Vehicle access control method and system based on infrared analysis

Abstract

The application discloses a vehicle access control method and system based on infrared analysis, wherein the method comprises the following steps: performing infrared image analysis and processing on a target vehicle to be accessed by an infrared device to obtain first analysis features; performing feature extraction processing on the target vehicle to obtain a vehicle identification code; after the target vehicle enters, performing tracking processing on the target vehicle according to the vehicle identification code to obtain a vehicle moving track; when the target vehicle leaves, performing infrared image analysis and processing on the target vehicle by the infrared device again to obtain second analysis features; performing vehicle personnel comparison processing on the second analysis features according to the first analysis features in combination with the vehicle moving track to obtain a comparison result; and when the comparison result is abnormal, issuing an abnormal alarm. The application can improve the efficiency of access control, reduce the labor cost, and can be widely applied in the technical field of access control.

Description

Technical Field

[0001] This invention relates to the field of access control technology, and in particular to a vehicle access control method and system based on infrared analysis. Background Technology

[0002] For communities or venues under closed management, strict control over personnel and vehicles entering and exiting is necessary. Currently, vehicle access control at entrances and exits only involves checking license plates, requiring passengers in the vehicle to present entry and exit permits. For individuals hiding, manual inspection is required, either by boarding the vehicle or using under-vehicle detection devices to capture images of the underside, which is time-consuming and labor-intensive. This inspection method is also prone to inaccuracies and increased human resource costs. In summary, the technical problems existing in these technologies urgently need to be solved. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a vehicle access control method and system based on infrared analysis to improve the accuracy of control.

[0004] On the one hand, the present invention provides a vehicle access control method based on infrared analysis, comprising:

[0005] The infrared image of the target vehicle to be entered is analyzed and processed by infrared equipment to obtain the first analysis feature, which is used to characterize the vehicle and personnel characteristics of the target vehicle when it enters.

[0006] The target vehicle is subjected to feature extraction processing to obtain the vehicle identification code;

[0007] After the target vehicle enters, the target vehicle is tracked according to the vehicle identification code to obtain the vehicle's movement trajectory;

[0008] When the target vehicle leaves, the infrared image of the target vehicle is analyzed again by the infrared device to obtain a second analysis feature. The second analysis feature is used to characterize the vehicle and personnel characteristics of the target vehicle when it leaves.

[0009] Based on the vehicle movement trajectory, the second analysis feature is compared with the first analysis feature to obtain the comparison result;

[0010] An anomaly alarm is issued when the comparison results are abnormal.

[0011] Optionally, the infrared image analysis of the target vehicle to be entered, performed using an infrared device to obtain the first analytical feature, includes:

[0012] An infrared image is obtained by performing infrared radiation imaging processing on the target vehicle using an infrared device.

[0013] The infrared image is input into the posture recognition model for human posture detection processing to obtain the posture recognition result.

[0014] The infrared image is input into the people estimation model for people counting processing to obtain the people estimation result;

[0015] The posture recognition result and the number of people estimation result are determined as the first analytical features.

[0016] Optionally, the step of inputting the infrared image into the pose recognition model for human pose detection processing to obtain the pose recognition result includes:

[0017] Input the infrared image into the posture recognition model;

[0018] The pose recognition model is used to perform position prediction processing on the key points of the infrared image to obtain a prediction confidence map and a vector field.

[0019] The predicted confidence map and the vector field are encoded using a greedy analysis algorithm to obtain the associated vector field;

[0020] A confidence analysis is performed on the associated vector field, and key points of the infrared image are marked based on the confidence analysis results to obtain the pose recognition result.

[0021] Optionally, the step of inputting the infrared image into the people estimation model for people counting processing to obtain the people estimation result includes:

[0022] The infrared image is input into the population estimation model;

[0023] The infrared image is processed by head feature extraction to obtain a crowd density map;

[0024] The population density map is processed by density map integral calculation to obtain the population estimation result.

[0025] Optionally, the step of performing feature extraction processing on the target vehicle to obtain a vehicle identification code includes:

[0026] Obtain the license plate number of the target vehicle;

[0027] The target vehicle is subjected to feature extraction processing to obtain vehicle features;

[0028] The extracted vehicle features and license plate number are used to generate an identifier, resulting in a vehicle identification code.

[0029] Optionally, the step of tracking the target vehicle based on the vehicle identification code to obtain the vehicle's movement trajectory includes:

[0030] Acquire video data from the camera;

[0031] The video data is processed using the vehicle identification code to obtain the vehicle's location;

[0032] The video data is processed by feature extraction according to the target tracking algorithm, and the extracted feature vectors are processed by similarity matching to obtain the vehicle trajectory sequence;

[0033] Based on the vehicle's location, the vehicle trajectory sequence is analyzed to obtain the vehicle's movement trajectory.

[0034] Optionally, the step of performing dwell analysis on the vehicle trajectory sequence based on the vehicle location to obtain the vehicle movement trajectory includes:

[0035] The vehicle trajectory sequence is subjected to time analysis processing to obtain the trajectory time sequence;

[0036] Based on the vehicle's location, the trajectory time series is analyzed for movement distance to obtain the dwell time analysis results.

[0037] The vehicle trajectory sequence is updated based on the dwell analysis results to obtain the vehicle movement trajectory.

[0038] On the other hand, embodiments of the present invention also provide a vehicle access control system based on infrared analysis, comprising:

[0039] The first module is used to perform infrared image analysis and processing on the target vehicle to be entered by infrared equipment to obtain the first analysis feature, which is used to characterize the vehicle and personnel characteristics of the target vehicle when it enters.

[0040] The second module is used to perform feature extraction processing on the target vehicle to obtain the vehicle identification code;

[0041] The third module is used to track the target vehicle based on the vehicle identification code after the target vehicle enters, and obtain the vehicle's movement trajectory.

[0042] The fourth module is used to perform infrared image analysis on the target vehicle again through the infrared device when the target vehicle leaves, to obtain a second analysis feature. The second analysis feature is used to characterize the vehicle and personnel characteristics of the target vehicle when it leaves.

[0043] The fifth module is used to combine the vehicle movement trajectory and perform vehicle and personnel comparison processing on the second analysis feature based on the first analysis feature to obtain the comparison result;

[0044] The sixth module is used to issue an anomaly alarm when the comparison results are abnormal.

[0045] On the other hand, embodiments of the present invention also disclose an electronic device, including a processor and a memory;

[0046] The memory is used to store programs;

[0047] The processor executes the program to implement the method described above.

[0048] On the other hand, embodiments of the present invention also disclose a computer-readable storage medium storing a program that is executed by a processor to implement the methods described above.

[0049] On the other hand, embodiments of the present invention also disclose a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the aforementioned method.

[0050] Compared with the prior art, the present invention has the following technical effects: The present invention performs infrared image comparison and analysis on target vehicles entering and leaving through infrared equipment, and performs secondary analysis on the comparison results in combination with target tracking algorithm, which can improve the accuracy of entry and exit control. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is a flowchart of a vehicle access control method based on infrared analysis provided in an embodiment of this application;

[0053] Figure 2 This is a schematic diagram of the structure of a posture recognition module provided in an embodiment of this application;

[0054] Figure 3 This is a flowchart of a specific embodiment provided in this application;

[0055] Figure 4 This is a schematic diagram of a vehicle access control device based on infrared analysis provided in an embodiment of this application;

[0056] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0058] In related technologies, under-vehicle detection devices or manual inspection are used to detect the hiding of people when entering and exiting vehicles. However, under-vehicle detection devices are limited to judging the underside of vehicles, which limits their application scope and is easily affected by changes in the external environment. Manual inspection is time-consuming and labor-intensive, which can easily lead to problems such as low accuracy and increased human resource costs.

[0059] In view of this, this application provides a vehicle access control method based on infrared analysis. The method described in this application can be applied to a terminal, a server, or software running on either a terminal or a server. The terminal can be a tablet, laptop, desktop computer, etc., but is not limited to these. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0060] Reference Figure 1 This invention provides a vehicle access control method based on infrared analysis, comprising:

[0061] S101. The infrared image of the target vehicle to be entered is analyzed and processed by the infrared device to obtain the first analysis feature. The first analysis feature is used to characterize the vehicle and personnel characteristics of the target vehicle when it enters.

[0062] S102. Perform feature extraction processing on the target vehicle to obtain the vehicle identification code;

[0063] S103. After the target vehicle enters, the target vehicle is tracked according to the vehicle identification code to obtain the vehicle's movement trajectory.

[0064] S104. When the target vehicle leaves, the infrared image of the target vehicle is analyzed again by the infrared device to obtain a second analysis feature. The second analysis feature is used to characterize the vehicle and personnel characteristics of the target vehicle when it leaves.

[0065] S105. Combining the vehicle movement trajectory, the second analysis feature is compared with the vehicle and personnel based on the first analysis feature to obtain the comparison result.

[0066] S106. When the comparison results are abnormal, an abnormality alarm is issued.

[0067] In this embodiment of the invention, the vehicle access control method based on infrared analysis can be applied to controlled areas or locations. Infrared devices, such as infrared cameras, are installed at the entrances and exits of the controlled locations to acquire infrared images of target vehicles waiting to enter. These images are then analyzed to obtain a first analytical feature, which characterizes the vehicle and its occupants upon entry, including posture recognition results and occupant estimation results. The posture recognition results are used to detect anomalies in occupant postures. For example, if a person is detected lying down, this can be defined as an anomaly, as a hidden person might be lying down or on their side. Using this anomaly helps detect whether someone is hiding in the vehicle. Then, target tracking is performed on the target vehicle. Specifically, the vehicle is identified, a unique identifier is generated, and the identifier is used for target tracking to obtain the vehicle's trajectory. When the vehicle leaves, the infrared image is analyzed again to obtain a second analytical feature, which characterizes the vehicle and its occupants upon departure, also including posture recognition results and occupant estimation results. This invention also combines vehicle movement trajectories with a comparative analysis of the first and second analytical features to obtain comparison results. An alarm is triggered when the comparison results are abnormal. In this invention, infrared cameras or sensors are typically installed at locations where vehicles need to be monitored, such as beside roads or at parking lot entrances, and can be distributed or centrally installed in fixed locations. Infrared sensors detect infrared radiation inside the vehicle. When a person is inside the vehicle, they emit infrared radiation, creating a difference from the vehicle's interior environment and forming an infrared image. This invention uses behavioral analysis algorithms to analyze and interpret the data received by the infrared cameras. In one feasible embodiment, the frequency, amplitude, and duration of changes in infrared radiation are detected to determine if there are any people or other hidden individuals inside the vehicle. If the sensor receives continuous changes in infrared radiation, it may indicate activity inside the vehicle. This invention primarily uses image processing and computer vision algorithms in conjunction with infrared cameras to analyze the number of people in the images. By detecting human contours, feature points, or behavioral patterns, the number of people can be estimated and counted, obtaining characteristics of vehicle entry and exit. These are then compared with the vehicle's movement trajectory to obtain comparison results. Specifically, by recording the number of vehicles entering, the system can compare the number of vehicles leaving to check for changes in the number of people. It can also determine whether the changes in the number of people conform to certain rules based on the vehicle movement trajectory. If the rules are not met, an alarm is triggered, the vehicle passage time is recorded, and corresponding outputs are generated. This invention can be used for traffic management, parking lot management, and secure location management.

[0068] It should be further noted that in various specific embodiments of this application, when processing data related to the identity or characteristics of the target object, such as the target object's information, behavioral data, historical data, and location information, is required, the target object's permission or consent will be obtained first. Furthermore, the collection, use, and processing of this data will comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require obtaining sensitive information about the target object, separate permission or consent from the target object will be obtained through pop-ups or redirection to a confirmation page. Only after obtaining the target object's separate permission or consent will the necessary target object-related data for the normal operation of the embodiments of this application be obtained.

[0069] As a further optional implementation, the step of performing infrared image analysis processing on the target vehicle to be approached using an infrared device to obtain the first analytical feature includes:

[0070] An infrared image is obtained by performing infrared radiation imaging processing on the target vehicle using an infrared device.

[0071] The infrared image is input into the posture recognition model for human posture detection processing to obtain the posture recognition result.

[0072] The infrared image is input into the people estimation model for people counting processing to obtain the people estimation result;

[0073] The posture recognition result and the number of people estimation result are determined as the first analytical features.

[0074] In this embodiment of the invention, infrared radiation imaging processing is performed on the target vehicle using an infrared device to obtain an infrared image. The infrared device can employ an infrared camera or infrared sensor to detect human body heat and convert it into an image or video. It can identify people using the infrared thermal radiation emitted by the human body, thus obtaining an infrared image. The infrared image is then input into a posture recognition model for human posture detection processing to obtain a posture recognition result. The infrared image is then input into a people estimation model for people counting processing to obtain a people estimation result. The posture recognition model and the people estimation model can employ a deep convolutional model with multiple convolutional layers and fully connected layers to learn human characteristics from infrared images or sensor data, thereby accurately detecting and counting people. Finally, the posture recognition result and the people estimation result are determined as the first analytical feature. This embodiment of the invention uses infrared devices to control vehicles, enabling rapid identification and detection of abnormal situations and reducing labor costs.

[0075] As a further optional implementation, the step of inputting the infrared image into the pose recognition model for human pose detection processing to obtain the pose recognition result includes:

[0076] Input the infrared image into the posture recognition model;

[0077] The pose recognition model is used to perform position prediction processing on the key points of the infrared image to obtain a prediction confidence map and a vector field.

[0078] The predicted confidence map and the vector field are encoded using a greedy analysis algorithm to obtain the associated vector field;

[0079] A confidence analysis is performed on the associated vector field, and key points of the infrared image are marked based on the confidence analysis results to obtain the pose recognition result.

[0080] In this embodiment of the invention, reference is made to Figure 2 The infrared image is input into the pose recognition model, which is a neural network model composed of multiple convolutional layers. This neural network model includes two branches: F represents the infrared image. Position prediction processing is performed on the key points of the infrared image, and the results are input into branches 1 and 2 respectively, yielding a prediction confidence map S and a vector field L. The upper part of the image, i.e., the first branch, is used to predict the confidence map, and the lower part, i.e., the second branch, is used to predict the associated vector field. Each regression of S and L completes one round of iterative prediction. Through continuous iterations of t∈(1,…,T), the entire prediction network architecture is formed. At each stage, the feedback loss function is calculated, and the inputs S, L, and F are connected to obtain the input for the next stage of prediction training. After n iterations, S can play a certain role in distinguishing the left and right structures of the prediction network architecture; the more iterations, the more significant the distinction. In each iteration, a greedy analysis algorithm is used to encode the predicted confidence map and the vector field to obtain the associated vector field. Then, confidence analysis is performed on the associated vector field, and key points in the infrared image are marked based on the confidence analysis results. Finally, the key points of all detected targets are marked, yielding the pose recognition result, which is the detected human pose, such as sitting or lying down. This embodiment of the invention detects the posture of personnel in vehicles through pose recognition, enabling rapid detection of abnormal personnel and reducing labor costs.

[0081] As a further optional implementation, the step of inputting the infrared image into the people estimation model for people counting processing to obtain the people estimation result includes:

[0082] The infrared image is input into the population estimation model;

[0083] The infrared image is processed by head feature extraction to obtain a crowd density map;

[0084] The population density map is processed by density map integral calculation to obtain the population estimation result.

[0085] In this embodiment of the invention, the number of people is estimated by inputting the infrared image into the number estimation model. The number estimation model can use a multi-column convolutional neural network to extract the head features of people, generate a crowd density map, and obtain the total number of people in the image by integrating the density map.

[0086] As a further optional implementation, the step of performing feature extraction processing on the target vehicle to obtain a vehicle identification code includes:

[0087] Obtain the license plate number of the target vehicle;

[0088] The target vehicle is subjected to feature extraction processing to obtain vehicle features;

[0089] The extracted vehicle features and license plate number are used to generate an identifier, resulting in a vehicle identification code.

[0090] In this embodiment of the invention, the license plate number of the target vehicle is obtained, and then feature extraction processing is performed on the target vehicle to obtain vehicle features, which may include the vehicle's appearance features or spatial features, etc. By combining the vehicle features and the license plate number, a unique identifier is generated for identifying the target vehicle.

[0091] As a further optional implementation, the step of tracking the target vehicle based on the vehicle identification code to obtain the vehicle's movement trajectory includes:

[0092] Acquire video data from the camera;

[0093] The video data is processed using the vehicle identification code to obtain the vehicle's location;

[0094] The video data is processed by feature extraction according to the target tracking algorithm, and the extracted feature vectors are processed by similarity matching to obtain the vehicle trajectory sequence;

[0095] Based on the vehicle's location, the vehicle trajectory sequence is analyzed to obtain the vehicle's movement trajectory.

[0096] In this embodiment of the invention, after a vehicle enters a controlled area, it can be monitored and tracked by multiple cameras. Within the monitored area, multiple cameras are installed at distances according to their field of view, with each camera managing a small area and identifying vehicles appearing in each area. This embodiment of the invention uses vehicle identification codes to perform target detection processing on the video data acquired by the multiple cameras to obtain the vehicle's location, and then uses a target tracking algorithm to obtain the vehicle's trajectory sequence. Specifically, video data from multiple adjacent cameras is collected, and the vehicle's location and identification code are labeled in each video frame. A target detection algorithm (Faster R-CNN) is used to detect and locate vehicles in each video frame, and a target tracking algorithm (DeepSORT) is used to continuously track the target identification codes. For each tracked vehicle, a feature vector is extracted from its trajectory sequence using models such as DeepSORT. These feature vectors can be the target's appearance features, motion features, or spatial features. Then, for vehicles appearing in adjacent cameras, the similarity of their feature vectors is compared. Distance metrics such as Euclidean distance or cosine similarity can be used to calculate similarity scores between feature vectors. A similarity threshold is set, and vehicles with similarity scores higher than the threshold are matched as the same vehicle. In this embodiment of the invention, the similarity threshold can be adjusted according to the specific scenario and dataset, and set accordingly based on the actual situation. This embodiment of the invention also considers the temporal sequence of vehicles crossing adjacent cameras, observing the patterns of vehicle appearance and disappearance. By analyzing information such as vehicle speed and direction of travel, combined with the relationship between time interval and spatial distance, vehicles are further associated. Because vehicles may stop during their trajectories, events such as people hiding, getting on, and getting off are likely to occur. Therefore, adjacent cameras where such events occur are associated, and the activity trajectories of vehicles entering and leaving the entire area are recorded based on vehicle characteristics and time series. The system can identify and compare the number and posture of people entering and leaving the area, record the destination of the relevant vehicles, and frame the license plates of suspicious vehicles in the video. It can also calculate the clarity of a series of license plate images of the same vehicle and find the clearest image to report and issue an abnormal alarm. The alarm information can be broadcast by voice and displayed in a pop-up window on the gatekeeper's computer.

[0097] As a further optional implementation, the step of performing dwell analysis processing on the vehicle trajectory sequence based on the vehicle location to obtain the vehicle movement trajectory includes:

[0098] The vehicle trajectory sequence is subjected to time analysis processing to obtain the trajectory time sequence;

[0099] Based on the vehicle's location, the trajectory time series is analyzed for movement distance to obtain the dwell time analysis results.

[0100] The vehicle trajectory sequence is updated based on the dwell analysis results to obtain the vehicle movement trajectory.

[0101] In this embodiment of the invention, by considering the temporal sequence of a vehicle crossing adjacent cameras, the patterns of vehicle appearance and disappearance are observed. By analyzing information such as the vehicle's speed and direction of travel, and combining this with the relationship between time intervals and spatial distances, a trajectory time series is obtained. Then, based on the activity trajectory time series, the vehicle's trajectory and speed are calculated, where instantaneous speed = distance between adjacent frames / time difference. If the instantaneous speed is greater than a threshold, acceleration is considered to have occurred. The trajectory sequence can be used to calculate the direction of motion using adjacent coordinates, where the direction of motion is represented as dir = arctg((y2-y1) / (x2-x1)), thus obtaining the direction sequence dir = [d1, d2, d3, ...]. By calculating the difference between adjacent directions and combining it with a direction threshold for estimation, when the calculated direction difference is greater than a preset threshold, a sudden change in direction is considered. If the distance traveled within a certain period is less than a preset distance threshold, a stop is considered to have occurred. Based on the stop analysis results, the vehicle trajectory sequence is updated to obtain the vehicle's movement trajectory. In this embodiment of the invention, based on the dwell time analysis results, such as people getting on and off the vehicle during the dwell time, the number of people in the first analysis feature of the vehicle can be updated or reported. Finally, the number of people in the second analysis feature detected when the vehicle leaves is compared. If an anomaly is found, an alarm is triggered; otherwise, the vehicle is allowed to pass. This embodiment of the invention uses infrared equipment to analyze and compare the characteristics of people entering and leaving the vehicle, and combines target tracking technology to perform secondary analysis on the comparison results, thereby improving the accuracy and robustness of vehicle entry and exit control, reducing labor costs, and improving processing efficiency.

[0102] Combined with appendix Figure 3 A specific embodiment of the present invention includes the following process: When a vehicle is about to enter, the license plate number and vehicle and personnel characteristics are extracted to generate a unique identification code for the vehicle. The number of people and their postures can be captured and identified using an infrared camera. Once the vehicle enters the premises, by associating with adjacent cameras in different areas, the relevant vehicle and personnel characteristic information of the vehicle involved in the lingering incident is identified in different camera areas. Upon departure, if any abnormal personnel are detected, an alarm is triggered, and the gatekeeper issues a voice announcement.

[0103] Reference Figure 4 This invention also provides a vehicle access control system based on infrared analysis, comprising:

[0104] The first module 401 is used to perform infrared image analysis and processing on the target vehicle to be entered by infrared equipment to obtain a first analysis feature. The first analysis feature is used to characterize the vehicle and personnel characteristics of the target vehicle when it enters.

[0105] The second module 402 is used to perform feature extraction processing on the target vehicle to obtain the vehicle identification code;

[0106] The third module 403 is used to track the target vehicle according to the vehicle identification code after the target vehicle enters, and obtain the vehicle movement trajectory.

[0107] The fourth module 404 is used to perform infrared image analysis on the target vehicle again through the infrared device when the target vehicle leaves, to obtain a second analysis feature. The second analysis feature is used to characterize the vehicle and personnel characteristics of the target vehicle when it leaves.

[0108] The fifth module 405 is used to combine the vehicle movement trajectory and perform vehicle and personnel comparison processing on the second analysis feature based on the first analysis feature to obtain the comparison result;

[0109] The sixth module 406 is used to issue an abnormal alarm when the comparison result is abnormal.

[0110] It is understood that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0111] Reference Figure 5 This invention also provides an electronic device, including a processor 501 and a memory 502; the memory is used to store a program; the processor executes the program to implement the method described above.

[0112] and Figure 1 Corresponding to the method described above, embodiments of the present invention also provide a computer-readable storage medium storing a program that is executed by a processor to implement the method described above.

[0113] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to perform... Figure 1 The method shown.

[0114] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is altered and sub-operations described as part of a larger operation are executed independently.

[0115] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the described functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0116] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0117] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0118] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0119] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0120] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0121] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0122] The above is a detailed description of the preferred embodiments of the present invention, but the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A vehicle access control method based on infrared analysis, characterized in that, The method includes: The infrared image of the target vehicle to be entered is analyzed and processed by infrared equipment to obtain the first analysis feature, which is used to characterize the vehicle and personnel characteristics of the target vehicle when it enters. The target vehicle is subjected to feature extraction processing to obtain the vehicle identification code; After the target vehicle enters, the target vehicle is tracked according to the vehicle identification code to obtain the vehicle's movement trajectory; When the target vehicle leaves, the infrared image of the target vehicle is analyzed again by the infrared device to obtain a second analysis feature. The second analysis feature is used to characterize the vehicle and personnel characteristics of the target vehicle when it leaves. Based on the vehicle movement trajectory, the second analysis feature is compared with the first analysis feature to obtain the comparison result; An anomaly alarm is issued when the comparison results are abnormal; The infrared image analysis of the target vehicle to be entered, performed using infrared equipment, yields the first analytical feature, including: An infrared image is obtained by performing infrared radiation imaging processing on the target vehicle using an infrared device. The infrared image is input into the posture recognition model for human posture detection processing to obtain the posture recognition result. The infrared image is input into the people estimation model for people counting processing to obtain the people estimation result; The posture recognition result and the number of people estimation result are determined as the first analytical features.

2. The method according to claim 1, characterized in that, The step of inputting the infrared image into the posture recognition model for human posture detection processing to obtain the posture recognition result includes: Input the infrared image into the posture recognition model; The pose recognition model is used to perform position prediction processing on the key points of the infrared image to obtain a prediction confidence map and a vector field. The predicted confidence map and the vector field are encoded using a greedy analysis algorithm to obtain the associated vector field; A confidence analysis is performed on the associated vector field, and key points of the infrared image are marked based on the confidence analysis results to obtain the pose recognition result.

3. The method according to claim 1, characterized in that, The step of inputting the infrared image into the people estimation model for people counting processing to obtain the people estimation result includes: The infrared image is input into the population estimation model; The infrared image is processed by head feature extraction to obtain a crowd density map; The population density map is processed by density map integral calculation to obtain the population estimation result.

4. The method according to claim 1, characterized in that, The step of performing feature extraction processing on the target vehicle to obtain the vehicle identification code includes: Obtain the license plate number of the target vehicle; The target vehicle is subjected to feature extraction processing to obtain vehicle features; The extracted vehicle features and license plate number are used to generate an identifier, resulting in a vehicle identification code.

5. The method according to claim 1, characterized in that, The step of tracking the target vehicle based on the vehicle identification code to obtain the vehicle's movement trajectory includes: Acquire video data from the camera; The vehicle location is obtained by performing target detection processing on the video data based on the vehicle identification code; The video data is processed by feature extraction according to the target tracking algorithm, and the extracted feature vectors are processed by similarity matching to obtain the vehicle trajectory sequence; Based on the vehicle's location, the vehicle trajectory sequence is analyzed to obtain the vehicle's movement trajectory.

6. The method according to claim 5, characterized in that, The step of performing dwell analysis on the vehicle trajectory sequence based on the vehicle location to obtain the vehicle movement trajectory includes: The vehicle trajectory sequence is subjected to time analysis processing to obtain a trajectory time series; Based on the vehicle's location, the trajectory time series is analyzed for movement distance to obtain the dwell time analysis results. The vehicle trajectory sequence is updated based on the dwell analysis results to obtain the vehicle movement trajectory.

7. A vehicle access control system based on infrared analysis, characterized in that, The system includes: The first module is used to perform infrared image analysis and processing on the target vehicle to be entered by infrared equipment to obtain the first analysis feature, which is used to characterize the vehicle and personnel characteristics of the target vehicle when it enters. The second module is used to perform feature extraction processing on the target vehicle to obtain the vehicle identification code; The third module is used to track the target vehicle based on the vehicle identification code after the target vehicle enters, and obtain the vehicle's movement trajectory. The fourth module is used to perform infrared image analysis on the target vehicle again through the infrared device when the target vehicle leaves, to obtain a second analysis feature. The second analysis feature is used to characterize the vehicle and personnel characteristics of the target vehicle when it leaves. The fifth module is used to combine the vehicle movement trajectory and perform vehicle and personnel comparison processing on the second analysis feature based on the first analysis feature to obtain the comparison result; The sixth module is used to issue an anomaly alarm when the comparison results are abnormal; The first module is used to perform infrared image analysis on the target vehicle to be approached using an infrared device to obtain a first analytical feature, including: An infrared image is obtained by performing infrared radiation imaging processing on the target vehicle using an infrared device. The infrared image is input into the posture recognition model for human posture detection processing to obtain the posture recognition result. The infrared image is input into the people estimation model for people counting processing to obtain the people estimation result; The posture recognition result and the number of people estimation result are determined as the first analytical features.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor; The memory is used to store programs; The processor executes the program to implement the method of any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.

Images