of a vehicle door;

judging whether the driving behaviors in N continuous video frame images in the monitoring video are the specified violation behaviors or whether the driving behaviors in P discontinuous video frame images in M continuous video frame images are the specified violation behaviors;

and if so, determining the violation behaviors of the locomotive crew members as the specified violation behaviors.

3. The method of claim 2, wherein determining the driving behavior of the locomotive crew member in each video frame image based on the critical area comprises:

identifying a side window area, an operation platform area, a door area and a locomotive attendant seat area in any one frame of video frame image, wherein the side window area, the operation platform area, the door area and the locomotive attendant seat area belong to the cab key area;

determining a designated driving area consisting of the side window area, the console area, the door area and the locomotive attendant seat area, wherein the designated driving area is a preset area in the locomotive cab and containing the locomotive attendant seat area;

determining that the locomotive attendant is off duty in the video frame image when it is determined that the locomotive attendant is not in the designated driving area.

4. The method of claim 2, wherein determining the driving behavior of the locomotive crew member in each video frame image based on the critical area comprises:

judging whether any frame of video frame image has a designated electronic device;

if the designated electronic equipment is arranged in the video frame image, judging whether the designated electronic equipment is positioned in the visual field range of the locomotive crew member;

if so, determining that the locomotive crew member has the illegal electronic equipment use behavior in the video frame image.

5. The method of claim 4, wherein determining whether the designated electronic device is within a field of view of the locomotive attendant comprises:

acquiring a face area, a head area, a hand area and an arm area in the video frame image;

determining a field of view region comprised of the face region, the head region, the hand region, and the arm region;

judging whether the specified electronic equipment is in the visual field area;

when the electronic equipment is in the visual field area, the specified electronic equipment is determined to be located in the visual field area.

6. The method of claim 2, wherein determining the driving behavior of the locomotive crew member in each video frame image based on the critical area comprises:

for any video frame image in the monitoring video, determining the area ratio of a face region and a head region in the video frame image and the aspect ratio of the face region in the video frame image, wherein the face region and the head region belong to the human body key region;

determining that the locomotive crew member has the boring behavior in the video frame image when the area ratio is greater than an area threshold or the aspect ratio is greater than an aspect ratio threshold.

7. The method of claim 2, wherein determining the driving behavior of the locomotive crew member in each video frame image based on the critical area comprises:

judging whether a video frame image with the vehicle door in an open state exists in the monitoring video;

if so, determining that the abnormal door opening behavior of the locomotive crew member appears in the video frame image.

8. An analysis device for analyzing a violation of a locomotive attendant, comprising:

the acquisition unit is used for acquiring a monitoring video of a locomotive attendant in the locomotive running process;

the detection unit is used for detecting key areas in each video frame image of the monitoring video, wherein the key areas comprise key areas of a human body and key areas of the cab;

and the determining unit is used for determining the violation behaviors of the locomotive crew members according to the key area, wherein the violation behaviors are prohibited behaviors in driving.

9. A computer device, comprising: the system comprises a processor, a memory and a communication bus, wherein the processor and the memory are communicated with each other through the communication bus;

the memory for storing a computer program;

the processor, executing the program stored in the memory, implements the locomotive attendant's violation analysis method of any of claims 1-7.

10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the locomotive attendant's violation analysis method of any one of claims 1-7.

Background

At present, the behavior analysis of railway locomotive crew members in China mainly depends on manual spot check and verification of locomotive monitoring videos and manual spot check and verification, due to the fact that workload is large, full coverage verification analysis of videos and staff cannot be achieved, and the problems of missing check and report and low efficiency exist.

Existing analysis methods can be divided into two categories: firstly, the state of a crew member is judged by monitoring the state of a vehicle, the driving state is monitored and recorded through a sensor, the driving state is monitored, and the behavior of the crew member is indirectly judged by comparing and analyzing the abnormal driving state. And secondly, the crew member is monitored through videos and is checked manually, and the behavior of the crew member is further judged.

The two types of analysis described above also have drawbacks: the first method is indirect monitoring, cannot completely and truly reflect the behavior of the crew, and is not timely analyzed; for the second method, manual review by analysts is required, and the workload is large. The behavior analysis quality is limited by the influence of subjective responsibility and business capability of people, and the missed check and report are easy to cause.

Disclosure of Invention

The application provides a method, a device, equipment and a storage medium for analyzing the violation behaviors of locomotive crew members, which are characterized in that a field image is directly acquired by utilizing a monitoring video (low quality) of the existing locomotive cab, the cab is not required to be modified, a new acquisition device is not required to be added, the violation behaviors of the crew member leaving the post, the violation behaviors of using electronic equipment, the head-leaning and idle chatting behaviors, the abnormal opening of a vehicle door and the like which influence the driving safety are intelligently and efficiently analyzed, the workload of personnel for auditing the videos is reduced, and the working efficiency is improved.

In a first aspect, a method for analyzing violation of a locomotive attendant is provided, comprising:

acquiring a monitoring video of a locomotive attendant in the locomotive running process;

detecting key areas in each video frame image of the monitoring video, wherein the key areas comprise key areas of a human body and key areas of the cab;

and determining the violation behaviors of the locomotive crew members according to the key area, wherein the violation behaviors are prohibited behaviors in driving.

Optionally, determining the violation by the locomotive attendant according to the critical area comprises:

determining the driving behaviors of the locomotive crew in each video frame image according to the key area, wherein the driving behaviors comprise designated violation behaviors or non-designated violation behaviors, and the designated violation behaviors comprise off-duty behaviors, behaviors of illegally using electronic equipment, head-bias chatting behaviors or abnormal opening behaviors of a vehicle door;

judging whether the driving behaviors in N continuous video frame images in the monitoring video are the specified violation behaviors or whether the driving behaviors in P discontinuous video frame images in M continuous video frame images are the specified violation behaviors;

and if so, determining the violation behaviors of the locomotive crew members as the specified violation behaviors.

Optionally, determining the driving behavior of the locomotive crew in each video frame image according to the critical area comprises:

identifying a side window area, an operation platform area, a door area and a locomotive attendant seat area in any one frame of video frame image, wherein the side window area, the operation platform area, the door area and the locomotive attendant seat area belong to the cab key area;

determining a designated driving area consisting of the side window area, the console area, the door area and the locomotive attendant seat area, wherein the designated driving area is a preset area in the locomotive cab and containing the locomotive attendant seat area;

determining that the locomotive attendant is off duty in the video frame image when it is determined that the locomotive attendant is not in the designated driving area.

Optionally, determining the driving behavior of the locomotive crew in each video frame image according to the critical area comprises:

judging whether any frame of video frame image has a designated electronic device;

if the designated electronic equipment is arranged in the video frame image, judging whether the designated electronic equipment is positioned in the visual field range of the locomotive crew member;

if so, determining that the locomotive crew member has the illegal electronic equipment use behavior in the video frame image.

Optionally, determining whether the designated electronic device is within a field of view of the locomotive attendant comprises:

acquiring a face area, a head area, a hand area and an arm area in the video frame image;

determining a field of view region comprised of the face region, the head region, the hand region, and the arm region;

judging whether the specified electronic equipment is in the visual field area;

when the electronic equipment is in the visual field area, the specified electronic equipment is determined to be located in the visual field area.

Optionally, determining the driving behavior of the locomotive crew in each video frame image according to the critical area comprises:

for any video frame image in the monitoring video, determining the area ratio of a face region and a head region in the video frame image and the aspect ratio of the face region in the video frame image, wherein the face region and the head region belong to the human body key region;

determining that the locomotive crew member has the boring behavior in the video frame image when the area ratio is greater than an area threshold or the aspect ratio is greater than an aspect ratio threshold.

Optionally, determining the driving behavior of the locomotive crew in each video frame image according to the critical area comprises:

judging whether a video frame image with the vehicle door in an open state exists in the monitoring video;

if so, determining that the abnormal door opening behavior of the locomotive crew member appears in the video frame image.

In a second aspect, there is provided a violation analysis device for a locomotive attendant, comprising:

the acquisition unit is used for acquiring a monitoring video of a locomotive attendant in the locomotive running process;

the detection unit is used for detecting key areas in each video frame image of the monitoring video, wherein the key areas comprise key areas of a human body and key areas of the cab;

and the determining unit is used for determining the violation behaviors of the locomotive crew members according to the key area, wherein the violation behaviors are prohibited behaviors in driving.

In a third aspect, there is provided a computer device comprising: the system comprises a processor, a memory and a communication bus, wherein the processor and the memory are communicated with each other through the communication bus;

the memory for storing a computer program;

the processor is configured to execute the program stored in the memory to implement the method for analyzing the violation of the locomotive crew member according to the first aspect.

A computer-readable storage medium is provided, storing a computer program that, when executed by a processor, implements the method for analyzing locomotive crew violation behavior of the first aspect.

Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages: according to the technical scheme provided by the embodiment of the application, the monitoring video of the locomotive crew member in the locomotive running process is obtained, the key area in each video frame image of the monitoring video is detected, and the violation behaviors of the locomotive crew member are determined according to the key area. By adopting the scheme, the existing locomotive cab video monitoring (low quality) is utilized to directly acquire the field image, the locomotive cab is not required to be transformed, a new image acquisition device is not required to be added, the violation behaviors such as crew off-duty behavior, illegal use of electronic equipment behavior, head-bias idle chat behavior and abnormal door opening behavior which affect the driving safety are intelligently and efficiently analyzed, the workload of auditing videos by personnel is reduced, and the working efficiency is improved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.

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 for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.

FIG. 1 is a schematic flow chart of a method for analyzing locomotive crew violation behavior in an embodiment of the present application;

FIG. 2 is a schematic flow chart of another method for analyzing violation by a locomotive attendant in an embodiment of the present application;

FIG. 3 is a schematic flow chart illustrating a method for analyzing the off-Shift behavior of a locomotive attendant in an embodiment of the present application;

FIG. 4 is a schematic structural diagram of a cab according to an embodiment of the present disclosure;

FIG. 5 is a schematic flow chart illustrating a method for analyzing locomotive crew violation electronic device behavior according to an embodiment of the present disclosure;

FIG. 6 is a schematic flow chart illustrating a method for analyzing the partially boring behavior of a locomotive attendant according to an embodiment of the present disclosure;

FIG. 7 is a schematic flow chart illustrating a method for analyzing abnormal door opening behavior of a locomotive attendant in an embodiment of the present application;

fig. 8 is a schematic structural diagram of a violation analysis device of a locomotive attendant in an embodiment of the present application;

fig. 9 is a schematic structural diagram of a computer device in an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The embodiment of the application provides a method for analyzing the violation behaviors of locomotive attendants, which can be applied to computer equipment;

the computer device may be any electronic device inside the locomotive, or may be any electronic device outside the locomotive, which is not specifically limited in this embodiment;

the computer device may include a smart Phone (such as an Android Phone, an iOS Phone, a Windows Phone, etc.), a tablet computer, a palm computer, a notebook computer, a video matrix, a monitoring platform, a Mobile Internet device (MID, Mobile Internet Devices), or a wearable device, which are merely examples, but are not exhaustive and include but are not limited to the above Devices.

As shown in fig. 1, the method for analyzing the violation of the locomotive crew member may include the steps of:

step 101, acquiring a monitoring video of a locomotive attendant in the locomotive running process;

in this embodiment, the monitoring video may be collected by using the video monitoring of the existing locomotive cab, the video monitoring is communicated with the computer device, and the video monitoring transmits the corresponding monitoring video to the computer device through a communication bus or a network.

In this embodiment, the video surveillance may be located at a location behind the right of the locomotive attendant.

102, detecting key areas in each video frame image of a monitoring video, wherein the key areas comprise key areas of a human body and key areas of a cab;

in this embodiment, a target detection algorithm in deep learning may be used to detect and obtain a key region in each video frame image.

Optionally, the human body critical areas include, but are not limited to, a locomotive crew area, a locomotive crew back area, a face area, a mask-worn face area, an arm area, a head area, and a hand area; the key areas of the cab include, but are not limited to, the seating area, the side window area, the door area (in both open and closed states), and the operator's station area.

And 103, determining the violation behaviors of the locomotive crew members according to the key area, wherein the violation behaviors are prohibited behaviors in driving.

According to the technical scheme provided by the embodiment of the application, the monitoring video of the locomotive crew member in the locomotive running process is obtained, the key area in each video frame image of the monitoring video is detected, and the violation behaviors of the locomotive crew member are determined according to the key area. By adopting the scheme, the existing locomotive cab video monitoring (low quality) is utilized to directly acquire the field image, the locomotive cab is not required to be transformed, a new image acquisition device is not required to be added, the violation behaviors such as crew off-duty behavior, illegal use of electronic equipment behavior, head-bias idle chat behavior and abnormal door opening behavior which affect the driving safety are intelligently and efficiently analyzed, the workload of auditing videos by personnel is reduced, and the working efficiency is improved.

In the application, in order to accurately determine whether the locomotive driver has the violation, in another embodiment of the application, the violation of the locomotive driver is determined according to the time or frequency of the occurrence of the specified violation.

Specifically, as shown in fig. 2, step 103 may include the following steps:

step 201, determining the driving behavior of a locomotive crew in each video frame image according to a key area;

the driving behaviors comprise specified violation behaviors or non-specified violation behaviors, and the specified violation behaviors comprise four types of violation behaviors including off-post behaviors, behaviors of illegally using electronic equipment, head-biased chatting behaviors and abnormal opening behaviors of a car door.

Step 202, judging whether the driving behaviors in the N continuous video frame images are all specified violation behaviors or whether the driving behaviors in the P discontinuous video frame images are all specified violation behaviors in the M continuous video frame images, if yes, executing step 203;

and step 203, determining the violation behaviors of the locomotive crew member as the specified violation behaviors.

If the specified violation occurs in the continuous N video frame images or the specified violation occurs in the discontinuous P video frame images in the continuous M video frame images, that is, the frequency of the specified violation exceeds the specified frequency in the continuous M video frame images, executing step 203; otherwise, return to continue execution 201.

Wherein M, N, P are all positive integers.

In this embodiment, in order to ensure the recognition accuracy, the computer device needs to analyze at least 2 frames of video frame images in 1 second. After the computer device obtains the monitoring video, the frame rate of the monitoring video can be read, and the detection frame number per second is distributed according to the frame rate. When the header file of the monitoring video is damaged and the frame rate of the monitoring video cannot be obtained, the frame rate of the on-site monitoring video should be considered, and when there are multiple frame rates, the lowest frame rate should be used as a reference to ensure that at least 2 frames are processed for 1 second, for example, when the frame rate of the on-site monitoring (i.e., an image acquisition device) is 1 second 8 frames or 1 second 25 frames, in this embodiment, the computer device is taken to analyze 8 frames of video frame images for 1 second, that is, 8 frames of video frame images are extracted from the video frame images acquired by the image acquisition device every 1 second as the video frame images at that moment, so the N frame of video frame images and the M frame of video frame images in step 202 both refer to the extracted video frame images.

In this embodiment, the designated frequency may be set in advance according to reality. The designated frequency is defined as the percentage of the video frame images with a certain type of designated violation behaviors in the discontinuous P video frame images in the continuous M video frame images.

In this embodiment, after the specific violation behaviors of the locomotive crew are determined, the reasons of the violation behaviors, the damage levels of the violation behaviors, the occurrence time and the like can be summarized.

In this embodiment, the execution of steps 201 to 203 may be performed in real time, that is, the video monitoring acquires each video frame image in the monitoring video, and transmits each video frame image to the computer device in real time, and after the computer device acquires the video frame image, the computer device immediately performs analysis on the violation behaviors of the locomotive crew on the video frame image; the execution of the steps 201 to 203 may also be performed periodically, that is, after the computer device obtains the monitoring video within the preset period time, the computer device performs analysis on the violation behaviors of the locomotive crew on each video frame image in the monitoring video, which is not specifically limited in this embodiment.

The following describes the analysis process of each type of violation:

with respect to off Shift behavior, it may be determined whether the locomotive attendant is exhibiting off Shift behavior in the video frame images by determining whether the locomotive attendant is within a designated driving area.

Specifically, as shown in fig. 3, step 201 may include the following steps:

step 301, identifying a side window area, an operation platform area, a vehicle door area and a locomotive attendant seat area in any frame of video frame image, wherein the side window area, the operation platform area, the vehicle door area and the locomotive attendant seat area belong to a cab key area;

step 302, determining a designated driving area formed by a side window area, an operation platform area, a door area and a locomotive attendant seat area, wherein the designated driving area is a preset area containing the locomotive attendant seat area in a locomotive cab;

step 303, determining that the locomotive attendant has off duty behavior in the video frame image when the locomotive attendant is determined not to be in the designated driving area.

Referring to fig. 4, fig. 4 is a schematic structural diagram of the cab shown in the present embodiment, wherein the defined areas on the right side of the door or the seat back, below the side window, and on the left side of the console are designated driving areas in the present embodiment. Judging whether the center (or the gravity center or the vertex of the area) of the locomotive attendant area in the video frame image is positioned on the right side of a vehicle door or a seat back or the left side of an operating platform; the projections of the locomotive crew region and the side window region in the horizontal direction are overlapped to meet a certain length. If the conditions are met, the locomotive crew member is judged to be located in the designated driving area, otherwise, the current driving behavior of the locomotive crew member is determined to be off-duty behavior when the locomotive crew member is not located in the designated driving area.

Regarding the illegal use of electronic equipment behavior, when determining whether the locomotive crew member has the illegal use of electronic equipment behavior in the video frame image, as shown in fig. 5, step 201 may include the following steps:

step 501, judging whether any frame of video frame image has designated electronic equipment, if yes, executing step 502;

step 502, judging whether the designated electronic equipment is positioned in the visual field range of the locomotive crew member, if so, executing step 503;

and step 503, determining that the locomotive crew member has illegal electronic equipment using behaviors in the video frame images.

If the specified electronic equipment is judged not to be in the visual field range of the locomotive crew member, namely when the specified electronic equipment is not arranged in the video frame image or the intersection of the visual field coverage area of the locomotive crew member in the video frame image and the specified electronic equipment area does not have enough area, the driving behavior of the locomotive crew member is determined not to be the illegal electronic equipment using behavior in the specified illegal behaviors.

When judging whether the intersection of the visual field coverage area of the locomotive crew in the video frame image and the designated electronic equipment area has enough area, the face area, the head area, the hand area and the arm area in the video frame image can be acquired; determining a visual field region consisting of a face region, a head region, a hand region and an arm region; judging whether the designated electronic equipment is in a visual field area; when the electronic equipment is in the visual field area, the specified electronic equipment is determined to be positioned in the visual field area, namely the intersection of the visual field coverage area of the locomotive crew in the video frame image and the specified electronic equipment has enough area.

Optionally, in this embodiment, the specified electronic device includes a mobile phone, a game machine, an ipad, and the like.

Regarding the head-biased chat behavior, when determining whether the locomotive attendant has the head-biased chat behavior in the video frame image, as shown in fig. 6, step 201 may include the following steps:

601, for any video frame image in the monitoring video, determining the area ratio of a face region and a head region in the video frame image and the aspect ratio of the face region in the video frame image, wherein the face region and the head region belong to a human body key region;

from the image processing angle, the width of the face region is determined according to the horizontal direction of the video frame image, and the height of the face region is determined according to the vertical direction of the video frame image.

Step 602, when the area ratio is larger than the area threshold value or the aspect ratio is larger than the aspect ratio threshold value, it is determined that the locomotive crew member has a bit-end chat behavior in the video frame image.

The area threshold and the aspect ratio threshold can be preset according to the position and angle information of video monitoring in the cab.

Regarding the abnormal door opening behavior, it may be determined whether the locomotive door is safely closed according to the door status of the locomotive in the video frame image, and specifically, as shown in fig. 7, step 201 may include the following steps:

step 701, judging whether a video frame image with the vehicle door in an open state exists in the monitoring video, and if so, executing the step 701;

step 702, determining that the locomotive crew member has abnormal door opening behavior in the video frame image.

In the present application, the above several examples may be executed sequentially, but the order of execution is not limited thereto, and may also be executed independently.

Based on the same concept, the embodiment of the present application provides a device for analyzing violation behaviors of locomotive attendants, the specific implementation of the device may refer to the description of the embodiment part of the method, repeated parts are not repeated, as shown in fig. 8, the device mainly includes:

the acquiring unit 801 is used for acquiring a monitoring video of a locomotive attendant in the locomotive running process;

the detection unit 802 is configured to detect a key area in each video frame image of the monitoring video, where the key area includes a human body key area and a cab key area;

the determining unit 803 is used for determining the violation behaviors of the locomotive crew members according to the key area, wherein the violation behaviors are prohibited behaviors in driving.

Optionally, the determining unit 803 is specifically configured to:

determining the driving behaviors of the locomotive crew in each video frame image according to the key area, wherein the driving behaviors comprise designated violation behaviors or non-designated violation behaviors, and the designated violation behaviors comprise off-Shift behaviors, behaviors of illegally using electronic equipment, wrong-head chatting behaviors or abnormal opening behaviors of a vehicle door;

judging whether the driving behaviors in N continuous video frame images in the monitoring video are all violation behaviors or whether the driving behaviors in P discontinuous video frame images in M continuous video frame images are all appointed violation behaviors;

and if so, determining the violation behaviors of the locomotive crew members as the specified violation behaviors.

Optionally, the determining unit 803 is specifically configured to:

for any frame of video frame image, identifying a side window area, an operation platform area, a door area and a locomotive attendant seat area in the video frame image, wherein the side window area, the operation platform area, the door area and the locomotive attendant seat area belong to a cab key area;

determining a designated driving area formed by a side window area, an operation platform area, a vehicle door area and a locomotive attendant seat area, wherein the designated driving area is a preset area containing the locomotive attendant seat area in a locomotive cab;

when it is determined that the locomotive attendant is not in the designated driving area, it is determined that the locomotive attendant is off duty in the video frame image.

Optionally, the determining unit 803 is specifically configured to:

judging whether any frame of video frame image has a designated electronic device;

if the video frame image has the designated electronic equipment, judging whether the designated electronic equipment is positioned in the visual field range of the locomotive crew;

and if the video frame image is in the visual field range, determining that the locomotive crew member has illegal electronic equipment using behavior in the video frame image.

Optionally, the determining unit 803 is specifically configured to:

acquiring a face area, a head area, a hand area and an arm area in a video frame image;

determining a visual field region consisting of a face region, a head region, a hand region and an arm region;

judging whether the designated electronic equipment is in a visual field area;

when the electronic equipment is in the visual field area, the specified electronic equipment is determined to be positioned in the visual field area.

Optionally, the determining unit 803 is specifically configured to:

for any video frame image in the monitoring video, determining the area ratio of a face region to a head region in the video frame image and the aspect ratio of the face region in the video frame image, wherein the face region and the head region belong to a human body key region;

when the area ratio is greater than the area threshold value or the aspect ratio is greater than the aspect ratio threshold value, it is determined that the locomotive crew member has a bit-wrong chat behavior in the video frame image.

Optionally, the determining unit 803 is specifically configured to:

judging whether a video frame image with the vehicle door in an open state exists in the monitoring video;

if yes, determining that the locomotive crew member has abnormal door opening behavior in the video frame image.

Based on the same concept, an embodiment of the present application further provides a computer device, as shown in fig. 9, the computer device mainly includes: a processor 901, a memory 902 and a communication bus 903, wherein the processor 901 and the memory 902 communicate with each other via the communication bus 903. The memory 902 stores a program executable by the processor 901, and the processor 901 executes the program stored in the memory 902, so as to implement the following steps:

acquiring a monitoring video of a locomotive attendant in the locomotive running process;

detecting key areas in each video frame image of a monitoring video, wherein the key areas comprise key areas of a human body and key areas of a cab;

and determining the violation behaviors of the locomotive crew members according to the key area, wherein the violation behaviors are prohibited behaviors in driving.

The communication bus 903 mentioned in the above electronic entertainment apparatus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus 903 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 9, but this does not indicate only one bus or one type of bus.

The Memory 902 may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Alternatively, the memory may be at least one storage device located remotely from the processor 901.

The Processor 901 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc., and may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.

In yet another embodiment of the present application, there is also provided a computer-readable storage medium having a computer program stored therein, which when run on a computer, causes the computer to execute the method for analyzing locomotive crew violation behavior as described in the above embodiment.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wirelessly (e.g., infrared, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The available media may be magnetic media (e.g., floppy disks, hard disks, tapes, etc.), optical media (e.g., DVDs), or semiconductor media (e.g., solid state drives), among others.

It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.