A method, device and equipment for detecting crowd at a pick-up point in a well

Abstract

The present application relates to a kind of for underground car stop personnel crowded detection method, device and equipment.The method includes: identifying vehicle and personnel in underground car stop image;According to the identification result of vehicle, it is judged whether vehicle is stationary state;Calculate the personnel density of vehicle area;According to personnel density, it is judged whether personnel crowded phenomenon occurs in underground car stop.The technical scheme provided by the present application, through camera acquisition car stop image, and through target recognition algorithm extraction personnel, door and other related feature information, in combination with personnel boarding law, design algorithm for underground car stop personnel crowded scene, relative to traditional artificial monitoring, this algorithm can greatly save manpower and material resources, and the algorithm has real-time, stability, high-precision characteristics.In addition, the scheme does not need to make hardware change to existing camera, reduce the cost of transformation.The present application has strong pertinence, high recognition rate, strong generalization ability and other advantages in underground personnel crowded scene.

Description

Technical Field

[0001] This invention relates to the field of underground traffic safety, and in particular to a method, apparatus, and equipment for detecting crowding at underground boarding points. Background Technology

[0002] Currently, safety supervision of underground boarding points is mostly carried out through on-site supervision by management personnel or remote video monitoring. However, due to personnel oversight and inadequate supervision, the safety of boarding points may not be guaranteed. Summary of the Invention

[0003] To overcome the problems existing in related technologies, the present invention provides a method, device and equipment for detecting crowding at underground boarding points. Based on computer vision algorithms, it can intelligently identify crowding phenomena at underground boarding points, achieve accurate and efficient safety monitoring, ensure the safety of underground boarding, and effectively avoid safety accidents caused by personnel negligence.

[0004] According to a first aspect of the present invention, a method for detecting crowding at underground vehicle boarding points is provided, comprising:

[0005] The acquired images of underground vehicle access points are input into a pre-trained target detection model to identify vehicles and people in the images;

[0006] Determine whether the vehicle is stationary based on the vehicle identification results;

[0007] Calculate the population density in the vehicle area if the vehicle is determined to be stationary.

[0008] The crowd density is used to determine whether overcrowding occurs at the underground boarding point.

[0009] Furthermore, the calculation of the personnel density in the vehicle area specifically includes:

[0010] Calculate the total area S of the personnel area 人 ;

[0011] Calculate the total area S occupied by the personnel area in the vehicle door area. door ;

[0012] Calculate S 人 and S door The intersection and union ratio;

[0013] The population density is obtained by calculating the ratio of the intersection-union ratio to the number of people.

[0014] Furthermore, the total area S of the calculated personnel area 人 Specifically, it includes:

[0015] Calculate the sum of the areas of intersection S between any two people. 交总 ;

[0016] Calculate the total area S of all people 总 ;

[0017] Calculate the total area S of the personnel area 人 =S 总 -S 交总 .

[0018] Furthermore, the total area S occupied by the personnel area in the vehicle door area is... door Specifically, it includes:

[0019] Calculate the average position coordinates of the vehicle door region in N consecutive frames of images, and use them as the door region coordinates;

[0020] By comparing the personnel area coordinates of each person with the door area coordinates, the coordinates of the area occupied by each person in the door area are determined.

[0021] Based on the coordinates of the area occupied by each person in the door area, calculate the total area S occupied by the person area in the vehicle door area. door .

[0022] Furthermore, before calculating the population density in the vehicle area, the following is also included:

[0023] Identify the safety helmets worn by people in images;

[0024] When the number of safety helmets exceeds the set number, the step of calculating the personnel density in the vehicle area is performed.

[0025] According to a second aspect of the present invention, an apparatus for detecting crowding at underground boarding points is provided, comprising:

[0026] The image recognition module is used to input the acquired images of underground vehicle access points into a pre-trained target detection model to identify vehicles and people in the images;

[0027] The vehicle identification module is used to determine whether a vehicle is stationary based on the vehicle identification results.

[0028] The density calculation module is used to calculate the population density in the vehicle area when the vehicle is determined to be stationary.

[0029] The crowding detection module is used to determine whether crowding has occurred at the underground boarding point based on the personnel density.

[0030] Furthermore, the density calculation module specifically includes:

[0031] The first calculation unit is used to calculate the total area S of the personnel area. 人 ;

[0032] The second calculation unit is used to calculate the total area S occupied by the personnel area in the vehicle door area. door ;

[0033] The third calculation unit is used to calculate S. 人 and S door The intersection and union ratio;

[0034] The fourth calculation unit is used to calculate the ratio of the intersection-union ratio to the number of people to obtain the personnel density.

[0035] Furthermore, it also includes:

[0036] The safety helmet recognition module is used to identify the safety helmets worn by people in images;

[0037] The density calculation module is used to calculate the personnel density in the vehicle area when the number of safety helmets identified by the safety helmet recognition module exceeds a set number.

[0038] According to a third aspect of the present invention, a terminal device is provided, comprising:

[0039] Processor; and

[0040] A memory that stores executable code, which, when executed by the processor, causes the processor to perform the method described above.

[0041] According to a fourth aspect of the present invention, a non-transitory machine-readable storage medium is provided, on which executable code is stored, which, when executed by a processor of an electronic device, causes the processor to perform the method described above.

[0042] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0043] By capturing images of boarding points using cameras and extracting relevant features such as people and vehicle doors using target recognition algorithms, and combining this with patterns of people boarding, an algorithm was designed specifically for crowded scenarios at underground boarding points. Compared to traditional manual monitoring, this algorithm can significantly save manpower and resources, and it features real-time performance, stability, and high accuracy. Furthermore, this solution requires no hardware modifications to existing cameras, reducing upgrade costs. This solution offers advantages such as strong targeting, high recognition rate, and strong generalization ability in crowded underground scenarios.

[0044] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0045] The above and other objects, features and advantages of the present invention will become more apparent from the more detailed description of exemplary embodiments of the invention in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the invention.

[0046] Figure 1 This is a flowchart illustrating a method for detecting crowding at underground boarding points according to an exemplary embodiment of the present invention;

[0047] Figure 2 It is a feature map for on-site identification based on target detection algorithms;

[0048] Figure 3 This is a structural block diagram of a device for detecting crowding at underground boarding points according to an exemplary embodiment of the present invention;

[0049] Figure 4 This is a schematic diagram of the structure of a computing device according to an exemplary embodiment of the present invention. Detailed Implementation

[0050] Preferred embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While preferred embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0051] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular forms “a,” “the,” and “the” used in this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0052] It should be understood that although the terms "first," "second," "third," etc., may be used in this invention to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this invention, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Thus, features defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0053] The hardware devices involved in this invention include cameras and GPU servers. The cameras can be existing network cameras in the mining farm, responsible for image acquisition. The GPU server performs algorithm inference and is located in the on-site server room. The technical solutions of the embodiments of this invention are described in detail below with reference to the accompanying drawings.

[0054] Figure 1 This is a flowchart illustrating a method for detecting crowding at underground boarding points according to an exemplary embodiment of the present invention.

[0055] See Figure 1 The method includes:

[0056] 10. Input the acquired images of underground vehicle access points into a pre-trained target detection model to identify vehicles and personnel in the images;

[0057] Specifically, the camera's installation position ensures a complete and clear view of the process of people boarding the vehicle. Through a trained target detection algorithm, feature information such as people and vehicle doors can be extracted from the image, including target name, target location, and target confidence level. For example... Figure 2 As shown.

[0058] 12. Determine whether the vehicle is stationary based on the vehicle identification results;

[0059] Preferably, the vehicle is stationary by comparing the IOU (Intersection over Union) of two adjacent frames of doors to determine whether the vehicle is stationary. In a specific embodiment, when the IOU of two adjacent frames of doors exceeds 90%, it indicates that the vehicle is stationary.

[0060] 14. Calculate the population density in the vehicle area if the vehicle is determined to be stationary.

[0061] Specifically, the calculation process for population density includes steps 141 to 144:

[0062] 141. Calculate the total area S of the personnel area. 人 ;

[0063] The specific calculation process for this step includes steps 1411 to 1413:

[0064] 1411. Calculate the sum S of the areas of intersection between any two people. 交总 ;

[0065] 1412. Calculate the total area S of all the people. 总 ;

[0066] 1413. Calculate the total area S of the personnel area. 人 =S 总 -S 交总 .

[0067] 142. Calculate the total area S occupied by the personnel area in the vehicle door area. door ;

[0068] The specific calculation process for this step includes steps 1421 to 1423:

[0069] 1421. Calculate the average position coordinates of the vehicle door region in N consecutive frames of images, and use them as the door region coordinates;

[0070] 1422. Compare the personnel area coordinates of each person with the door area coordinates to determine the coordinates of the area occupied by each person in the door area;

[0071] 1423. Based on the coordinates of the area occupied by each person in the door area, calculate the total area S occupied by the personnel area in the vehicle door area. door .

[0072] 143. Calculate S 人 and S door The intersection and union ratio;

[0073] 144. Calculate the ratio of the intersection-union ratio to the number of people to obtain the population density.

[0074] 16. Determine whether overcrowding occurs at the underground vehicle boarding point based on the personnel density.

[0075] Specifically, an appropriate threshold is set according to the scenario. For example, in this scenario, it could be set to 0.15-0.25 to determine if the personnel density is within the threshold range. If it is, then congestion is considered to have occurred; otherwise, no congestion has occurred. When congestion occurs in multiple consecutive frames, an on-site alarm is issued. When no congestion occurs in multiple consecutive frames, the on-site alarm is deactivated.

[0076] Furthermore, prior to step 14, the following steps are also included:

[0077] 13. Identify the safety helmets worn by the personnel in the image; when the number of safety helmets exceeds the set number, proceed to step 14.

[0078] Specifically, when a person is detected in the image, due to the angle, the person's center point coordinates may not be within the average position area of ​​the vehicle door. Therefore, it is determined whether the person's safety helmet is within the average position area of ​​the vehicle door. The number of safety helmets is counted as the current number of people boarding the vehicle. When the number of safety helmets appearing in the vehicle door area exceeds the preset number, the personnel density is calculated.

[0079] Figure 3 This is a structural block diagram of an apparatus for detecting crowding at underground boarding points according to an exemplary embodiment of the present invention.

[0080] See Figure 3 The system includes:

[0081] The image recognition module is used to input the acquired images of underground vehicle access points into a pre-trained target detection model to identify vehicles and people in the images;

[0082] The vehicle identification module is used to determine whether a vehicle is stationary based on the vehicle identification results.

[0083] The density calculation module is used to calculate the population density in the vehicle area when the vehicle is determined to be stationary.

[0084] The crowding detection module is used to determine whether crowding has occurred at the underground boarding point based on the personnel density.

[0085] Optionally, in this embodiment, the density calculation module specifically includes:

[0086] The first calculation unit is used to calculate the total area S of the personnel area. 人 ;

[0087] The second calculation unit is used to calculate the total area S occupied by the personnel area in the vehicle door area. door ;

[0088] The third calculation unit is used to calculate S. 人 and S door The intersection and union ratio;

[0089] The fourth calculation unit is used to calculate the ratio of the intersection-union ratio to the number of people to obtain the personnel density.

[0090] Optionally, in this embodiment, the device further includes:

[0091] The safety helmet recognition module is used to identify the safety helmets worn by people in images;

[0092] The density calculation module is used to calculate the personnel density in the vehicle area when the number of safety helmets identified by the safety helmet recognition module exceeds a set number.

[0093] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated further here.

[0094] Figure 4 This is a schematic diagram of the structure of a computing device according to an exemplary embodiment of the present invention.

[0095] See Figure 4 The computing device 400 includes a memory 410 and a processor 420.

[0096] The processor 420 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0097] Memory 410 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. ROM may store static data or instructions required by processor 420 or other modules of the computer. Permanent storage devices may be read-write storage devices. Permanent storage devices may be non-volatile storage devices that retain stored instructions and data even when the computer is powered off. In some embodiments, permanent storage devices use mass storage devices (e.g., magnetic or optical disks, flash memory) as permanent storage devices. In other embodiments, permanent storage devices may be removable storage devices (e.g., floppy disks, optical drives). System memory may be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory. System memory may store some or all of the instructions and data required by the processor during operation. Furthermore, memory 410 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, memory 410 may include a removable storage device that is readable and / or writable, such as a laser disc (CD), a read-only digital multifunction optical disc (e.g., DVD-ROM, dual-layer DVD-ROM), a read-only Blu-ray disc, an ultra-high density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not contain carrier waves or transient electronic signals transmitted wirelessly or via wired connections.

[0098] The memory 410 stores executable code, which, when processed by the processor 420, can cause the processor 420 to execute part or all of the methods described above.

[0099] Furthermore, the method according to the present invention can also be implemented as a computer program or computer program product, which includes computer program code instructions for performing some or all of the steps in the above-described method of the present invention.

[0100] Alternatively, the present invention can also be implemented as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) storing executable code (or computer program, or computer instruction code) that, when executed by a processor of an electronic device (or computing device, server, etc.), causes the processor to perform some or all of the steps of the method described above according to the present invention.

[0101] The present invention has been described in detail above with reference to the accompanying drawings. In the above embodiments, the descriptions of each embodiment have their own emphasis; for parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. Those skilled in the art should also understand that the actions and modules involved in the specification are not necessarily essential to the present invention. Furthermore, it is understood that the steps in the method of the embodiments of the present invention can be adjusted, combined, and deleted according to actual needs, and the modules in the device of the embodiments of the present invention can be combined, divided, and deleted according to actual needs.

[0102] Those skilled in the art will also understand that the various exemplary logic blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein can be implemented as electronic hardware, computer software, or a combination of both.

[0103] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0104] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for detecting crowding at underground vehicle boarding points, characterized in that, include: The acquired images of underground vehicle access points are input into a pre-trained target detection model to identify vehicles and people in the images; Determine whether the vehicle is stationary based on the vehicle identification results; Calculate the population density in the vehicle area if the vehicle is determined to be stationary. Based on the personnel density, determine whether overcrowding is occurring at the underground vehicle boarding point; Specifically, calculating the personnel density in the vehicle area includes: Calculate the total area of ​​the personnel area ; Calculate the total area occupied by the personnel area in the vehicle door area. ; calculate and The intersection and union ratio; Calculate the ratio of the intersection-union ratio to the number of people to obtain the population density; The total area of ​​the calculation personnel area Specifically, it includes: Calculate the sum of the areas of intersection between each pair of people. ; Calculate the total area of ​​all people. ; Calculate the total area of ​​the personnel area ; The total area occupied by the personnel area in the vehicle door area. Specifically, it includes: Calculate the average position coordinates of the vehicle door region in N consecutive frames of images, and use them as the door region coordinates; By comparing the personnel area coordinates of each person with the door area coordinates, the coordinates of the area occupied by each person in the door area are determined. Based on the coordinates of the area occupied by each person in the door area, calculate the total area occupied by the person area in the vehicle's door area. .

2. The method according to claim 1, characterized in that, Before calculating the population density in the vehicle area, the following is also included: Identify the safety helmets worn by people in images; When the number of safety helmets exceeds the set number, the step of calculating the personnel density in the vehicle area is performed.

3. A device for detecting crowding at underground vehicle boarding points, characterized in that, include: The image recognition module is used to input the acquired images of underground vehicle access points into a pre-trained target detection model to identify vehicles and people in the images; The vehicle identification module is used to determine whether a vehicle is stationary based on the vehicle identification results. The density calculation module is used to calculate the population density in the vehicle area when the vehicle is determined to be stationary. The crowding detection module is used to determine whether crowding has occurred at the underground vehicle boarding point based on the personnel density. The density calculation module specifically includes: The first calculation unit is used to calculate the total area of ​​the personnel area. ; The second calculation unit is used to calculate the total area occupied by the personnel area in the vehicle door area. ; The third calculation unit is used for calculation. and The intersection and union ratio; The fourth calculation unit is used to calculate the ratio of the intersection-union ratio to the number of people to obtain the population density; The first computing unit is specifically used for: Calculate the sum of the areas of intersection between each pair of people. ; Calculate the total area of ​​all people. ; Calculate the total area of ​​the personnel area ; The second computing unit is specifically used for: Calculate the average position coordinates of the vehicle door region in N consecutive frames of images, and use them as the door region coordinates; By comparing the personnel area coordinates of each person with the door area coordinates, the coordinates of the area occupied by each person in the door area are determined. Based on the coordinates of the area occupied by each person in the door area, calculate the total area occupied by the person area in the vehicle's door area. .

4. The apparatus according to claim 3, characterized in that, Also includes: The safety helmet recognition module is used to identify the safety helmets worn by people in images; The density calculation module is used to calculate the personnel density in the vehicle area when the number of safety helmets identified by the safety helmet recognition module exceeds a set number.

5. A terminal device, characterized in that, include: processor; as well as A memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method as described in claim 1 or 2.

6. A non-transitory machine-readable storage medium having executable code stored thereon, characterized in that, When the executable code is executed by the processor of the electronic device, the processor performs the method as described in claim 1 or 2.

Images