One-way door opening and closing regulation and control method, system and equipment and storage medium

Abstract

The invention discloses a one-way door opening and closing regulation and control method, system and device and a storage medium, and belongs to the field of automation. The method comprises the following steps: acquiring pressure distribution data and infrared radiation data of a one-way door passing area; based on the spatial distribution characteristics of the infrared radiation data, a preset temperature threshold value and the spatial distribution characteristics of the pressure distribution data, determining passage types including human body passage and human body cooperative equipment passage; determining gait feature information according to space time sequence features corresponding to the passing target in the pressure distribution data and a preset gait template; determining passing behavior information according to the passing type and the gait feature information; according to the pressure distribution data, people flow density information of the one-way door passing area is determined, and according to the preset corresponding relation of the people flow density information, the passing behavior information and the opening and closing control information, target opening and closing control information is determined, so that control over opening and closing of the one-way door is completed. The embodiment of the invention can be suitable for different passing requirements, and the passing efficiency and the user experience are improved.

Description

Technical Field

[0001] This application belongs to the field of automation, and particularly relates to a method, system, device, and computer-readable storage medium for controlling the opening and closing of a one-way door. Background Art

[0002] In public places such as high-speed railway stations, airports, and hospitals, as a core facility for controlling the flow of people, one-way doors need to achieve efficient passage while ensuring safety. In such scenarios, the passing targets may include ordinary pedestrians, people carrying luggage, or passing groups using medical devices such as wheelchairs. The passing behaviors of different passing groups have significant differences in the opening and closing speeds and times of one-way doors.

[0003] The existing methods for controlling the opening and closing of one-way doors generally adopt a fixed opening and closing speed and time or rely on manual intervention. In the fixed opening and closing speed and time mode, the one-way door opens and closes at a constant speed and time. In special cases, the staff manually triggers a preset mode, such as long-pressing a button to extend the opening time.

[0004] Facing the passing behaviors of different passing groups, the fixed speed and time mode cannot meet the requirements of different passing groups for the opening and closing speeds and times of one-way doors, and manual intervention relies on personnel on duty and has a risk of misjudgment. Therefore, the existing methods for controlling the opening and closing of one-way doors have technical problems of low passing efficiency and poor user experience due to the inability to automatically adapt to different application scenarios. Summary of the Invention

[0005] The embodiments of this application provide a method, system, device, and computer-readable storage medium for controlling the opening and closing of a one-way door, which can adapt to different passing requirements and improve passing efficiency and user experience.

[0006] In a first aspect, the embodiments of this application provide a method for controlling the opening and closing of a one-way door, and the method includes:

[0007] Obtain the pressure distribution data and infrared radiation data in the passing area of the one-way door;

[0008] Based on the spatial distribution characteristics of the infrared radiation data, a preset temperature threshold, and the spatial distribution characteristics of the pressure distribution data, determine the passing type of the passing target, and the passing type includes human passing and human-cooperating device passing;

[0009] According to the spatial temporal characteristics corresponding to the passing target in the pressure distribution data and a preset gait template, determine the gait characteristic information of the passing target;

[0010] According to the passing type of the passing target and the gait characteristic information of the passing target, determine the passing behavior information of the passing target;

[0011] Determine the pedestrian flow density information of the one-way door passage area according to the pressure distribution data, and determine the target switch control information corresponding to the passage behavior information and pedestrian flow density information of the passage target according to the corresponding relationship between the preset pedestrian flow density information, passage behavior information, and switch control information;

[0012] Complete the control of the one-way door switch according to the target switch control information.

[0013] In an implementable embodiment, based on the spatial distribution characteristics of the infrared radiation data, the preset temperature threshold, and the spatial distribution characteristics of the pressure distribution data, determine the passage type of the passage target, where the passage type includes human passage and human-coordinated device passage, including:

[0014] Extract the coordinates of the continuous temperature region in the infrared radiation data that is higher than the preset temperature threshold, and obtain the temperature region boundary, the centroid coordinates of the temperature region, and the coverage area of the temperature region through the region growing algorithm;

[0015] Calculate the coordinates of the pressure concentration region in the pressure distribution data where the pressure value exceeds the preset threshold, and obtain the pressure region boundary, the centroid coordinates of the pressure region, and the shape of the pressure region through the geometric envelope algorithm;

[0016] Perform spatial coordinate mapping based on the centroid coordinates of the temperature region and the centroid coordinates of the pressure region, and generate a coupling coefficient representing the correlation between the heat source and the pressure distribution by calculating the spatial overlap degree and the centroid offset;

[0017] According to the coverage area of the temperature region and the shape of the pressure region, obtain the ratio of the heat source pressure distribution area through the temperature field gradient attenuation analysis and the symmetry detection of the pressure distribution form, and determine the collaborative determination value representing the degree of human-device collaboration according to the coupling coefficient;

[0018] Compare the collaborative determination value with the preset threshold range. When the collaborative determination value is within the first threshold interval of the preset threshold range, determine that the passage type of the passage target is human passage; when it is within the second threshold interval of the preset threshold range, determine that the passage type of the passage target is human-coordinated device passage.

[0019] In an implementable embodiment, perform spatial coordinate mapping based on the centroid coordinates of the temperature region and the centroid coordinates of the pressure region, and generate a coupling coefficient representing the correlation between the heat source and the pressure distribution by calculating the spatial overlap degree and the centroid offset, including:

[0020] Project the centroid coordinates of the temperature region and the centroid coordinates of the pressure region onto a preset plane coordinate system to generate a pair of centroid coordinates;

[0021] Based on the vertex distribution of the temperature region boundary and the pressure region boundary, calculate the ratio of the geometric intersection area to the union area to generate a spatial overlap degree parameter;

[0022] Calculate the distance vector between the centroid of the temperature region and the centroid of the pressure region according to the centroid coordinate pair, and weight the distance vector by the coverage area of the temperature region to obtain the centroid offset;

[0023] Determine the weight based on the energy concentration degree of the temperature region boundary and the pressure distribution symmetry degree of the pressure region shape, and perform weighted superposition of the spatial overlap degree parameter and the centroid offset to generate the coupling coefficient.

[0024] In an implementable embodiment, according to the passing type of the passing target and the gait feature information of the passing target, determine the passing behavior information of the passing target, including:

[0025] Perform multi-dimensional space encoding on the device collaboration identifier in the passing type and the gait cycle and stride parameters in the gait feature information to generate a joint feature vector including the device collaboration identifier, the gait cycle sequence, and the stride sequence;

[0026] Based on the gait cycle sequence and the stride sequence in the joint feature vector, perform time series alignment processing with a preset gait template, calculate the phase offset of the gait cycle sequence and the difference index of the stride sequence, and generate a gait matching degree parameter;

[0027] Adjust the gait matching degree parameter according to the status value of the device collaboration identifier to obtain the target gait matching degree parameter;

[0028] Based on the target gait matching degree parameter, extract the matching degree fluctuation characteristics within a continuous time window, and obtain the passing state category according to the status value of the device collaboration identifier and the matching degree fluctuation characteristics and the preset determination conditions;

[0029] Match the passing state category with a preset behavior level mapping table, and output the passing behavior information characterizing the movement urgency degree, the gait stability level, and the device collaboration state.

[0030] In an implementable embodiment, based on the gait cycle sequence and the stride sequence in the joint feature vector, perform time series alignment processing with a preset gait template, calculate the phase offset of the gait cycle sequence and the difference index of the stride sequence, and generate a gait matching degree parameter, including:

[0031] Align the waveform feature points of the gait cycle sequence with the reference cycle of the gait template to generate the aligned gait cycle sequence and stride sequence;

[0032] Extract the cycle fluctuation parameters from the aligned gait cycle sequence, perform segment-by-segment difference calculation with the reference cycle of the gait template to generate the phase offset, and based on the aligned stride sequence, extract the stride dynamic range and the difference coefficient to generate the difference index;

[0033] Linearly superimpose the phase offset and the difference index according to a preset weight ratio to generate a gait matching degree parameter.

[0034] In an implementable embodiment, based on the target gait matching degree parameter, extract the matching degree fluctuation characteristics within a continuous time window, and according to the status value of the device collaboration identifier and the matching degree fluctuation characteristics and preset determination conditions, obtain the passage status category, including:

[0035] Intercept the target gait matching degree parameter by a sliding window according to the reference cycle length of the preset gait template to generate a segmented matching degree sequence;

[0036] Calculate the mean value, variance and peak interval parameter in the segmented matching degree sequence to generate a statistical feature vector including mean value fluctuation, variance fluctuation and peak interval fluctuation;

[0037] Determine the determination threshold range of the statistical feature vector according to the status value of the device collaboration identifier, and compare the statistical feature vector with the determination threshold range to obtain the passage status category.

[0038] In an implementable embodiment, determine the determination threshold range of the statistical feature vector according to the status value of the device collaboration identifier, and compare the statistical feature vector with the determination threshold range to obtain the passage status category, including:

[0039] When the status value of the device collaboration identifier is 1, set the determination threshold of the variance fluctuation in the statistical feature vector to the first threshold corresponding to the human body collaborative device passage scenario;

[0040] When the status value of the device collaboration identifier is 0, set the determination threshold of the peak interval fluctuation in the matching degree fluctuation characteristics to the second threshold corresponding to the human body passage scenario;

[0041] Compare the variance fluctuation with the first threshold. When the variance fluctuation is greater than the preset abnormal fluctuation threshold, the passage status category is the gait abnormal status;

[0042] When the variance fluctuation is less than or equal to the preset abnormal fluctuation threshold, when the status value of the device collaboration identifier is 1 and the variance fluctuation is less than the first threshold, the passage status category is the device passage status;

[0043] When the variance fluctuation is less than or equal to the preset abnormal fluctuation threshold, when the status value of the device collaboration identifier is 0 and the peak interval fluctuation is less than the second threshold, the passage status category is the emergency passage status.

[0044] In a second aspect, an embodiment of the present application provides a one-way door switch control system, and the system includes:

[0045] An acquisition module, configured to acquire pressure distribution data and infrared radiation data of the one-way door passage area;

[0046] A determination module, configured to determine the passage type of the passage target based on the spatial distribution characteristics of the infrared radiation data, a preset temperature threshold, and the spatial distribution characteristics of the pressure distribution data, where the passage type includes human passage and human-cooperated device passage;

[0047] The determination module is further configured to determine the gait feature information of the passage target according to the spatial temporal characteristics corresponding to the passage target in the pressure distribution data and a preset gait template;

[0048] The determination module is further configured to determine the passage behavior information of the passage target according to the passage type of the passage target and the gait feature information of the passage target;

[0049] The determination module is further configured to determine the crowd density information of the one-way door passage area according to the pressure distribution data, and determine the target switch control information corresponding to the passage behavior information and the crowd density information of the passage target according to the corresponding relationship between the preset crowd density information, the passage behavior information, and the switch control information;

[0050] A control module, configured to control the opening and closing of the one-way door according to the target switch control information.

[0051] In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement a one-way door switch control method according to any one of the implementation manners in the first aspect.

[0052] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, a one-way door switch control method according to any one of the implementation manners in the first aspect is implemented.

[0053] A unidirectional door switch control method, system, device, and computer-readable storage medium according to an embodiment of the present application achieve intelligent control of the unidirectional door through multi-source data fusion and dynamic behavior analysis. First, pressure distribution and infrared radiation data are synchronously collected to construct a spatial mapping relationship between the heat source and the pressure area, solving the defect that a single sensor is vulnerable to environmental interference. Secondly, based on the centroid offset of the heat source and pressure morphology analysis, human passage and device collaboration scenarios are accurately distinguished, avoiding misjudgment of irregular pressure distributions by traditional methods. Further, by combining gait timing feature extraction and template matching, gait stability and urgency are quantified, breaking through the limitation of being unable to adapt to dynamic behaviors in the fixed-rate mode. Finally, by fusing passage types, gait parameters, and crowd density information, a door speed command is dynamically generated to achieve differential control such as accelerating emergency passage and delaying device transportation. Through multi-source perception and behavior semantic modeling, the present application overcomes the defect that traditional fixed rates or manual interventions cannot automatically adapt to different passage scenarios, solves the problems of low efficiency and safety hazards caused by misjudgment, and realizes the balance between safety and efficiency in high-density crowd scenarios.

[0054] Furthermore, through the joint encoding of device collaboration identification and gait parameters, a joint vector containing device status and gait dynamic features is constructed to solve the deficiency that traditional models ignore device collaboration scenarios. Based on the time series alignment algorithm, the interference of step frequency differences is eliminated, and gait rhythm abnormalities and propulsion stability differences are quantified to improve the recognition robustness in complex scenarios. By dynamically adjusting parameter weights in combination with device status, the sensitivity to gait mutations and device bumps is enhanced. Finally, through fluctuation feature extraction and behavior level mapping, semantic commands such as emergency passage and device transportation are output. For device collaboration scenarios and emergency passage requirements, the present application solves the problems of lagging response and misjudgment of abnormal states in the prior art through dynamic parameter fusion and priority determination, and significantly improves the passage safety and emergency response capabilities in scenarios such as medical treatment and transportation hubs. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required to be used in the embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0056] Figure 1 is a flowchart showing the unidirectional door switch control method provided by an embodiment of the present application;

[0057] Figure 2 is a flowchart showing the method for determining the passage type of the passage target provided by an embodiment of the present application;

[0058] Figure 3 is a flowchart showing the method for determining the passage behavior information of the passage target provided by an embodiment of the present application;

[0059] Figure 4 It is a schematic structural diagram of a one-way door switch control system provided by an embodiment of the present application;

[0060] Figure 5 It is a schematic hardware structure diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0061] The features and exemplary embodiments of various aspects of the present application will be described in detail below. To make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by showing examples of the present application.

[0062] It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, elements defined by the statement "comprising..." do not preclude the existence of additional identical elements in the process, method, article or device comprising the said elements.

[0063] In public places such as high-speed railway stations, airports, and hospitals, as a core facility for controlling the flow of people, one-way doors need to achieve efficient passage while ensuring passage safety. In such scenarios, the target passage behaviors are complex and diverse: ordinary pedestrians have a stable gait but strong mobility, those carrying large luggage have limited moving speed, medical devices such as wheelchairs and stretchers require an extended door opening time to avoid collisions, and in the case of emergency evacuation, the door needs to respond quickly. The requirements for the opening and closing speed, opening duration, and action sensitivity of one-way doors vary significantly for different passage behaviors, and the traditional fixed control mode is difficult to meet the dynamic adaptation requirements.

[0064] In the prior art, the one-way door control method mainly relies on a fixed switching rate or manual intervention. In the fixed-rate mode, the door completes the opening and closing actions at a preset speed and time. For example, a mechanical limit device is used to enforce one-way passage, or a simple sensor (such as an infrared beam) is used to trigger a fixed-delay opening. Such methods cannot distinguish the types and behavioral characteristics of passing targets. For example, when a wheelchair passes, the door may close too quickly, leading to a collision risk, and the response delay during an emergency evacuation may cause congestion. In the manual intervention mode, although the opening time can be extended by long-pressing a button, it relies on personnel on duty and there is a risk of misjudgment. For example, it is difficult for staff to identify the equipment's passing needs in a timely manner during peak hours, resulting in an imbalance between passing efficiency and safety.

[0065] The core defect of the above methods lies in the lack of intelligent perception and dynamic regulation capabilities for passing intentions. The fixed-rate mode ignores the diversity of passing scenarios and is difficult to adapt to the different needs of different groups; the manual intervention mode is inefficient and unreliable. Therefore, due to the inability to achieve passing behavior recognition and adaptive adjustment of door control parameters in the prior art, the passing efficiency is low and potential safety hazards are prominent. There is an urgent need for a new regulation scheme that integrates multi-source perception and intelligent decision-making.

[0066] To solve the problems of the prior art, the embodiments of the present application provide a one-way door opening and closing regulation method, system, device, and computer-readable storage medium. First, the one-way door opening and closing regulation method provided by the embodiments of the present application will be introduced below.

[0067] Figure 1 The flowchart of the one-way door opening and closing regulation method provided by an embodiment of the present application is shown. As Figure 1 shown, the method includes steps S110 to S160.

[0068] S110: Obtain the pressure distribution data and infrared radiation data of the one-way door passing area.

[0069] The pressure distribution data refers to the pressure values and their spatial distribution information at each position in the passing area collected in real time by a pressure sensor array, including the pressure intensity, contact area, and dynamic change trajectory, and is used to detect the contact area and movement state of the passing target. The infrared radiation data refers to the heat source distribution information in the passing area captured by an infrared sensor, including the heat source temperature, spatial coordinates, and thermal field gradient, and is used to identify the difference between a living target and a non-living device.

[0070] Deploy a pressure sensor array on the ground in the one-way door passage area. Use piezoelectric film or capacitive sensor technology to record the pressure values of each node in real time according to the preset sampling frequency, generate a two-dimensional pressure distribution matrix, and extract the pressure concentration area through the coordinates of the non-zero area. At the same time, install an infrared thermal imager on the top or side of the door to capture the infrared image of the passage area at a fixed scanning frequency and generate a temperature distribution matrix, and extract the continuous heat source area higher than the ambient temperature. The pressure matrix and the infrared temperature matrix can also be synchronized through timestamps and mapped to the same spatial coordinate system to ensure the spatio-temporal consistency of multi-source data.

[0071] Exemplarily, a pressure sensor array is installed on the ground of the passage of the one-way door to cover an area of 1 meter wide and 2 meters long, and an infrared thermal imager is installed on the top of the door to cover the entire passage field of view. When a wheelchair user passes through, the pressure sensor detects the long-strip distribution trajectory of the high pressure value in the area where the wheels contact, and the infrared sensor captures the high-temperature heat source of the human torso and the low-temperature area of the wheelchair metal parts. The system outputs the pressure distribution matrix in real time to mark the wheelchair wheel pressure position and the infrared temperature matrix to mark the human heat source coordinates for subsequent steps to determine the passage type.

[0072] S120: Determine the passage type of the passage target based on the spatial distribution characteristics of the infrared radiation data, the preset temperature threshold, and the spatial distribution characteristics of the pressure distribution data. The passage types include human passage and human collaborative device passage.

[0073] The spatial distribution characteristics of the infrared radiation data refer to the temperature distribution pattern of the heat source in the passage area collected by the infrared sensor, including the spatial coordinates, coverage range, and temperature gradient change characteristics of the heat source, which are used to identify the differences between living targets and non-living devices. The preset temperature threshold is a critical value set according to the normal body temperature range of the human body, which is used to distinguish the human heat source from the environmental noise. The spatial distribution characteristics of the pressure distribution data are the morphological information of the contact area of the passage target obtained through the pressure sensor array, including the geometric shape, centroid position, and dynamic change trajectory of the pressure concentration area.

[0074] Extract the high-temperature heat source distribution data in the passage area through the infrared sensor, filter out the invalid noise in combination with the preset temperature threshold, and identify the potential human heat source and its coverage area. Synchronously analyze the morphological characteristics of the contact area collected by the pressure sensor, including the geometric shape and centroid position of the pressure concentration area. Conduct a correlation analysis on the spatial distribution characteristics of the heat source and the pressure area, and determine whether the passage target is a human independent passage or a human collaborative device passage based on the matching degree between the heat source coverage range and the pressure pattern.

[0075] S130: Determine the gait characteristic information of the passage target according to the spatial and temporal characteristics corresponding to the passage target in the pressure distribution data and the preset gait template.

[0076] Spatial-temporal features refer to the dynamic pressure change trajectories of passing targets collected by a pressure sensor array in the time and space dimensions, including the movement paths of pressure concentration areas, the temporal sequence of pressure intensity fluctuations, and the morphological evolution of contact areas, which are used to characterize gait rhythm and movement stability. A gait template is a preset standardized gait parameter model that contains benchmark data such as the period, stride, and pressure distribution symmetry of typical human gaits, and is used to match and compare with the gait features collected in real time. Gait feature information refers to the dynamic parameters extracted based on pressure temporal data, including gait period, stride, and pressure distribution symmetry, which are used to quantify movement rhythm and stability.

[0077] Based on the dynamic data of the pressure sensor array, continuously track the pressure concentration area of the passing target in consecutive frames, generate the movement trajectory of the pressure centroid and the temporal change curve of the contact area morphology, and extract the gait period and stride parameters. Through the analysis of pressure distribution symmetry and dynamic stability evaluation, quantify the gait stability and generate a multi-dimensional feature vector. Compare the multi-dimensional feature vector with the preset gait template, calculate the phase offset and difference index, and screen out the key gait feature parameters.

[0078] Exemplarily, when a passenger passes by pushing a suitcase, the pressure sensor captures the pressure distribution differences between the double-leg gait and the suitcase wheels. The double-leg gait shows periodic alternating pressure peaks, and the stride and period match the gait template; the suitcase wheels show a continuous linear pressure trajectory, and an abnormal mark is triggered because it does not conform to the periodic characteristics of the template. The system generates gait feature information by combining gait stability parameters for subsequent steps to determine the passing behavior.

[0079] S140: Determine the passing behavior information of the passing target according to the passing type of the passing target and the gait feature information of the passing target.

[0080] The passing behavior information is a semantic description of the target's movement intention, including the emergency passing state (fast movement requires priority response), the equipment passing state (uniform transportation requires extended door control time), and the gait abnormal state (imbalance or fall requires safety braking), which provides a decision-making basis for the door control strategy.

[0081] By fusing the passing type and gait feature information to construct a multi-dimensional data representation model, integrating the equipment collaboration identifier and gait dynamic parameters to form a unified feature space; analyzing the key feature differences by extracting the regularities of gait temporal changes; mapping the feature differences to semantic passing behavior information based on a dynamic rule adaptation mechanism, which can include the emergency passing state, the equipment passing state, and the gait abnormal state, etc.

[0082] S150: Determine the pedestrian flow density information of the one-way door passage area based on the pressure distribution data, and determine the target switch control information corresponding to the passage behavior information and pedestrian flow density information of the passage target according to the preset corresponding relationship among the pedestrian flow density information, passage behavior information, and switch control information.

[0083] The pedestrian flow density information refers to the statistical value of the pressure distribution per unit area within the one-way door passage area collected by the pressure sensor array, including the proportion of the pressure coverage area, the total pressure value, and the dynamic change trend, which is used to quantify the congestion degree of the passage area. The switch control information refers to the set of dynamic gating instructions generated according to the preset strategy, including the door opening speed, holding time, closing sensitivity, and abnormal response strategy, which is used to adapt to the gating requirements of different pedestrian flow densities and passage behaviors. The preset corresponding relationship refers to the mapping logic established between the pedestrian flow density, passage behavior, and switch control parameters through a rule library or a machine learning model. For example, in a high-density scenario, the opening time is extended, and the closing speed is reduced when equipment is passing.

[0084] Calculate the proportion of the pressure coverage area and the dynamic change rate within the passage area based on the pressure distribution data, and divide the pedestrian flow density level into low density, medium density, or high density. Input the passage behavior information and the pedestrian flow density level into the preset mapping model, and generate the target switch control instruction through multi-dimensional rule matching. For example, in a high-density scenario, the door holding time is extended, the closing speed is reduced when equipment is passing, and the highest-priority response is triggered during emergency passage. The dynamic parameter adaptation combines the device collaboration identifier and gait characteristics to ensure that the gating strategy matches the real-time scenario.

[0085] Exemplarily, when the pressure coverage area exceeds 70% and continuous gait cycle compression is detected, the system determines that it is in a high-density congestion state, triggers the door holding time to be extended to 5 seconds, and reduces the opening speed to 0.5 times the standard rate. If the passage behavior information is the device collaboration identifier and the pedestrian flow density is medium, the system extends the holding time to 4 seconds and sets the closing speed to 0.3 times the standard rate to prevent pinching. When the gait characteristics show that the phase offset exceeds the limit and the stride difference is significant, regardless of the current density, the system immediately opens the door at the maximum speed and maintains the fully open state until the target leaves.

[0086] S160: Complete the control of the one-way door switch according to the target switch control information.

[0087] Call the motor drive module based on the target switch control information, and convert the instruction parameters (such as opening speed, holding time) into the PWM control signal or CAN bus instruction of the motor. Real-time collect the execution status data through the door angle encoder or speed sensor, compare it with the target parameters and calculate the deviation value. If the deviation exceeds the preset tolerance range, dynamically adjust the motor output through the PID control algorithm, for example, reduce the speed to compensate for the inertia error or extend the holding time to adapt to the flow fluctuation of people. Synchronously execute the abnormal response strategy, for example, immediately trigger the reverse braking and send an alarm signal when it is detected that the door is blocked.

[0088] In one embodiment, the piezoelectric film sensor array deployed on the ground of the one-way door at the security inspection exit channel field of the airport real-time collects the pressure distribution data of the footsteps of passengers and the rollers of the luggage, generates a two-dimensional pressure matrix and marks the high-pressure concentration area; the infrared thermal imager installed on the top of the door frame scans the passing area at a rate of 10 frames per second, and extracts the human torso heat source with a temperature higher than 35°C and the contour of the low-temperature metal luggage. The system calculates the coupling coefficient through the spatial offset between the centroid coordinates of the heat source and the centroid of the pressure, and combines the heat source coverage area and the long-strip distribution characteristics of the pressure area to determine the type of "human and equipment coordinated passage". At the same time, based on the pressure time-series data, extract the difference index between the gait cycle of the passenger and the roller trajectory. When the gait cycle is stable but the roller pressure has no continuous fluctuation, generate the behavior information of the "equipment passage state". Determine that the flow of people is medium to high density according to the pressure coverage area ratio reaching 65%, trigger the door to open at 0.4 times the standard speed and hold for 4 seconds to ensure the safe passage of passengers carrying luggage; when the infrared sensor detects that the subsequent passengers are approaching at an accelerated speed, immediately switch to the emergency response mode, the door opens at full speed and maintains the fully open state until the pressure sensor confirms that there are no remaining targets in the passing area and then resumes the normal control.

[0089] This embodiment realizes the intelligent regulation of the one-way door through multi-source data fusion and dynamic behavior analysis. First, synchronously collect the pressure distribution and infrared radiation data, construct the spatial mapping relationship between the heat source and the pressure area, and solve the defect that a single sensor is vulnerable to environmental interference; secondly, based on the centroid offset of the heat source and the pressure morphology analysis, accurately distinguish the human passage and the equipment coordination scenario, and avoid the misjudgment of the irregular pressure distribution by the traditional method; further combine the gait time-series feature extraction and template matching to quantify the gait stability and emergency level, and break through the limitation that the fixed rate mode cannot adapt to dynamic behaviors; finally, fuse the passage type, gait parameters and flow density information, and dynamically generate the door speed instruction to realize differential control such as emergency passage acceleration and equipment transportation delay. This application overcomes the defects that the traditional fixed rate or manual intervention cannot automatically adapt to different passage scenarios through multi-source perception and behavior semantic modeling, solves the problems of low efficiency and safety hazards caused by misjudgment, and realizes the balance between safety and efficiency in high-density flow scenarios.

[0090] The problem in traditional one-way door control that it is impossible to accurately distinguish between the passage of an independent human body and the coordinated passage with a carried device. Since it is difficult to identify the complex behavioral characteristics when devices such as wheelchairs and luggage carts move in coordination with the human body in a fixed-rate mode or with manual intervention, it is easy to cause the door to close too quickly, resulting in collisions or response delays. To improve the passage safety and efficiency, the embodiments of the present application solve it in the following ways.

[0091] Figure 2 FIG. shows a flowchart of a method for determining the passage type of a passage target provided by an embodiment of the present application. As Figure 2 shown, the method includes steps S210 to S250.

[0092] In an implementable embodiment, step S120: Based on the spatial distribution characteristics of the infrared radiation data, the preset temperature threshold, and the spatial distribution characteristics of the pressure distribution data, determine the passage type of the passage target. The passage types include human passage and human-coordinated device passage, including:

[0093] S210: Extract the coordinates of the continuous temperature region in the infrared radiation data that is higher than the preset temperature threshold, and through the region growing algorithm, obtain the temperature region boundary, the centroid coordinates of the temperature region, and the coverage area of the temperature region.

[0094] The region growing algorithm is an image segmentation technology based on seed point diffusion, used to extract continuous high-temperature regions from infrared data, generate the temperature region boundary and centroid coordinates. By processing the infrared radiation data with the region growing algorithm, continuous high-temperature regions higher than the preset temperature threshold are extracted from the temperature matrix. The algorithm uses high-temperature pixels as the initial seed points, spreads to adjacent pixels, and merges regions where the temperature gradient meets the preset conditions to generate a closed temperature region boundary; the centroid coordinates of the temperature region are calculated based on the weighted average of the coordinates of the pixels within the boundary, and the coverage area of the temperature region is obtained by multiplying the number of pixels by the resolution.

[0095] S220: Calculate the coordinates of the pressure concentration region in the pressure distribution data where the pressure value exceeds the preset threshold, and through the geometric envelope algorithm, obtain the pressure region boundary, the centroid coordinates of the pressure region, and the shape of the pressure region.

[0096] The geometric envelope algorithm generates a geometric boundary by calculating the outer contour vertices of the pressure concentration region to describe the morphological characteristics of the pressure distribution. For the high-pressure value region in the pressure distribution data, the geometric envelope algorithm (such as the convex hull algorithm) is used to generate the minimum circumscribed polygon boundary to determine the geometric shape of the pressure concentration region; the centroid coordinates of the pressure region are calculated based on the weighted spatial position average of the pressure values, and the morphological characteristics of the pressure region are quantified by calculating the aspect ratio and symmetry detection (such as principal component analysis).

[0097] S230: Perform spatial coordinate mapping based on the centroid coordinates of the temperature region and the centroid coordinates of the pressure region, and generate a coupling coefficient representing the correlation between the heat source and the pressure distribution by calculating the spatial overlap degree and the centroid offset.

[0098] The spatial overlap degree is the ratio of the intersection area to the union area of the heat source and the pressure region, reflecting the consistency of spatial coverage. The centroid offset is the spatial position deviation of the distance vector between the heat source centroid and the pressure centroid after being weighted by the temperature region area.

[0099] Project the centroid coordinates of the temperature and pressure regions onto the same plane coordinate system, calculate the ratio of the geometric intersection area to the union area of the two as the spatial overlap degree parameter; calculate the distance vector between the centroids through the Euclidean distance formula, and weight the distance vector with the proportion of the temperature region coverage area as the weight to generate the centroid offset parameter. Based on the energy concentration degree (heat source gradient attenuation range) of the temperature region and the morphological symmetry parameter of the pressure region, dynamically allocate the weights of the spatial overlap degree and the centroid offset, and generate the coupling coefficient after weighted superposition.

[0100] S240: According to the temperature region coverage area and the pressure region shape, through the temperature field gradient attenuation analysis and the pressure distribution morphological symmetry detection, obtain the ratio of the heat source pressure distribution area, and determine the collaborative determination value representing the collaborative degree between the human body and the device according to the coupling coefficient.

[0101] The centroid offset is the spatial position deviation of the distance vector between the heat source centroid and the pressure centroid after being weighted by the temperature region area. The ratio of the heat source pressure distribution area quantifies the geometric adaptation degree between the heat source and the pressure region by analyzing the temperature field gradient attenuation range and the pressure morphology symmetry.

[0102] Combining the temperature field gradient attenuation analysis (the coverage range of the heat source energy spreading outwards) and the results of the pressure region morphological symmetry detection, calculate the ratio of the heat source coverage area to the pressure region area; fuse the area ratio and the coupling coefficient according to the preset weight ratio to generate the collaborative determination value representing the collaborative degree between the human body and the device.

[0103] S250: Compare the collaborative determination value with the preset threshold range. When the collaborative determination value is within the first threshold interval of the preset threshold range, determine that the passage type of the passage target is human passage; when it is within the second threshold interval of the preset threshold range, determine that the passage type of the passage target is human collaborative device passage.

[0104] Compare the collaborative determination value with the preset threshold range. If the determination value is within the first interval (high spatial overlap degree, low centroid offset and morphological adaptation), determine it as human passage; if it is within the second interval (low overlap degree, significant centroid offset and morphological difference), determine it as human collaborative device passage. Through multi-dimensional parameter fusion and dynamic threshold classification, accurate determination of the passage type is achieved.

[0105] Exemplarily, when a passenger pushes a luggage cart through a one-way door, the infrared thermal imager captures the high-temperature area of the human torso and the low-temperature signal of the metal frame of the luggage cart. The system uses a region growing algorithm to extract continuous high-temperature areas from the infrared temperature matrix as the human heat source, generates a closed boundary, and calculates the centroid coordinates and the covered area. Synchronously analyze the data of the pressure sensor, process the long strip-shaped pressure concentration area formed by the wheel pressure of the luggage cart through the geometric envelope algorithm, generate the minimum circumscribed polygon boundary, and extract morphological features such as the pressure centroid coordinates and the aspect ratio. Project the heat source and the pressure centroid onto the same plane coordinate system, and calculate the spatial overlap degree and the centroid offset amount between the two. Since the wheel pressure area of the luggage cart is far from the human heat source, the spatial overlap degree is significantly lower than the threshold value, and the centroid offset amount exceeds the human passage range after being weighted by the temperature area. Combining the temperature field gradient attenuation analysis (the heat source energy diffusion range is limited) and the pressure area morphological symmetry detection (the long strip-shaped trajectory is asymmetric), generate the low heat source pressure distribution area ratio. Finally, after the collaborative decision value fuses the above parameters and falls into the device collaborative interval, the system determines that the passage type is the human and device collaborative passage, triggers the door body to extend the opening time and the low-speed closing instruction, and ensures the safe passage of the luggage cart.

[0106] In this embodiment, by fusing the infrared heat source distribution characteristics and the pressure morphological characteristics, and combining multi-dimensional parameters such as the spatial overlap degree, the centroid offset amount, and the morphological symmetry to dynamically generate the collaborative decision value, the recognition accuracy of the human passage and the device collaborative scenario is significantly improved, and the technical bottleneck that the traditional single sensor is vulnerable to environmental interference and cannot distinguish complex passage behaviors is solved; through the preset threshold interval and the dynamic weight distribution mechanism, both the physical interpretability of the classification logic is guaranteed, and the adaptability of the algorithm to new devices and high-density scenarios is enhanced, effectively reducing the misjudgment rate and the collision risk, and realizing the collaborative optimization of safety and efficiency.

[0107] In an implementable embodiment, S230: Perform spatial coordinate mapping based on the centroid coordinates of the temperature area and the centroid coordinates of the pressure area, and generate a coupling coefficient representing the correlation between the heat source and the pressure distribution by calculating the spatial overlap degree and the centroid offset amount, including:

[0108] Project the centroid coordinates of the temperature area and the centroid coordinates of the pressure area onto a preset plane coordinate system to generate a centroid coordinate pair; calculate the ratio of the geometric intersection area to the union area based on the vertex distribution of the temperature area boundary and the pressure area boundary to generate a spatial overlap degree parameter; according to the centroid coordinate pair, calculate the distance vector between the centroid of the temperature area and the centroid of the pressure area, and weight the distance vector by the covered area of the temperature area to obtain the centroid offset amount; determine the weight based on the energy concentration degree of the temperature area boundary and the pressure distribution symmetry degree of the pressure area shape, and perform weighted superposition of the spatial overlap degree parameter and the centroid offset amount to generate a coupling coefficient.

[0109] The centroid coordinate pair refers to the coordinate combination formed by geometrically projecting the centroid coordinates of the infrared heat source region and the centroid coordinates of the pressure concentration region onto the same plane coordinate system, which is used to quantify the spatial correlation between the two. The spatial overlap parameter reflects the matching degree of the two in the spatial coverage range by calculating the ratio of the geometric intersection area of the heat source region and the pressure region to the union area. The energy concentration refers to the attenuation characteristic of the temperature gradient within the boundary of the infrared heat source, which is used to evaluate the diffusion range and energy distribution uniformity of the heat source; the pressure distribution symmetry is calculated by the geometric envelope algorithm to obtain the aspect ratio of the pressure region or the result of principal component analysis, which describes the regularity of the pressure pattern.

[0110] First, the centroid coordinates of the infrared and pressure regions are projected onto a unified plane coordinate system through affine transformation to eliminate the coordinate deviation caused by the difference in the sensor installation position. Based on the boundary vertex data of the heat source and pressure regions, the convex polygon intersection algorithm is used to calculate the geometric intersection area and union area of the two, and the spatial overlap parameter is generated. For example, if the heat source region and the wheel pressure region partially overlap, the lower the proportion of the intersection area, the weaker the spatial correlation between the two.

[0111] After that, after calculating the Euclidean distance between the centroids, the proportion of the temperature region coverage area in the total detection area is used as a weight factor to weight the distance vector. For example, when the heat source coverage area is large, its contribution weight to the offset is higher. At the same time, combining the heat source energy concentration (temperature gradient attenuation rate) and the pressure pattern symmetry (the degree of deviation of the aspect ratio from the standard value), the weight ratio of the spatial overlap and the centroid offset is dynamically adjusted. For example, when the heat source energy distribution is uneven, the weight of the spatial overlap is reduced and the weight of the centroid offset is increased.

[0112] Finally, the spatial overlap parameter and the weighted centroid offset are linearly superimposed according to the dynamic weights to generate a coupling coefficient that comprehensively characterizes the correlation between the heat source and the pressure distribution. This coefficient provides a fusion parameter basis for subsequent traffic type determination by quantifying the spatial coverage consistency, position deviation, and pattern adaptability.

[0113] In this embodiment, by dynamically fusing the heat source energy concentration and the pressure pattern symmetry parameters, a weighted superposition model of the spatial overlap and the centroid offset is constructed to generate a highly representative coupling coefficient, which significantly improves the recognition accuracy and algorithm robustness of the human-device collaboration scenario. Based on the temperature field gradient attenuation characteristic, the energy distribution range of the heat source is quantified, and combined with the geometric symmetry analysis of the pressure region, the weight ratio of the spatial overlap and the centroid offset is adaptively adjusted, effectively suppressing the influence of environmental noise interference and local data anomalies on the classification result, and breaking through the adaptability bottleneck of the traditional static threshold determination in complex scenarios. Through multi-dimensional parameter fusion and dynamic weight distribution mechanism, accurate modeling of the spatial correlation between the heat source and the pressure distribution is realized, providing a highly reliable decision basis for traffic type determination.

[0114] In the one-way door control method in the prior art, since the device cooperation state and gait dynamic characteristics cannot be effectively integrated, the recognition accuracy of passing behaviors is low, and the dynamic adaptation ability is poor. It is difficult to distinguish complex scenarios such as device cooperative passing, emergency acceleration, or gait imbalance, leading to rigid door control strategies and potential safety hazards. To solve the above technical problems, the present application is solved through the following embodiments.

[0115] Figure 3 The flowchart shows a method for determining passing behavior information of a passing target provided by an embodiment of the present application. As Figure 3 shown, the method includes steps S310 to S350.

[0116] In an implementable embodiment, step S140: Determine the passing behavior information of the passing target according to the passing type of the passing target and the gait feature information of the passing target, including:

[0117] S310: Perform multi-dimensional space encoding on the device cooperation identifier in the passing type and the gait cycle and stride parameters in the gait feature information to generate a joint feature vector including the device cooperation identifier, gait cycle sequence, and stride sequence.

[0118] Multi-dimensional space encoding refers to mapping discrete device cooperation identifiers (such as marking independent human passing as 0 and device cooperative passing as 1) and continuous gait cycles and stride parameters through normalization processing into the same high-dimensional feature space to form a structured data vector. The joint feature vector is a multi-dimensional data set containing the device cooperation identifier, gait cycle sequence, and stride sequence, and is used to characterize the composite behavior features of the target.

[0119] Perform standardization processing (such as Z-score normalization) on the device cooperation identifier (such as marking independent human passing as 0 and device cooperative passing as 1) and the gait cycle and stride parameters. After eliminating the dimension difference, generate a joint feature vector through feature splicing. For example, in the device cooperation scenario, the gait cycle is stable but the roller track has no fluctuation, and the normal gait and the device track are distinguished through the difference in the feature vector.

[0120] S320: Based on the gait cycle sequence and stride sequence in the joint feature vector, perform time series alignment processing with a preset gait template, calculate the phase offset of the gait cycle sequence and the difference index of the stride sequence, and generate a gait matching degree parameter.

[0121] The phase offset refers to the waveform difference between the real-time gait cycle sequence and the preset template after time series alignment, reflecting the degree of abnormal gait rhythm; the difference index quantifies the degree of movement emergency by calculating the deviation of the dynamic range of the stride sequence from the reference value.

[0122] The dynamic time warping (DTW) algorithm is used to align the real-time gait cycle sequence with the preset template, calculate the phase difference at each time point after alignment, and generate a phase offset sequence; synchronously analyze the fluctuation amplitude of the stride sequence, and calculate the standard deviation ratio of it to the template reference value as the difference index. The two are superimposed according to the preset weight to generate the gait matching degree parameter.

[0123] S330: According to the status value of the device collaboration identifier, adjust the gait matching degree parameter to obtain the target gait matching degree parameter.

[0124] Adjust the weight of the matching degree parameter according to the device collaboration identifier status value. For example, in the device collaboration scenario, reduce the sensitivity of gait cycle fluctuations (weight set to 0.3), enhance the weight of the stride difference index (weight set to 0.7), and avoid the static pressure of the roller track from interfering with the determination result.

[0125] S340: Based on the target gait matching degree parameter, extract the matching degree fluctuation characteristics within the continuous time window, and obtain the passage status category according to the status value of the device collaboration identifier and the matching degree fluctuation characteristics and the preset determination conditions.

[0126] The matching degree fluctuation characteristics are statistical parameters (such as mean, variance, peak interval) extracted from the continuous time window, which are used to describe the dynamic changes of gait stability.

[0127] S350: Match the passage status category with the preset behavior level mapping table, and output the passage behavior information characterizing the movement urgency, gait stability level and device collaboration status.

[0128] Intercept the target gait matching degree parameter based on the sliding window, calculate the mean fluctuation, variance fluctuation and peak interval parameters within the window to form a statistical feature vector; select the determination threshold according to the device collaboration identifier, compare the feature vector with the preset conditions, and output the passage status category (such as emergency passage, device transportation, abnormal gait). Finally, through the preset behavior level mapping table, convert the status category into semantic passage behavior information.

[0129] Exemplarily, first encode the device collaboration identifier (identifier is 1) with the detected gait cycle (stable 1.2 seconds / step) and stride (0.6 meters) parameters into a joint feature vector. Align the real-time gait cycle with the template waveform through the DTW algorithm, calculate the phase offset as 0.05 seconds, and the difference index as 0.3 (low stride difference due to no roller pressure fluctuation). Then the device collaboration identifier triggers the weight of the stride difference index to be increased to 0.7, generating the target gait matching degree parameter of 0.25. Extract the mean fluctuation of 0.02 and variance fluctuation of 0.01 of the matching degree within the continuous 5-second window, and determine it as the stable device passage status. Finally, combine the preset mapping table and output the "device passage status" behavior information.

[0130] In this embodiment, through the joint encoding of device collaboration identification and gait parameters, a joint vector containing device status and gait dynamic characteristics is constructed to address the deficiency that traditional models ignore the device collaboration scenario. Based on the time series alignment algorithm, the interference of step frequency differences is eliminated, the gait rhythm abnormality and propulsion stability difference are quantified, and the recognition robustness in complex scenarios is improved. The parameter weights are dynamically adjusted in combination with the device status to enhance the sensitivity to gait mutations and device bumps. Finally, through the extraction of fluctuation characteristics and the mapping of behavior levels, semantic instructions such as emergency passage and device transportation are output. This application addresses the device collaboration scenario and the emergency passage requirement, and through dynamic parameter fusion and priority determination, solves the problems of lagged response and misjudgment of the prior art to abnormal states, and significantly improves the passage safety and emergency response capabilities in scenarios such as medical treatment and transportation hubs.

[0131] In an implementable embodiment, S320: Based on the gait cycle sequence and stride sequence in the joint feature vector, perform time series alignment processing with a preset gait template, calculate the phase offset of the gait cycle sequence and the difference index of the stride sequence, and generate a gait matching degree parameter, including:

[0132] Align the waveform feature points of the gait cycle sequence with the reference cycle of the gait template to generate the aligned gait cycle sequence and stride sequence; extract the cycle fluctuation parameters from the aligned gait cycle sequence, perform segment-by-segment difference calculation with the reference cycle of the gait template to generate the phase offset, and based on the aligned stride sequence, extract the stride dynamic range and difference coefficient to generate the difference index; linearly superimpose the phase offset and the difference index according to a preset weight ratio to generate the gait matching degree parameter.

[0133] The gait matching degree parameter is a weighted linear combination of the phase offset and the difference index, and is used to comprehensively evaluate the global similarity between the gait and the template.

[0134] First, the dynamic time warping (DTW) algorithm is adopted. Using the waveform feature points (such as peaks and valleys) of the reference period of the preset gait template as anchor points, the real-time gait cycle sequence is non-linearly stretched or compressed to generate a gait sequence with aligned time axes. For example, since the trajectory of the suitcase wheels has no periodic fluctuations, after DTW alignment, the waveform difference from the human gait template is significant, triggering a phase shift marker. Then, segmented fluctuation parameters (such as the mean and variance of a single-step cycle) are extracted from the aligned gait cycle sequence, compared with the reference period of the template segment by segment, and the cumulative value of the local difference at each time point is calculated to generate a global phase shift amount. For example, in an emergency passage scenario, the gait cycle is compressed, resulting in an over-limit phase shift amount. Based on the aligned stride sequence, its dynamic range (such as the difference between the maximum and minimum strides) is statistically calculated, and a ratio operation is performed with the standard deviation of the reference stride of the template to quantify the amplitude of stride fluctuations. For example, when pushing the suitcase at a constant speed, the stride difference index approaches 1, while when running at an accelerated pace, the index increases significantly. Finally, the phase shift amount and the difference index are linearly superimposed according to a preset weight (such as 0.6:0.4) to generate a gait matching degree parameter. The weight allocation is dynamically adjusted according to the device cooperation state. For example, when the device is passing through, the weight of the phase shift is reduced, enhancing the sensitivity to stride differences.

[0135] In an implementable embodiment, S340: Based on the target gait matching degree parameter, extract the matching degree fluctuation characteristics within a continuous time window. According to the state value of the device cooperation identifier and the matching degree fluctuation characteristics and preset determination conditions, obtain the passage state category, including:

[0136] According to the reference period length of the preset gait template, perform a sliding window cut on the target gait matching degree parameter to generate a segmented matching degree sequence; calculate the mean, variance, and peak interval parameters in the segmented matching degree sequence to generate a statistical feature vector including mean fluctuation, variance fluctuation, and peak interval fluctuation; determine the determination threshold range of the statistical feature vector according to the state value of the device cooperation identifier, and compare the statistical feature vector with the determination threshold range to obtain the passage state category.

[0137] The segmented matching degree sequence is a set of subsequence collections generated after the sliding window cut. Each subsequence contains the time series data of the matching degree parameter within the current window. The statistical feature vector is a quantization index generated by calculating the mean fluctuation, variance fluctuation, and peak interval parameters of the segmented sequence, used to describe the stability and abnormality of the gait matching degree. The mean fluctuation reflects the overall deviation degree of the matching degree, the variance fluctuation represents the discreteness of the matching degree, and the peak interval fluctuation reveals the interval law of periodic abnormalities.

[0138] First, based on the reference cycle length of the gait template (such as the average gait cycle of adults), a fixed-length sliding window is used to intercept the target gait matching degree parameter. The window length is the same as the reference cycle to ensure that each window covers a complete gait motion. For example, if the reference cycle is 1.2 seconds, the window length is set to 1.2 seconds, and the step size is set to 0.3 seconds to allow overlapping sampling and avoid loss of key features. Then, for each segmented matching degree sequence, calculate its mean fluctuation (the difference between the current window mean and the historical mean), variance fluctuation (the ratio of the current window variance to the historical variance), and peak interval fluctuation (the average time difference between adjacent peaks). For example, after eliminating short-term noise through a moving average algorithm, the statistical characteristics of the data within the window are extracted to generate a multi-dimensional feature vector. Finally, according to the status value (0 or 1) of the device collaboration identifier, different decision threshold ranges are selected, and the statistical feature vector is compared with the decision threshold ranges to obtain the passage status category.

[0139] In an implementable embodiment, determining the decision threshold range of the statistical feature vector according to the status value of the device collaboration identifier, and comparing the statistical feature vector with the decision threshold range to obtain the passage status category, including:

[0140] When the status value of the device collaboration identifier is 1, set the decision threshold of the variance fluctuation in the statistical feature vector to the first threshold corresponding to the human-body collaborative device passage scenario; when the status value of the device collaboration identifier is 0, set the decision threshold of the peak interval fluctuation in the matching degree fluctuation feature to the second threshold corresponding to the human passage scenario; compare the variance fluctuation with the first threshold. In the case where the variance fluctuation is greater than the preset abnormal fluctuation threshold, the passage status category is the gait abnormal state; in the case where the variance fluctuation is less than or equal to the preset abnormal fluctuation threshold, when the status value of the device collaboration identifier is 1 and the variance fluctuation is less than the first threshold, the passage status category is the device passage state; in the case where the variance fluctuation is less than or equal to the preset abnormal fluctuation threshold, when the status value of the device collaboration identifier is 0 and the peak interval fluctuation is less than the second threshold, the passage status category is the emergency passage state.

[0141] The variance fluctuation refers to the change in the degree of dispersion of the target gait matching degree parameter within consecutive time windows, reflecting the dynamic deviation of gait stability. The peak interval fluctuation describes the time interval difference between adjacent peaks in the matching degree parameter, and is used to capture the rhythm disorder of periodic abnormalities or emergency acceleration behaviors. The first threshold corresponding to the human-body collaborative device passage scenario is the upper limit of tolerance for the variance fluctuation of the matching degree in the device collaboration state, and is used to distinguish between stable device transportation and bumpy abnormalities; the second threshold corresponding to the human passage scenario is the sensitive limit for the peak interval fluctuation during independent human passage, and is used to identify gait imbalance or emergency acceleration.

[0142] When the device cooperation identifier is 1, such as when a wheelchair or a luggage cart passes through, according to the stability requirements of the device transportation scenario, the determination threshold of the variance fluctuation is set to the first threshold, allowing slight fluctuations when the device moves in cooperation with the human body. When the device cooperation identifier is 0, that is, when the human body passes independently, the system switches to the human gait monitoring mode, and the determination threshold of the peak interval fluctuation is set to the second threshold, which is used to detect abnormal gait rhythm or emergency acceleration.

[0143] Preset an abnormal fluctuation threshold. If the variance fluctuation of the current window exceeds this preset threshold, it is directly determined as an abnormal gait state, such as falling or congestion, and a response with the highest priority is triggered. When the variance fluctuation of the current window is less than or equal to this preset threshold, and the status value of the device cooperation identifier is 1 and the variance fluctuation is less than the first threshold, it is determined as the device passing state, that is, the device is moving at a constant speed, such as a luggage cart being steadily pushed forward, and the door opening time needs to be extended. When the status value of the device cooperation identifier is 0 and the peak interval fluctuation is less than the second threshold, it is determined as the emergency passing state, that is, an emergency acceleration behavior, such as a passenger running, and the door needs to respond quickly.

[0144] Only some discriminant examples of the passing state categories are written in the embodiments of this application, and the discriminant situation of the passing state categories can be determined according to the actual situation.

[0145] Based on the same concept, the embodiments of this application provide a one-way door switch control system. The following will combine Figure 4 to elaborate in detail on the one-way door switch control system provided by the embodiments of this application.

[0146] Figure 4 is a structural block diagram of a one-way door switch control system shown in the embodiments of this application.

[0147] As Figure 4 shown, the one-way door switch control system may include:

[0148] An acquisition module 410, configured to acquire pressure distribution data and infrared radiation data of the one-way door passing area;

[0149] A determination module 420, configured to determine the passing type of the passing target based on the spatial distribution characteristics of the infrared radiation data, a preset temperature threshold, and the spatial distribution characteristics of the pressure distribution data. The passing types include human passing and human-cooperated device passing;

[0150] The determination module 420 is further configured to determine the gait feature information of the passing target according to the spatial temporal characteristics corresponding to the passing target in the pressure distribution data and a preset gait template;

[0151] The determination module 420 is further configured to determine the passing behavior information of the passing target according to the passing type of the passing target and the gait feature information of the passing target;

[0152] The determination module 420 is further configured to determine the pedestrian flow density information of the one-way door passage area according to the pressure distribution data, and determine the target switch control information corresponding to the passage behavior information and the pedestrian flow density information of the passage target according to the corresponding relationship between the preset pedestrian flow density information, the passage behavior information, and the switch control information;

[0153] The control module 430 is configured to control the opening and closing of the one-way door according to the target switch control information.

[0154] In one embodiment, the determination module 420 is specifically configured to extract the coordinates of the continuous temperature region higher than the preset temperature threshold in the infrared radiation data, and obtain the temperature region boundary, the centroid coordinates of the temperature region, and the temperature region coverage area through the region growing algorithm; calculate the coordinates of the pressure concentration region where the pressure value in the pressure distribution data exceeds the preset threshold, and obtain the pressure region boundary, the centroid coordinates of the pressure region, and the pressure region shape through the geometric envelope algorithm; perform spatial coordinate mapping based on the centroid coordinates of the temperature region and the centroid coordinates of the pressure region, and generate a coupling coefficient representing the correlation between the heat source and the pressure distribution by calculating the spatial overlap degree and the centroid offset; according to the temperature region coverage area and the pressure region shape, obtain the ratio of the heat source pressure distribution area through the temperature field gradient attenuation analysis and the pressure distribution form symmetry detection, and determine the collaborative determination value representing the degree of cooperation between the human body and the device according to the coupling coefficient; compare the collaborative determination value with the preset threshold range, and determine that the passage type of the passage target is human passage when the collaborative determination value is in the first threshold interval of the preset threshold range, and determine that the passage type of the passage target is human collaborative device passage when it is in the second threshold interval of the preset threshold range.

[0155] In one embodiment, the determination module 420 is specifically configured to project the centroid coordinates of the temperature region and the centroid coordinates of the pressure region onto a preset plane coordinate system to generate a centroid coordinate pair; calculate the ratio of the geometric intersection area to the union area based on the vertex distribution of the temperature region boundary and the pressure region boundary to generate a spatial overlap degree parameter; according to the centroid coordinate pair, calculate the distance vector between the centroid of the temperature region and the centroid of the pressure region, and weight the distance vector by the temperature region coverage area to obtain the centroid offset; determine the weights based on the energy concentration degree of the temperature region boundary and the pressure distribution symmetry degree of the pressure region shape, and perform weighted superposition of the spatial overlap degree parameter and the centroid offset to generate a coupling coefficient.

[0156] In one embodiment, the determination module 420 is specifically configured to perform multi-dimensional space encoding on the device collaboration identifier in the access type, the gait cycle, and the stride parameters in the gait feature information to generate a joint feature vector including the device collaboration identifier, the gait cycle sequence, and the stride sequence; based on the gait cycle sequence and the stride sequence in the joint feature vector, perform time series alignment processing with a preset gait template, calculate the phase offset of the gait cycle sequence and the difference index of the stride sequence, and generate a gait matching degree parameter; adjust the gait matching degree parameter according to the status value of the device collaboration identifier to obtain a target gait matching degree parameter; based on the target gait matching degree parameter, extract the matching degree fluctuation feature within a continuous time window, and obtain the access status category according to the status value of the device collaboration identifier and the matching degree fluctuation feature and a preset determination condition; match the access status category with a preset behavior level mapping table, and output the access behavior information characterizing the movement urgency, the gait stability level, and the device collaboration status.

[0157] In one embodiment, the determination module 420 is specifically configured to perform waveform feature point alignment on the gait cycle sequence and the reference cycle of the gait template to generate an aligned gait cycle sequence and stride sequence; extract the cycle fluctuation parameter from the aligned gait cycle sequence, perform piecewise difference calculation with the reference cycle of the gait template to generate a phase offset, and based on the aligned stride sequence, extract the stride dynamic range and the difference coefficient to generate a difference index; linearly superimpose the phase offset and the difference index according to a preset weight ratio to generate a gait matching degree parameter.

[0158] In one embodiment, the determination module 420 is specifically configured to perform sliding window interception on the target gait matching degree parameter according to the reference cycle length of the preset gait template to generate a segmented matching degree sequence; calculate the mean value, variance, and peak interval parameter in the segmented matching degree sequence to generate a statistical feature vector including mean value fluctuation, variance fluctuation, and peak interval fluctuation; determine the determination threshold range of the statistical feature vector according to the status value of the device collaboration identifier, and compare the statistical feature vector with the determination threshold range to obtain the access status category.

[0159] In one embodiment, the determining module 420 is specifically configured to, when the status value of the device collaboration identifier is 1, set the determination threshold for variance fluctuation in the statistical feature vector to a first threshold corresponding to the human body collaborative device passing scenario; when the status value of the device collaboration identifier is 0, set the determination threshold for peak interval fluctuation in the matching degree fluctuation feature to a second threshold corresponding to the human body passing scenario; compare the variance fluctuation with the first threshold, and when the variance fluctuation is greater than the preset abnormal fluctuation threshold, the passing status category is the gait abnormal status; when the variance fluctuation is less than or equal to the preset abnormal fluctuation threshold, when the status value of the device collaboration identifier is 1 and the variance fluctuation is less than the first threshold, the passing status category is the device passing status; when the variance fluctuation is less than or equal to the preset abnormal fluctuation threshold, when the status value of the device collaboration identifier is 0 and the peak interval fluctuation is less than the second threshold, the passing status category is the emergency passing status.

[0160] Figure 4 Each module in the system shown has the function of implementing Figures 1 to 3 each step in and can achieve its corresponding technical effects. For the sake of brevity, it will not be elaborated here.

[0161] Figure 5 FIG. shows a schematic hardware structure diagram of an electronic device provided by an embodiment of the present application.

[0162] The electronic device may include a processor 510 and a memory 520 storing computer program instructions.

[0163] Specifically, the above-mentioned processor 510 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0164] The memory 520 may include a mass storage for data or instructions. By way of example and not limitation, the memory 520 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disc, a magneto-optical disc, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In a suitable case, the memory 520 may include a removable or non-removable (or fixed) medium. In a suitable case, the memory 520 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 520 is a non-volatile solid-state memory.

[0165] The memory may include a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk storage media device, an optical storage media device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Thus, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to the first aspect of the present disclosure.

[0166] The processor 510 realizes any one of the one-way gate switch control methods in the above embodiments by reading and executing the computer program instructions stored in the memory 520.

[0167] In one example, the electronic device may further include a communication interface 530 and a bus 540. Among them, as Figure 5 shown, the processor 510, the memory 520, and the communication interface 530 are connected through the bus 540 and complete communication with each other.

[0168] The communication interface 530 is mainly used to implement communication between various modules, devices, units, and / or devices in the embodiments of the present application.

[0169] The bus 540 includes hardware, software, or both, and couples the components of the online data flow charging device to each other. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses or a combination of two or more of these. In a suitable case, the bus 540 may include one or more buses. Although the embodiments of the present application describe and illustrate a specific bus, the present application contemplates any suitable bus or interconnect.

[0170] The electronic device can execute the one-way gate switch control method in the embodiments of the present application, thereby implementing the one-way gate switch control method described in combination with Figures 1 to 3 description.

[0171] In addition, in combination with the one-way door switch control method in the above embodiments, the embodiments of the present application can provide a computer-readable storage medium to implement. Computer program instructions are stored on the computer-readable storage medium; when the computer program instructions are executed by a processor, any one of the one-way door switch control methods in the above embodiments is implemented.

[0172] It should be clear that the present application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, the detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present application.

[0173] The functional blocks shown in the above structure block diagrams can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, and so on. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted via a data signal carried in a carrier wave on a transmission medium or a communication link. "Machine-readable medium" can include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical discs, hard disks, fiber optic media, radio frequency (RF) links, and so on. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0174] It should also be noted that the exemplary embodiments mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above steps, that is, the steps can be executed in the order mentioned in the embodiments, or different from the order in the embodiments, or several steps can be executed simultaneously.

[0175] As described above with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems) and computer program products according to embodiments of the present application. It should be understood that each block in the flowchart and / or block diagram, and the combination of 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, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the functions / actions specified in one or more blocks of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general purpose processor, a special purpose processor, a special application processor, or a field programmable logic circuit. It should also be understood that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can also be implemented by dedicated hardware performing the specified functions or actions, or by a combination of dedicated hardware and computer instructions.

[0176] As described above, the above is only the specific implementation manner of the present application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein. It should be understood that the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present application.

Claims

1. A unidirectional door switch control method, characterized in that, Including: Obtain the pressure distribution data and infrared radiation data of the one-way door passage area; Based on the spatial distribution characteristics of the infrared radiation data, a preset temperature threshold, and the spatial distribution characteristics of the pressure distribution data, determine the passage type of the passage target, where the passage type includes human passage and human-coordinated device passage; According to the spatial temporal characteristics corresponding to the passage target in the pressure distribution data and a preset gait template, determine the gait characteristic information of the passage target; According to the passage type of the passage target and the gait characteristic information of the passage target, determine the passage behavior information of the passage target; Determine the crowd density information of the one-way door passage area according to the pressure distribution data, and according to the corresponding relationship between the preset crowd density information, passage behavior information, and switch control information, determine the target switch control information corresponding to the passage behavior information and the crowd density information of the passage target; Complete the control of the one-way door switch according to the target switch control information.

2. The method according to claim 1, wherein The determining the passage type of the passage target based on the spatial distribution characteristics of the infrared radiation data, a preset temperature threshold, and the spatial distribution characteristics of the pressure distribution data, where the passage type includes human passage and human-coordinated device passage, includes: Extract the coordinates of the continuous temperature region in the infrared radiation data that is higher than the preset temperature threshold, and through the region growing algorithm, obtain the temperature region boundary, the centroid coordinates of the temperature region, and the coverage area of the temperature region; Calculate the coordinates of the pressure concentration region in the pressure distribution data where the pressure value exceeds the preset threshold, and through the geometric envelope algorithm, obtain the pressure region boundary, the centroid coordinates of the pressure region, and the shape of the pressure region; Perform spatial coordinate mapping based on the centroid coordinates of the temperature region and the centroid coordinates of the pressure region, and generate a coupling coefficient representing the correlation between the heat source and the pressure distribution by calculating the spatial overlap degree and the centroid offset; According to the coverage area of the temperature region and the shape of the pressure region, through temperature field gradient decay analysis and pressure distribution form symmetry detection, obtain the ratio of the heat source pressure distribution area, and determine the collaborative determination value representing the degree of human-device collaboration according to the coupling coefficient; Compare the collaborative determination value with the preset threshold range. When the collaborative determination value is in the first threshold interval of the preset threshold range, determine that the passage type of the passage target is human passage, and when it is in the second threshold interval of the preset threshold range, determine that the passage type of the passage target is human-coordinated device passage.

3. The method according to claim 2, wherein The performing spatial coordinate mapping based on the centroid coordinates of the temperature region and the centroid coordinates of the pressure region, and generating a coupling coefficient representing the correlation between the heat source and the pressure distribution by calculating the spatial overlap degree and the centroid offset, includes: Project the centroid coordinates of the temperature region and the centroid coordinates of the pressure region onto a preset plane coordinate system to generate a centroid coordinate pair; Based on the vertex distribution of the temperature region boundary and the pressure region boundary, calculate the ratio of the geometric intersection area to the union area to generate a spatial overlap degree parameter; According to the centroid coordinate pair, calculate the distance vector between the centroid of the temperature region and the centroid of the pressure region, and weight the distance vector by the area covered by the temperature region to obtain the centroid offset; Determine the weight based on the energy concentration degree of the boundary of the temperature region and the pressure distribution symmetry degree of the shape of the pressure region, and perform weighted superposition of the spatial overlap degree parameter and the centroid offset to generate the coupling coefficient.

4. The method according to claim 1, characterized in that, The determining the passing behavior information of the passing target according to the passing type of the passing target and the gait feature information of the passing target includes: Perform multi-dimensional space coding on the device collaboration identifier in the passing type and the gait cycle and stride parameters in the gait feature information to generate a joint feature vector including the device collaboration identifier, the gait cycle sequence, and the stride sequence; Based on the gait cycle sequence and the stride sequence in the joint feature vector, perform time series alignment processing with a preset gait template, calculate the phase offset of the gait cycle sequence and the difference index of the stride sequence, and generate a gait matching degree parameter; Adjust the gait matching degree parameter according to the status value of the device collaboration identifier to obtain the target gait matching degree parameter; Based on the target gait matching degree parameter, extract the matching degree fluctuation feature within a continuous time window, and obtain the passing status category according to the status value of the device collaboration identifier and the matching degree fluctuation feature and a preset determination condition; Match the passing status category with a preset behavior level mapping table, and output the passing behavior information characterizing the movement urgency degree, the gait stability level, and the device collaboration status.

5. The method according to claim 4, wherein The performing, based on the gait cycle sequence and the stride sequence in the joint feature vector, time series alignment processing with a preset gait template, calculating the phase offset of the gait cycle sequence and the difference index of the stride sequence, and generating a gait matching degree parameter includes: Align the waveform feature points of the gait cycle sequence with the reference cycle of the gait template to generate the aligned gait cycle sequence and stride sequence; Extract the cycle fluctuation parameters from the aligned gait cycle sequence, perform segment-by-segment difference calculation with the reference cycle of the gait template to generate the phase offset, and based on the aligned stride sequence, extract the stride dynamic range and the difference coefficient to generate the difference index; Perform linear superposition of the phase offset and the difference index according to a preset weight ratio to generate the gait matching degree parameter.

6. The method according to claim 4, wherein The extracting, based on the target gait matching degree parameter, the matching degree fluctuation feature within a continuous time window, and obtaining the passing status category according to the status value of the device collaboration identifier and the matching degree fluctuation feature and a preset determination condition includes: Perform sliding window interception on the target gait matching degree parameter according to the reference cycle length of the preset gait template to generate a segmented matching degree sequence; Calculate the mean value, variance, and peak interval parameter in the segmented matching degree sequence to generate a statistical feature vector including mean value fluctuation, variance fluctuation, and peak interval fluctuation; Determine the determination threshold range of the statistical feature vector according to the status value of the device collaboration identifier, and compare the statistical feature vector with the determination threshold range to obtain the passage status category.

7. The method according to claim 6, characterized in that The step of determining the determination threshold range of the statistical feature vector according to the status value of the device collaboration identifier, and comparing the statistical feature vector with the determination threshold range to obtain the passage status category includes: When the status value of the device collaboration identifier is 1, set the determination threshold of the variance fluctuation in the statistical feature vector to the first threshold corresponding to the human body collaborative device passage scenario; When the status value of the device collaboration identifier is 0, set the determination threshold of the peak interval fluctuation in the matching degree fluctuation feature to the second threshold corresponding to the human body passage scenario; Compare the variance fluctuation with the first threshold. When the variance fluctuation is greater than the preset abnormal fluctuation threshold, the passage status category is the gait abnormal status; When the variance fluctuation is less than or equal to the preset abnormal fluctuation threshold, when the status value of the device collaboration identifier is 1 and the variance fluctuation is less than the first threshold, the passage status category is the device passage status; When the variance fluctuation is less than or equal to the preset abnormal fluctuation threshold, when the status value of the device collaboration identifier is 0 and the peak interval fluctuation is less than the second threshold, the passage status category is the emergency passage status.

8. A one-way door switch control system, characterized in that, The system includes: An acquisition module, configured to acquire pressure distribution data and infrared radiation data of a one-way door passage area; A determination module, configured to determine the passage type of the passage target based on the spatial distribution characteristics of the infrared radiation data, a preset temperature threshold, and the spatial distribution characteristics of the pressure distribution data, where the passage type includes human body passage and human body collaborative device passage; The determination module is further configured to determine the gait feature information of the passage target according to the spatial temporal characteristics corresponding to the passage target in the pressure distribution data and a preset gait template; The determination module is further configured to determine the passage behavior information of the passage target according to the passage type of the passage target and the gait feature information of the passage target; The determination module is further configured to determine the crowd density information of the one-way door passage area according to the pressure distribution data, and determine the target switch control information corresponding to the passage behavior information and the crowd density information of the passage target according to the corresponding relationship between the preset crowd density information, passage behavior information, and switch control information; A control module, configured to control the opening and closing of the one-way door according to the target switch control information.

9. An electronic device, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the one-way door switch control method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, Computer program instructions are stored on a computer-readable storage medium, and when the computer program instructions are executed by a processor, they implement the one-way door switch control method according to any one of claims 1-7.

Images