Carriage congestion detection method and system

Abstract

The present invention discloses a method, medium, device and system for detecting the degree of congestion in a carriage, wherein the method comprises: obtaining a video of the environment in a carriage, and performing frame processing on the video of the environment in the carriage to generate an image of the environment in the carriage corresponding to the video of the environment in the carriage; inputting the image of the environment in the carriage into a pre-trained carriage congestion analysis model to calculate the degree of congestion in the carriage corresponding to the image of the environment in the carriage through the carriage congestion analysis model; and being able to detect the degree of congestion in the carriage of a public transport vehicle in real time to accurately obtain the degree of congestion in the carriage, thereby facilitating the dispatch of the public transport vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of public transportation scheduling, and in particular to a carriage congestion detection method, a computer-readable storage medium, a computer device and a carriage congestion detection system. Background Art

[0002] With the deepening development of industrialization, informatization and urbanization, people have higher expectations for improving the supply capacity and service quality of public transportation.

[0003] In the related technologies, public transportation enterprises usually dispatch public transportation vehicles manually based on experience (for example, whether it is a weekday, whether it is a peak period, etc.). Due to the uncertainty of manual judgment, public transportation dispatch is often unreasonable, which in turn leads to a waste of public transportation resources, or causes the public to have a poor experience of public transportation due to congestion, affecting the public's travel satisfaction. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems in the above-mentioned technology to a certain extent. To this end, one purpose of the present invention is to propose a method for detecting the crowdedness of a carriage, which can detect the crowdedness of a public transportation vehicle in real time, so as to accurately obtain the crowdedness of the carriage and facilitate the dispatch of the public transportation vehicle.

[0005] A second object of the present invention is to provide a computer-readable storage medium.

[0006] A third object of the present invention is to provide a computer device.

[0007] The fourth object of the present invention is to provide a carriage congestion detection system.

[0008] To achieve the above-mentioned purpose, a first aspect of the present invention proposes a method for detecting car congestion, comprising the following steps: acquiring a car interior environment video, and performing frame processing on the car interior environment video to generate a car interior environment image corresponding to the car interior environment video; inputting the car interior environment image into a pre-trained car congestion analysis model to calculate the car congestion corresponding to the car interior environment image through the car congestion analysis model.

[0009] According to the method for detecting cabin congestion of an embodiment of the present invention, first, a cabin environment video is obtained, and the cabin environment video is frame-processed to decompose the cabin environment video into multiple cabin environment images corresponding to the cabin environment video; then, the cabin environment image is input into a pre-trained cabin congestion analysis model, and the cabin congestion analysis model can calculate the cabin congestion corresponding to the cabin environment image based on the cabin environment image after receiving the cabin environment image; thereby, real-time detection of the cabin congestion of public transportation vehicles is realized to accurately obtain the cabin congestion, which is convenient for the scheduling of public transportation vehicles.

[0010] In addition, the carriage congestion detection method proposed in the above embodiment of the present invention may also have the following additional technical features:

[0011] Optionally, before obtaining the in-cabin environment video, it also includes: obtaining detection images captured by all cameras installed on the vehicle, and inputting the detection images captured by each camera into a pre-trained camera position analysis model, so as to determine whether the camera is an in-cabin environment video capture camera through the camera position analysis model; if the camera is an in-cabin environment capture camera, the video captured by the camera is used as the in-cabin environment video.

[0012] Optionally, the camera position analysis model also determines the in-car position corresponding to the in-car environment acquisition camera based on the detection image, so as to determine the corresponding in-car congestion analysis model based on the in-car position corresponding to the in-car environment acquisition camera.

[0013] Optionally, the method further includes: sending the carriage congestion corresponding to each vehicle to a dispatching system so that the dispatching system dispatches the vehicle according to the carriage congestion.

[0014] Optionally, the method further includes: sending the cabin congestion corresponding to each vehicle to a cloud platform so that the cloud platform can visualize the cabin congestion.

[0015] To achieve the above objectives, a second aspect of the present invention provides a computer-readable storage medium on which a car congestion detection program is stored. When the car congestion detection program is executed by a processor, the car congestion detection method as described above is implemented.

[0016] According to the computer-readable storage medium of an embodiment of the present invention, by storing a car crowding detection program, the processor implements the car crowding detection method as described above when executing the car crowding detection program, thereby realizing real-time detection of the crowding in the car of a public transportation vehicle, so as to accurately obtain the car crowding and facilitate the scheduling of public transportation vehicles.

[0017] To achieve the above-mentioned purpose, a third aspect of the present invention proposes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the above-mentioned car congestion detection method is implemented.

[0018] According to the computer device of an embodiment of the present invention, the car crowding detection program is stored in the memory, so that when the processor executes the car crowding detection program, the car crowding detection method as described above is implemented, thereby realizing real-time detection of the crowding in the public transportation vehicle car, so as to accurately obtain the car crowding and facilitate the scheduling of public transportation vehicles.

[0019] To achieve the above-mentioned purpose, the fourth aspect of the present invention proposes a car congestion detection system, including: an acquisition module, the acquisition module is used to acquire a car interior environment video, and frame-process the car interior environment video to generate a car interior environment image corresponding to the car interior environment video; a first detection module, the first detection module is used to input the car interior environment image into a pre-trained car congestion analysis model to calculate the car congestion corresponding to the car interior environment image through the car congestion analysis model.

[0020] According to the carriage congestion detection system of the embodiment of the present invention, an acquisition module is set to acquire a carriage interior environment video, and the carriage interior environment video is frame-processed to generate a carriage interior environment image corresponding to the carriage interior environment video; the first detection module is used to input the carriage interior environment image into a pre-trained carriage congestion analysis model, so as to calculate the carriage congestion corresponding to the carriage interior environment image through the carriage congestion analysis model; thereby, real-time detection of the carriage congestion of public transportation vehicles is realized, so as to accurately obtain the carriage congestion and facilitate the scheduling of public transportation vehicles.

[0021] In addition, the carriage congestion detection system proposed in the above embodiment of the present invention may also have the following additional technical features:

[0022] Optionally, it also includes a second detection module, which is used to obtain detection images collected by all cameras installed on the vehicle before obtaining the in-cabin environment video, and input the detection images collected by each camera into a pre-trained camera position analysis model, so as to determine whether the camera is an in-cabin environment video collection camera through the camera position analysis model; the second detection module is also used to use the video collected by the camera as the in-cabin environment video when the camera is an in-cabin environment collection camera.

[0023] Optionally, the camera position analysis model also determines the in-car position corresponding to the in-car environment acquisition camera based on the detection image, so as to determine the corresponding in-car congestion analysis model based on the in-car position corresponding to the in-car environment acquisition camera. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic diagram of a flow chart of a method for detecting carriage congestion according to an embodiment of the present invention;

[0025] Figure 2 is a flow chart of a method for detecting carriage congestion according to another embodiment of the present invention;

[0026] Figure 3 4 is a block diagram of a system for detecting carriage congestion according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0028] In the related art, public transportation vehicles are mostly dispatched manually based on experience, which leads to unreasonable dispatch. According to the method for detecting the cabin congestion of an embodiment of the present invention, first, a cabin environment video is obtained, and the cabin environment video is frame-processed to decompose the cabin environment video into multiple cabin environment images corresponding to the cabin environment video; then, the cabin environment image is input into a pre-trained cabin congestion analysis model, and the cabin congestion analysis model can calculate the cabin congestion corresponding to the cabin environment image according to the cabin environment image after receiving the cabin environment image; thereby, real-time detection of the cabin congestion of public transportation vehicles is achieved to accurately obtain the cabin congestion, which is convenient for dispatching public transportation vehicles.

[0029] In order to better understand the above technical solution, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0030] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0031] Figure 1 FIG. 1 is a flow chart of a method for detecting carriage congestion according to an embodiment of the present invention. Figure 1 As shown, the carriage congestion detection method includes the following steps:

[0032] S101, obtaining a vehicle interior environment video, and performing frame processing on the vehicle interior environment video to generate a vehicle interior environment image corresponding to the vehicle interior environment video.

[0033] That is, firstly, the interior environment video of a public transportation vehicle (eg, a bus, a BRT vehicle, etc.) is acquired; then, the interior environment video is frame-processed to decompose the interior environment video into interior environment images corresponding to the interior environment video.

[0034] In some embodiments, in order to reduce data transmission traffic, save computing power, and improve the accuracy of detection results, the vehicle congestion detection method proposed in the embodiment of the present invention further includes:

[0035] Obtain detection images collected by all cameras installed in the vehicle, and input the detection images collected by each camera into a pre-trained camera position analysis model, so as to determine whether the camera is a camera for collecting video of the vehicle environment through the camera position analysis model;

[0036] If the camera is a camera for collecting the environment in the vehicle cabin, the video collected by the camera is used as the video of the environment in the vehicle cabin.

[0037] It can be understood that public transportation vehicles are equipped with multiple cameras, some of which are used to collect images of the interior environment of the vehicle (for example, cockpit cameras, front cameras, middle door cameras and rear cameras, etc.); and some images are used to collect images of the exterior environment of the vehicle (for example, reversing image cameras, image collection cameras on both sides of the vehicle and cameras for collecting images of the exterior domain of the front of the vehicle, etc.); therefore, in order to avoid unnecessary calculations; first, when the vehicle is running, control the multiple cameras loaded on the public transportation vehicle to collect detection images, and then input the detection images collected by each camera into the pre-trained camera position analysis model respectively, then the camera position analysis model can determine whether the camera is an interior environment video collection camera according to the input detection image, and if so, use the video collected by the camera as the interior environment video, so as to subsequently analyze the congestion of the vehicle based on the interior environment video.

[0038] It should be noted that in order to save computing power, the judgment of whether a camera is a camera for collecting video of the vehicle's interior environment only needs to be performed when the vehicle is initially running; and after the judgment is completed, it is only necessary to add a uniquely identifiable identifier to the corresponding camera based on the judgment result; and then the camera can be judged whether it is a camera for collecting video of the vehicle's interior environment based on the uniquely identifiable identifier.

[0039] In some embodiments, in order to further improve the accuracy of the final cabin congestion result obtained by the cabin congestion detection method proposed in the embodiments of the present invention; the camera position analysis model also determines the cabin position corresponding to the cabin environment acquisition camera based on the detection image, so as to determine the corresponding cabin congestion analysis model based on the cabin environment acquisition camera's cabin position corresponding to the cabin.

[0040] That is, the camera position analysis model is further used to determine the position in the cabin corresponding to the camera for collecting the cabin environment (for example, the camera is a door camera, a front camera, a cockpit camera, etc.) according to the detection image collected by each camera; at the same time, when training the cabin congestion analysis model, the model is trained according to the historical information of cameras at different positions to generate cabin congestion analysis models corresponding to different positions (for example, a door congestion analysis model, a front congestion analysis model, and a rear congestion analysis model, etc.); further, the corresponding cabin congestion analysis model can be determined according to the position corresponding to each cabin environment collection camera in the subsequent process, so as to calculate the congestion corresponding to the camera according to the corresponding cabin congestion analysis model.

[0041] It should be noted that the training method of the camera position analysis model has been fully documented in the prior art and will not be elaborated here.

[0042] S102, inputting the cabin environment image into a pre-trained cabin congestion analysis model to calculate the cabin congestion corresponding to the cabin environment image through the cabin congestion analysis model.

[0043] That is, after acquiring the interior environment image of the vehicle cabin, the interior environment image of the vehicle cabin is input into a pre-trained vehicle cabin congestion analysis model, and the vehicle cabin congestion analysis model can calculate the corresponding vehicle cabin congestion according to the interior environment image of the vehicle cabin.

[0044] It should be noted that the training method of the analysis model has been described in detail in the prior art and will not be repeated here.

[0045] As an example, first, historical pictures of different positions in the carriage are obtained, and a training set is formed based on the historical pictures corresponding to different positions, and a carriage congestion analysis model is trained based on the training set to form a carriage congestion analysis model corresponding to each position.

[0046] In some embodiments, in order to facilitate management personnel to dispatch public transportation vehicles according to the carriage congestion, the carriage congestion detection method proposed in the embodiment of the present invention also includes: sending the carriage congestion corresponding to each vehicle to the dispatching system, so that the dispatching system dispatches the vehicle according to the carriage congestion.

[0047] There are many ways in which the dispatching system can calculate the degree of congestion in the carriage to provide dispatching basis for relevant personnel.

[0048] As an example, a congestion threshold corresponding to each camera position is set respectively; after the congestion corresponding to the environment image inside the vehicle is calculated, it is determined whether the congestion is greater than the congestion threshold according to its position; if so, a corresponding alarm message is generated so that the dispatcher can make reasonable dispatch of the current congestion situation.

[0049] As another example, first, a weight value corresponding to the congestion of each camera is set according to the position of the camera. Then, after obtaining the congestion corresponding to the interior environment image captured by each camera of the public transportation vehicle, a weighted average is performed on all congestion according to the corresponding weight value, so as to take the weighted average as the congestion corresponding to the public transportation vehicle; then, it is determined whether the congestion corresponding to the public transportation vehicle is greater than a preset congestion threshold; if so, a corresponding congestion alarm is generated so that relevant personnel can perform scheduling according to the alarm.

[0050] In some embodiments, in order to make the congestion calculation results convenient for public travel, the carriage congestion detection method proposed in the embodiment of the present invention also includes: sending the carriage congestion corresponding to each vehicle to the cloud platform so that the cloud platform can visualize the carriage congestion.

[0051] That is to say, after the carriage crowdedness is calculated, the carriage crowdedness is further visualized (for example, when the public connects to the cloud platform through their mobile terminals, they can make choices based on their own travel departure and destination through the cloud platform; then, the cloud platform can query the public transportation routes that can be taken between the two places based on the departure and destination; then, when the user clicks on one of the public transportation routes, the cloud platform can visualize the congestion corresponding to each vehicle traveling on the public transportation route.); thus, when the public obtains the congestion information corresponding to the vehicle, they can choose their own travel route based on the obtained congestion information; so as to improve the public's travel experience and increase the public's satisfaction with public transportation.

[0052] like Figure 2As shown, in a specific embodiment of the present invention, the carriage congestion detection method includes the following steps:

[0053] S201, acquiring detection images collected by all cameras, and inputting the detection images collected by each camera into a pre-trained camera position analysis model.

[0054] S202, the camera position analysis model determines whether the camera is a camera for collecting video of the vehicle interior environment based on the detected image; if yes, execute step S203.

[0055] S203, using the video captured by the camera as the vehicle interior environment video.

[0056] S204, the camera position analysis model determines the position in the cabin corresponding to the cabin environment acquisition camera according to the detection image, and determines the corresponding cabin congestion analysis model according to each cabin environment acquisition camera.

[0057] S205, acquiring a vehicle interior environment video, and performing frame processing on the vehicle interior environment video to generate a vehicle interior environment image corresponding to the vehicle interior environment video.

[0058] S206, inputting the cabin environment image into a corresponding pre-trained cabin congestion analysis model, so as to calculate the cabin congestion corresponding to the cabin environment image through the cabin congestion analysis model.

[0059] S207, calculating the compartment congestion degree corresponding to the vehicle according to the compartment congestion degree corresponding to the interior environment image of the compartment, and sending the compartment congestion degree corresponding to the vehicle to the dispatching system so that the dispatching system dispatches the vehicle according to the compartment congestion degree.

[0060] S208, sending the cabin congestion corresponding to each vehicle to the cloud platform so that the cloud platform can visualize the cabin congestion.

[0061] In summary, according to the method for detecting cabin congestion according to an embodiment of the present invention, first, a cabin environment video is obtained, and the cabin environment video is frame-processed to decompose the cabin environment video into multiple cabin environment images corresponding to the cabin environment video; then, the cabin environment image is input into a pre-trained cabin congestion analysis model, and the cabin congestion analysis model can calculate the cabin congestion corresponding to the cabin environment image according to the cabin environment image after receiving the cabin environment image; thereby, real-time detection of the cabin congestion of public transportation vehicles is realized to accurately obtain the cabin congestion, which is convenient for the scheduling of public transportation vehicles.

[0062] In order to implement the above embodiment, the embodiment of the present invention proposes a computer-readable storage medium, on which a car congestion detection program is stored. When the car congestion detection program is executed by a processor, the car congestion detection method as described above is implemented.

[0063] According to the computer-readable storage medium of an embodiment of the present invention, by storing a car crowding detection program, the processor implements the car crowding detection method as described above when executing the car crowding detection program, thereby realizing real-time detection of the crowding in the car of a public transportation vehicle, so as to accurately obtain the car crowding and facilitate the scheduling of public transportation vehicles.

[0064] In order to implement the above embodiment, an embodiment of the present invention proposes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned car congestion detection method is implemented.

[0065] According to the computer device of an embodiment of the present invention, the car crowding detection program is stored in the memory, so that when the processor executes the car crowding detection program, the car crowding detection method as described above is implemented, thereby realizing real-time detection of the crowding in the public transportation vehicle car, so as to accurately obtain the car crowding and facilitate the scheduling of public transportation vehicles.

[0066] In order to implement the above embodiment, the embodiment of the present invention proposes a carriage congestion detection system, such as Figure 3 As shown, the carriage congestion detection system includes: an acquisition module 10 and a first detection module 20.

[0067] The acquisition module 10 is used to acquire the vehicle interior environment video and perform frame processing on the vehicle interior environment video to generate a vehicle interior environment image corresponding to the vehicle interior environment video;

[0068] The first detection module is used to input the interior environment image of the vehicle compartment into a pre-trained vehicle compartment crowding analysis model, so as to calculate the vehicle compartment crowding corresponding to the interior environment image through the vehicle compartment crowding analysis model.

[0069] In some embodiments, the vehicle compartment congestion detection system proposed in the embodiments of the present invention also includes a second detection module (not shown in the figure), which is used to obtain detection images collected by all cameras installed on the vehicle before obtaining the vehicle compartment environment video, and input the detection images collected by each camera into a pre-trained camera position analysis model, so as to determine whether the camera is a vehicle compartment environment video collection camera through the camera position analysis model; the second detection module is also used to use the video collected by the camera as the vehicle compartment environment video when the camera is a vehicle compartment environment collection camera.

[0070] In some embodiments, the camera position analysis model also determines the in-car position corresponding to the in-car environment acquisition camera based on the detection image, so as to determine the corresponding in-car congestion analysis model based on the in-car position corresponding to the in-car environment acquisition camera.

[0071] It should be noted that the above Figure 1 and Figure 2 The description of the carriage congestion detection method is also applicable to the carriage congestion detection system, which will not be repeated here.

[0072] In summary, according to the carriage congestion detection system of the embodiment of the present invention, an acquisition module is set to acquire the carriage environment video, and the carriage environment video is frame-processed to generate a carriage environment image corresponding to the carriage environment video; the first detection module is used to input the carriage environment image into a pre-trained carriage congestion analysis model, so as to calculate the carriage congestion corresponding to the carriage environment image through the carriage congestion analysis model; thereby, real-time detection of the carriage congestion of public transportation vehicles is realized, so as to accurately obtain the carriage congestion and facilitate the scheduling of public transportation vehicles.

[0073] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0074] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0075] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0076] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0077] It should be noted that in the claims, any reference signs placed between brackets shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claim. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names.

[0078] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0079] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0080] In the description of the present invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0081] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0082] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0083] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms should not be understood as necessarily referring to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0084] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for detecting carriage congestion, characterized in that: The following steps are involved: Acquire a vehicle interior environment video, and perform frame processing on the vehicle interior environment video to generate a vehicle interior environment image corresponding to the vehicle interior environment video; Inputting the cabin environment image into a pre-trained cabin crowding analysis model to calculate the cabin crowding corresponding to the cabin environment image through the cabin crowding analysis model; Before obtaining the in-cabin environment video, it also includes: When the vehicle is initially running, the detection images collected by all cameras installed in the vehicle are obtained, and the detection images collected by each camera are respectively input into a pre-trained camera position analysis model, so as to determine whether the camera is a camera for collecting video of the vehicle environment through the camera position analysis model; If the camera is a camera for collecting the environment in the vehicle cabin, the video collected by the camera is used as the video of the environment in the vehicle cabin; The camera position analysis model further determines the position in the compartment corresponding to the in-compartment environment acquisition camera according to the detection image, so as to determine the corresponding compartment congestion analysis model according to the position in the compartment corresponding to the in-compartment environment acquisition camera; The method further includes: setting a weight value corresponding to the congestion degree of each camera according to the position of the camera, and sending the congestion degree of the carriage corresponding to each vehicle to the dispatching system, so that after the dispatching system obtains the congestion degree corresponding to the carriage environment image collected by each camera of the public transportation vehicle, it performs weighted averaging on all congestion degrees according to the corresponding weight value, and uses the weighted average value as the congestion degree corresponding to the public transportation vehicle, and determines whether the congestion degree corresponding to the public transportation vehicle is greater than a preset congestion threshold value, and if so, generates a corresponding congestion alarm, so that the dispatching personnel can perform dispatching according to the congestion alarm; The method further comprises: The congestion degree corresponding to each vehicle is sent to the cloud platform. When the user connects to the cloud platform through his mobile terminal, he makes a choice through the cloud platform based on the departure and destination of his trip. The cloud platform queries the public transportation routes available between the two places based on the departure and destination. When the user clicks on one of the public transportation routes, the cloud platform visualizes the congestion degree corresponding to each driving vehicle corresponding to the public transportation route.

2. A computer-readable storage medium, characterized in that: A carriage congestion detection program is stored thereon, and when the carriage congestion detection program is executed by the processor, the carriage congestion detection method as claimed in claim 1 is implemented.

3. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the vehicle compartment congestion detection method as claimed in claim 1 is implemented.

4. A carriage congestion detection system, characterized in that: include: An acquisition module, the acquisition module is used to acquire a video of the interior environment of the vehicle compartment, and perform frame processing on the video of the interior environment of the vehicle compartment to generate an image of the interior environment of the vehicle compartment corresponding to the video of the interior environment of the vehicle compartment; a first detection module, the first detection module is used to input the cabin environment image into a pre-trained cabin crowding analysis model, so as to calculate the cabin crowding corresponding to the cabin environment image through the cabin crowding analysis model; set the weight value corresponding to the crowding of each camera according to the position of the camera, and send the cabin crowding corresponding to each vehicle to the dispatching system, so that after the dispatching system obtains the crowding corresponding to the cabin environment image collected by each camera of the public transportation vehicle, it performs weighted average on all crowding according to the corresponding weight value, and uses the weighted average as the crowding corresponding to the public transportation vehicle, and determines whether the crowding corresponding to the public transportation vehicle is greater than a preset crowding threshold. If so, a corresponding crowding alarm is generated so that the dispatching personnel can perform dispatching according to the crowding alarm; send the crowding corresponding to each vehicle to the cloud platform, and when the user connects to the cloud platform through his mobile terminal, the cloud platform selects according to the departure and destination of his own travel, and the cloud platform queries the public transportation routes that can be taken between the two places according to the departure and destination. When the user clicks on one of the public transportation routes, the cloud platform visualizes the crowding corresponding to each driving vehicle corresponding to the public transportation route; The system further includes a second detection module, which is used to obtain detection images collected by all cameras installed on the vehicle before obtaining the vehicle interior environment video when the vehicle is initially running, and input the detection images collected by each camera into a pre-trained camera position analysis model to determine whether the camera is a vehicle interior environment video collection camera through the camera position analysis model; The second detection module is further configured to use the video captured by the camera as the in-car environment video when the camera is an in-car environment acquisition camera; The camera position analysis model also determines the in-car position corresponding to the in-car environment acquisition camera based on the detection image, so as to determine the corresponding in-car congestion analysis model based on the in-car position corresponding to the in-car environment acquisition camera.

Images