A method and system for passage detection based on passage logic

Abstract

The application relates to the technical field of detection, and discloses a passing detection method and system based on passing logic, which comprises the following steps: collecting data in a detection area through a distance sensor at a preset position; judging whether there is a preliminary anomaly based on the data and the passing logic; if it is judged that there is a preliminary anomaly, starting an infrared detector and collecting infrared data in the detection area through the infrared detector; and judging whether there is abnormal passing based on the infrared data. Different from the passing detection method of manual detection and judgment in the prior art, the application firstly performs primary judgment according to the data collected by the distance sensor and the passing logic, and then performs secondary judgment based on the infrared detection data, so that whether there is abnormal passing is judged under the premise of preventing the occurrence of special misjudgment. Through the above mode, the application provides an automatic passing detection method based on passing logic, and effectively prevents the occurrence of tailing.

Description

Technical Field

[0001] This invention relates to the field of detection technology, and in particular to a passage detection method and system based on passage logic. Background Technology

[0002] Self-service turnstiles are commonly used to manage pedestrian flow and regulate entry and exit, and are therefore widely used in subways, high-speed rail stations, airports, customs, border inspection stations, office buildings, and other locations. However, tailgating is a common occurrence when using self-service turnstiles, potentially causing personal injury and property damage to authorized personnel and administrators.

[0003] In existing technologies, manual detection is commonly used to prevent tailgating. However, relying solely on manual detection is inefficient and prone to omissions or errors when personnel are fatigued or during peak traffic periods. Furthermore, the labor cost of equipping each lane with a detection personnel is too high. Therefore, there is an urgent need for an automated passage detection method to prevent tailgating.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this invention is to provide an automated passage detection method to prevent tailgating.

[0006] To achieve the above objectives, the present invention provides a passage detection method based on passage logic, the method comprising the following steps:

[0007] Data within the detection area is collected by a distance sensor at a preset location;

[0008] Based on the data and access logic, determine whether there is a preliminary anomaly;

[0009] If the aforementioned preliminary anomaly is determined to exist, the infrared detector is activated to collect infrared data within the detection area.

[0010] The infrared data is used to determine whether there is any abnormal passage.

[0011] Optionally, the step of determining whether there is a preliminary anomaly based on the data and access logic includes:

[0012] Based on the data, the number and height of the detected targets within the detection area are obtained;

[0013] When the number is greater than a preset number, determine whether the height of the detected target is greater than a preset height;

[0014] When the height of the detected target is greater than the preset height, the object shape of the detected target is detected to see if it conforms to the preset shape.

[0015] When there are at least two targets within the detection area that are larger than a preset height and do not conform to a preset shape, the passage logic determines whether there is a preliminary anomaly.

[0016] Optionally, the step of obtaining the number and height of the detected targets within the detection area based on the data includes:

[0017] Based on the data, cluster analysis is performed on the point cloud within the detection area to obtain the point cloud clustering result of the detected target;

[0018] Based on the point cloud clustering results, the cluster center at the top position of the detected target is determined;

[0019] Based on the point cloud corresponding to the cluster centers, the height and position of the detected target are obtained;

[0020] The number of detected targets is obtained based on the location of the detected targets within the detection area.

[0021] Optionally, the step of determining whether there is abnormal passage based on the infrared data includes:

[0022] Based on the infrared data, an infrared thermal image of the target being detected within the detection area is determined;

[0023] Based on the infrared thermal image, determine whether there are at least two pedestrians among the detected targets;

[0024] If it exists, then it is determined that there is abnormal passage.

[0025] Optionally, the step of determining whether there are at least two pedestrians among the detected target based on the infrared thermal image includes:

[0026] Based on the infrared thermal image, determine whether there are at least two objects in the detection area that have a common heat source and whose heat source area exceeds a preset area;

[0027] If present, it is determined that there are at least two pedestrians among the detected targets.

[0028] Optionally, after determining whether abnormal passage exists based on the infrared data, the method further includes:

[0029] If the abnormal passage is detected, an alarm message is triggered and the passage gate is closed.

[0030] Optionally, after determining that the abnormal passage exists, triggering an alarm message and closing the passage gate, the method further includes:

[0031] Collect facial information of people passing through abnormally and add the facial information to a preset warning electronic file.

[0032] Furthermore, to achieve the above objectives, the present invention also proposes a passage detection system based on passage logic, wherein the passage detection system based on passage logic includes:

[0033] The first acquisition module is used to acquire data within the detection area through a distance sensor at a preset location;

[0034] The first judgment module is used to determine whether there is a preliminary anomaly based on the data and the passage logic;

[0035] The second acquisition module is used to activate the infrared detector and acquire infrared data in the detection area if the preliminary abnormality is determined to exist.

[0036] The second judgment module is used to determine whether there is abnormal passage based on the infrared data.

[0037] This invention collects data within a detection area using a distance sensor at a preset location; based on the data and traffic logic, it determines whether a preliminary anomaly exists; if a preliminary anomaly is detected, an infrared detector is activated to collect infrared data within the detection area; and based on the infrared data, it determines whether abnormal passage exists. Unlike existing manual detection methods, this invention first performs an initial judgment based on the data collected by the distance sensor and traffic logic, and then performs a secondary judgment based on the infrared detection data, determining whether abnormal passage exists while preventing special misjudgments. Therefore, through the above method, this invention provides an automated traffic detection method based on traffic logic, effectively preventing tailgating. Attached Figure Description

[0038] Figure 1 This is a flowchart illustrating the first embodiment of the passage detection method of the present invention;

[0039] Figure 2 This is a flowchart illustrating the second embodiment of the passage detection method of the present invention;

[0040] Figure 3 This is a flowchart illustrating the third embodiment of the passage detection method of the present invention;

[0041] Figure 4 This is a structural block diagram of the first embodiment of the passage detection device based on passage logic of the present invention.

[0042] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0043] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0044] This invention provides a passage detection method based on passage logic, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the passage detection method based on passage logic of the present invention.

[0045] In this embodiment, the passage detection method includes the following steps:

[0046] Step S10: Collect data within the detection area using a distance sensor at a preset location;

[0047] It should be noted that the executing entity of the method in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer or personal computer, or other electronic devices capable of performing the same or similar functions. The passage detection methods provided in this embodiment and the following embodiments will be specifically described here using the aforementioned passage detection device.

[0048] It is understandable that the aforementioned preset position can be the installation position of the distance sensor. To facilitate better data acquisition by the distance sensor, it is typically installed above or to the side of the self-service gate channel. A distance sensor is a type of sensor generally used to sense the distance between itself and an object to perform a preset function. Based on their working principle, they can be divided into optical distance sensors, infrared distance sensors, and ultrasonic distance sensors. However, the accuracy of ultrasonic distance sensors is easily affected by temperature. Therefore, this embodiment preferably uses a laser distance sensor for data acquisition. The acquisition method can be that the distance sensor scans the entire detection area using non-visible light to obtain a complete 2D depth image within the detection area.

[0049] It should be noted that the aforementioned detection area can be the area where the distance sensor needs to collect data. The detection area can be the entire passageway or a range slightly larger than the passageway; the specific range is not limited in this embodiment. The detection area can be further divided into an identification area and a non-identification area. The identification area is the area where data analysis is required, while the non-identification area is the area where data analysis is not required. In this embodiment, the passageway is determined to be normal by analyzing the data collected by the distance sensor within the identification area. The identification area can be a portion of the passageway near the gate or the entire passageway; the specific range is not limited in this embodiment.

[0050] In its implementation, the distance sensor first acquires a 2D depth image within the detection area. Then, it converts the sensor's own coordinate system to a ground coordinate system with the ground as the plane, transforming the 2D depth image into 3D point cloud data. Ground registration is then performed on the point cloud data to obtain the distance between each point. The coordinate transformation method can be as follows: based on the distance sensor's installation location and angle, and combined with experimental calibration, the rotation offset angle of the distance sensor's coordinate system relative to the ground coordinate system is obtained, and the transformation is performed based on this offset angle. Finally, the distance from each point cloud to the recognition area is calculated to determine whether the point cloud is within the defined recognition area, and data outside the recognition area is eliminated.

[0051] Step S20: Determine whether there is a preliminary anomaly based on the data and access logic;

[0052] It is understandable that when analyzing the data collected by the distance sensor to identify the specific situation of the detected target within the identification area, the analysis results may include the following: person-to-person, person-to-object, and object-to-object. Therefore, the above-mentioned common logic can be: when a person-to-person or person-to-object situation is detected within the identification area, that is, when at least one pedestrian is present among the detected targets within the identification area, a preliminary anomaly can be determined, and then the next step of infrared detection can be performed; if no pedestrian is detected among the detected targets within the identification area, the infrared detector is not activated, and step S30 is not performed. It is easy to understand that during the data analysis process, it is easy to misidentify objects as humans. Therefore, in this embodiment, when making the initial judgment using the data collected by the distance sensor and the common logic, attention should be paid to distinguishing between objects and humans during the data analysis process. Therefore, in this embodiment, step S20 may include the following steps:

[0053] Step S201: Based on the data, obtain the number and height of the detected targets within the detection area;

[0054] It should be noted that the above data refers to the point cloud data within the identification area. This embodiment obtains the point cloud clustering results of the detected targets within the identification area by performing cluster analysis on the point cloud data within the identification area. The cluster analysis method used can be: hierarchical clustering, dynamic clustering, ordered sample clustering, etc. Of course, cluster analysis tools based on algorithms such as k-means and k-centroids can also be used for cluster analysis. This embodiment does not limit the specific analysis methods and means. The point cloud clustering results include the cluster center at the top position of the detected target. The height of the point cloud corresponding to the cluster center in the ground coordinate system is the height of the detected target. The position of the cluster center relative to the identification area is the position of the detected target. Therefore, the number of cluster centers in the identification area can be obtained through position analysis, which in turn yields the number of detected targets in the identification area.

[0055] Step S202: When the number is greater than a preset number, determine whether the height of the detected target is greater than a preset height;

[0056] Step S203: When the height of the detected target is greater than the preset height, detect whether the object shape of the detected target conforms to the preset shape;

[0057] Step S204: When there are at least two targets in the detection area that are larger than the preset height and do not conform to the preset shape, determine whether there is a preliminary anomaly based on the passage logic.

[0058] Understandably, the first step is to detect the number of targets within the recognition area and determine whether the detected number is greater than a preset number. Generally, the preset number is one. However, in special cases, the preset number can be greater than one. For example, if a tour group of five people enters a certain place, all five people can enter as long as one of them pays the admission fee. In this case, the preset number can be five. Therefore, this embodiment does not limit the specific value of the preset number.

[0059] Furthermore, in real-world applications, pedestrians typically have size and height restrictions on the luggage and other items they can carry when passing through self-service gates. Therefore, if the number of detected targets within the recognition area exceeds a preset limit, an initial judgment can be made based on height. If the height requirement is not met, the shape of the detected target that does not meet the height requirement can be further determined to be a preset shape. It is easy to understand that if the detected target is luggage or other items, its shape is relatively regular and square, while if the detected target is a human, its shape is more irregular. Therefore, a secondary judgment can be made based on the object shape of the detected target, which can be obtained based on the contour of the detected target's 3D point cloud data. Similarly, this embodiment can determine whether there is at least one pedestrian among the detected targets based on the object shape or contour of the detected target, and then determine whether to proceed to the next step S30 according to the above passage logic.

[0060] It should be noted that the preset height can be changed according to specific application scenarios. For example, airports require carry-on baggage to be no larger than 55×40×20 cubic centimeters, in which case the preset height could be 60 centimeters. Train stations, on the other hand, require the sum of the external dimensions (length, width, and height) to be no more than 160 centimeters, in which case the preset height could be 100 centimeters. Therefore, this embodiment does not impose any restrictions on the specific value of the preset height. Furthermore, the preset height can be stored in the aforementioned access control equipment or manually input by relevant personnel according to the specific application scenario. The preset shape is stored in the preset shape library within the access control equipment. The preset shapes are designed based on the dimensions of common carry-on baggage items, such as the dimensions of a 20-inch suitcase or a large-capacity handbag.

[0061] In the specific implementation, firstly, it is determined whether the number of detected targets within the recognition area is greater than a preset number. Then, it is determined whether the height of all detected targets is greater than a preset height, and the point cloud data of detected targets with a height less than the preset height are eliminated. Next, it is detected whether the shape of the remaining detected targets conforms to a preset shape, and the point cloud data of detected targets that conform to the preset shape are eliminated. Finally, the number of detected targets within the recognition area is detected. If there are still at least two detected targets, based on the passage logic, that is, based on the contour of the 3D point cloud data of the remaining detected targets, it is determined whether there is at least one pedestrian among the detected targets. If there is, it is determined that there is a preliminary anomaly, and the next step of infrared detection is performed; if not, step S30 is not performed.

[0062] Step S30: If the preliminary anomaly is determined to exist, the infrared detector is activated to collect infrared data in the detection area.

[0063] Step S40: Determine whether there is any abnormal passage based on the infrared data.

[0064] Understandably, while initial identification of the target based on data collected by the distance sensor can largely prevent misidentification of objects as people, some special items may still be misidentified. For example, bicycles exceeding 140cm in height and with irregular shapes, and musical instruments such as cellos exceeding 120cm in height and with irregular shapes, may be misidentified as people due to their height and irregular shape. Therefore, further identification of the target is required. Since these types of objects typically do not have excessively high temperatures, this embodiment can use an infrared detector for further data collection and detection.

[0065] It should be noted that the aforementioned infrared detector is a sensor that uses infrared light for data processing, enabling non-contact temperature measurement. The infrared data collected can be the infrared radiation energy of the target being detected within the identification area.

[0066] This embodiment collects data within a detection area using a distance sensor at a preset location; based on the data and passage logic, it determines whether a preliminary anomaly exists; if a preliminary anomaly is determined, an infrared detector is activated to collect infrared data within the detection area; based on the infrared data, it determines whether abnormal passage exists. Unlike existing manual detection methods, this embodiment uses a combined approach of distance sensor and infrared detection. First, the number of detected targets is obtained from the data collected by the distance sensor. If the number of detected targets exceeds a preset number, a preliminary judgment is made based on the height and shape of the detected targets, as well as the passage logic, to initially avoid misidentifying objects as humans. Then, a second judgment is made using infrared detection data to determine whether abnormal passage exists, while preventing special misjudgments. Therefore, through the above method, this embodiment provides an automated passage detection method based on passage logic, effectively preventing tailgating.

[0067] Reference Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the passage detection method based on passage logic of the present invention. Figure 1 The illustrated embodiment presents a second embodiment of the passage detection method based on passage logic of the present invention.

[0068] In this embodiment, step S40 specifically includes:

[0069] Step S401: Based on the infrared data, determine the infrared thermal image of the target being detected within the detection area;

[0070] Step S402: Based on the infrared thermal image, determine whether there are at least two pedestrians among the detected targets;

[0071] Step S403: If it exists, then it is determined that there is an abnormal passage.

[0072] It should be noted that in this embodiment, the infrared detector first collects the infrared radiation energy distribution within the identification area, then reflects it onto the photosensitive element of the infrared detector, converts the infrared radiation energy into an electrical signal, and then converts the electrical signal into an infrared thermal image. Here, infrared radiation energy is a specific band of infrared signal emitted by the thermal radiation of the target being detected. The infrared thermal image corresponds to the thermal distribution field of the object's surface within the identification area; therefore, different patterns in the infrared thermal image represent different targets being detected, and different colors represent different temperatures of the targets. Thus, this embodiment further determines the target by converting the invisible infrared radiation energy emitted by the target being detected into a visible infrared thermal image.

[0073] To determine whether there are at least two pedestrians in the identification area based on infrared thermal images, the identification method can be as follows: First, threshold segmentation is performed based on the shape information, motion information, and possible temperature range of the human body in the infrared thermal image to segment out candidate areas that may belong to pedestrians from the image; then, based on specific characteristics, such as the heat source of the human body is generally uniformly distributed (for example, the heat source of a bicycle is not uniformly distributed but dispersed) and the heat source area is generally large, the candidate areas are re-identified and verified, and then the pedestrians in the candidate areas are found and the number is counted.

[0074] In addition, the above recognition method can also be as follows: First, threshold segmentation is performed based on the pedestrian's shape information, movement information, and the pedestrian's temperature being higher than the surrounding environment to segment candidate regions of interest from the image; then, the candidate regions are re-identified and verified based on specific features such as shape features and pedestrian gait features, and then the pedestrians in the candidate regions are identified and their numbers are counted.

[0075] After counting the number of pedestrians in the recognition area, if at least two pedestrians are detected among the detected targets in the recognition area, it is determined that there is abnormal passage.

[0076] This embodiment determines the infrared thermal image of the target within the detection area using infrared data; based on the infrared thermal image, it determines whether there are at least two pedestrians among the target; if so, it determines that there is abnormal passage. This embodiment uses infrared data of the target collected by an infrared detector to form an infrared thermal image, and then uses shape information, motion information, and pedestrian characteristics to re-identify and distinguish objects and pedestrians in the thermal image, thus avoiding the situation of misidentifying objects as humans and effectively determining whether there is abnormal passage, that is, effectively determining whether tailgating has occurred.

[0077] Reference Figure 3 , Figure 3 This is a flowchart illustrating the third embodiment of the passage detection method based on passage logic of the present invention. Figure 1 Alternatively, as shown in embodiment 2, a third embodiment of the passage detection method based on passage logic of the present invention is proposed. Figure 3 Based on Figure 1 The embodiments shown are examples of the proposed embodiments.

[0078] In this embodiment, after step S40, the method further includes:

[0079] Step S50: If the abnormal passage is determined to exist, an alarm message is triggered and the passage gate is closed.

[0080] Step S60: Collect the facial information of the person passing through the abnormal passage and add the facial information to the preset warning electronic file.

[0081] Understandably, when an abnormal passage situation occurs—that is, when it is determined that at least two pedestrians are in the passageway—an alarm should be triggered immediately. For example, when two pedestrians are detected passing through the passageway simultaneously, a warning light can be activated, and a voice broadcast system can be activated to warn that only one person can pass through the gate at a time, and the second pedestrian should immediately exit the passageway and wait for the next identity verification. Alternatively, the warning light can be activated, and the abnormal passage situation can be sent to relevant staff, reminding them to immediately go to the passageway where the abnormal passage situation occurred to check and maintain passage order. At the same time, after detecting an abnormal passage situation, the passage gate should be closed immediately to prevent unauthorized personnel from ignoring warning messages and taking advantage of the situation to pass through the gate.

[0082] Furthermore, to enhance the security of passage detection, facial information of pedestrians can be collected when abnormal passage occurs and added to a preset electronic alert file. This preset electronic alert file is stored in the passage detection device, containing facial information collected and verified for all abnormal passage situations. It's easy to understand that some abnormal passage situations occur due to pedestrians rushing and inadvertently entering existing passageways, not intentionally. In such cases, after secondary verification by relevant staff, the corresponding pedestrian's facial information can be deleted from the preset electronic alert file. The purpose of setting up the preset electronic alert file is to increase vigilance against individuals who have attempted to tailgate. When the camera collects the facial information of such individuals, relevant staff are immediately notified to go to the location of the passageway where they were, to prevent them from tailgating again.

[0083] This embodiment immediately triggers an alarm and closes the access gate upon detecting abnormal passage. Simultaneously, it collects facial information of the person experiencing the abnormal passage and adds it to a pre-set electronic alert file. This embodiment, upon confirming abnormal passage, immediately takes measures such as triggering an alarm and closing the gate to prevent unauthorized personnel from passing through. Furthermore, after secondary confirmation of the abnormal passage, it collects facial information of the person experiencing the abnormal passage to strengthen prevention against such individuals, prevent tailgating from recurring, and improve the security of passage detection.

[0084] refer to Figure 4 , Figure 4 This is a structural block diagram of the first embodiment of the access detection system based on access logic of the present invention.

[0085] like Figure 4 As shown, the access detection system based on access logic proposed in this embodiment of the invention includes:

[0086] The first acquisition module 401 is used to acquire data within the detection area through a distance sensor at a preset position;

[0087] The first judgment module 402 is used to determine whether there is a preliminary abnormality based on the data and the passage logic;

[0088] The second acquisition module 403 is used to activate the infrared detector and acquire infrared data in the detection area if the preliminary abnormality is determined to exist.

[0089] The second judgment module 404 is used to determine whether there is abnormal passage based on the infrared data.

[0090] This embodiment collects data within a detection area using a distance sensor at a preset location; based on the data and passage logic, it determines whether a preliminary anomaly exists; if a preliminary anomaly is determined, an infrared detector is activated to collect infrared data within the detection area; based on the infrared data, it determines whether abnormal passage exists. Unlike the manual detection methods used in existing technologies, this embodiment first performs an initial judgment based on the data collected by the distance sensor and the passage logic, and then performs a secondary judgment based on the infrared detection data, determining whether abnormal passage exists while preventing special misjudgments. Therefore, through the above method, this embodiment provides an automated passage detection method based on passage logic, effectively preventing tailgating.

[0091] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0092] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0093] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0094] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method of passage detection based on passage logic, characterized in that The method includes the following steps: Data within the detection area is collected by a distance sensor at a preset location, and the data is point cloud data within the detection area; Based on the data and access logic, determine whether there is a preliminary anomaly; If the aforementioned preliminary anomaly is determined to exist, the infrared detector is activated to collect infrared data within the detection area. Based on the infrared data, determine whether there is any abnormal passage; The step of determining whether there is a preliminary anomaly based on the data and access logic includes: Based on the data, the number and height of the detected targets within the detection area are obtained; When the number is greater than a preset number, determine whether the height of the detected target is greater than a preset height; When the height of the detected target is greater than the preset height, the object shape of the detected target is detected to see if it conforms to the preset shape. When there are at least two targets within the detection area that are larger than a preset height and do not conform to a preset shape, the passage logic is used to determine whether there is a preliminary anomaly. The step of obtaining the number and height of the detected targets within the detection area based on the data includes: Based on the data, cluster analysis is performed on the point cloud within the detection area to obtain the point cloud clustering result of the detected target; Based on the point cloud clustering results, the cluster center at the top position of the detected target is determined; Based on the point cloud corresponding to the cluster centers, the height and position of the detected target are obtained; Based on the location of the detected target within the detection area, the number of the detected targets is obtained; The step of determining whether there is abnormal passage based on the infrared data includes: Based on the infrared data, an infrared thermal image of the target being detected within the detection area is determined; Based on the infrared thermal image, determine whether there are at least two pedestrians among the detected targets; If it exists, then it is determined that there is abnormal passage; The step of determining whether there are at least two pedestrians among the detected target based on the infrared thermal image includes: Based on the infrared thermal image, determine whether there are at least two objects in the detection area that have a common heat source and whose heat source area exceeds a preset area; If present, it is determined that there are at least two pedestrians among the detected targets.

2. The method as described in claim 1, characterized in that, After determining whether there is abnormal passage based on the infrared data, the process also includes: If the abnormal passage is detected, an alarm message is triggered and the passage gate is closed.

3. The method as described in claim 2, characterized in that, If the abnormal passage is determined to exist, after triggering an alarm message and closing the passage gate, the method further includes: Collect facial information of people passing through abnormally and add the facial information to a preset warning electronic file.

4. A passage detection system based on passage logic, characterized in that, The access detection system based on access logic includes: The first acquisition module is used to acquire data within a detection area through a distance sensor at a preset position, wherein the data is point cloud data within the detection area; The first judgment module is used to determine whether there is a preliminary anomaly based on the data and the passage logic; The second acquisition module is used to activate the infrared detector and acquire infrared data in the detection area if the preliminary abnormality is determined to exist. The second judgment module is used to determine whether there is abnormal passage based on the infrared data; The first judgment module is further configured to, based on the data, obtain the number and height of the detected targets within the detection area; when the number is greater than a preset number, determine whether the height of the detected targets is greater than a preset height; when the height of the detected targets is greater than the preset height, detect whether the object shape of the detected targets conforms to a preset shape; when there are at least two detected targets within the detection area that are greater than a preset height and do not conform to a preset shape, determine whether there is a preliminary anomaly based on the passage logic. The first judgment module is further configured to perform cluster analysis on the point cloud in the detection area based on the data to obtain the point cloud clustering result of the detected target; determine the cluster center at the top position of the detected target based on the point cloud clustering result; obtain the height and position of the detected target based on the point cloud corresponding to the cluster center; and obtain the number of detected targets based on the position of the detected target in the detection area. The second judgment module is further configured to determine the infrared thermal image of the detected target within the detection area based on the infrared data; and to determine whether there are at least two pedestrians among the detected target based on the infrared thermal image; if so, to determine that there is abnormal passage. The second judgment module is further configured to determine, based on the infrared thermal image, whether there are at least two objects in the detection area that have a unified heat source and a heat source area exceeding a preset area; if so, it is determined that there are at least two pedestrians among the detected targets.

Images