Non-bird false touch gating dynamic protection method based on temperature difference and displacement dual-threshold fusion

Abstract

The invention relates to the field of gating dynamic protection. A non-bird false touch gating dynamic protection method based on temperature difference and displacement double threshold fusion comprises the steps that real-time monitoring data of a gating area are acquired, and the real-time monitoring data comprise temperature difference characteristic parameters, displacement characteristic parameters, infrared shielding parameters and visual image parameters; obtaining a temperature difference discriminant value according to the temperature difference characteristic parameters; acquiring a displacement discriminant value according to the displacement characteristic parameter; obtaining an infrared discrimination value according to the infrared shielding parameter; obtaining a visual discrimination value according to the visual image parameter; obtaining a comprehensive discrimination index according to the temperature difference discrimination value, the displacement discrimination value, the infrared discrimination value and the visual discrimination value; and judging whether the comprehensive judgment index exceeds a preset dual-threshold decision interval or not. According to the method, through collaborative analysis of multi-dimensional data such as temperature difference, displacement, infrared shielding and visual images, biological contact and non-biological contact are effectively distinguished, and the detection accuracy in a complex scene is improved.

Description

Technical Field

[0001] The present application relates to the field of gated dynamic protection, and in particular to a method for gated dynamic protection against non-bird false touches based on dual-threshold fusion of temperature difference and displacement. Background Art

[0002] As a typical application of Internet of Things technology in the security field, the smart access control system has been widely penetrated into various scenarios such as residential, commercial, and industrial.

[0003] Among the related technologies, existing technologies rely on infrared tubes or matrices to detect occlusions, but are unable to distinguish between biological and non-biological occlusions (such as instantaneous occlusions by fallen leaves and dust can easily trigger false alarms). In addition, in strong light environments (such as summer noon), infrared sensors are easily interfered with, leading to missed detections or misjudgments. At the same time, there is a lack of multi-dimensional data fusion, and decisions are made only based on a single indicator of occlusion area or duration, which cannot rule out non-biological false contact scenarios such as birds briefly flying by or debris accumulation. Summary of the Invention

[0004] This application provides a dynamic protection method for non-bird accidental touch gates based on the fusion of dual thresholds of temperature difference and displacement to solve the problem that related technologies lack multi-dimensional data fusion and only make decisions based on a single indicator of occlusion area or duration, which cannot rule out non-biological accidental touch scenarios such as birds flying briefly or debris accumulation.

[0005] In a first aspect, the present application provides a non-bird false touch gate dynamic protection method based on temperature difference and displacement dual threshold fusion, the method comprising: Acquiring real-time monitoring data of the gated area, wherein the real-time monitoring data includes temperature difference characteristic parameters, displacement characteristic parameters, infrared shielding parameters, and visual image parameters; Obtaining a temperature difference discrimination value according to the temperature difference characteristic parameter; Obtaining a displacement discrimination value according to the displacement characteristic parameter; Obtaining an infrared discrimination value according to the infrared blocking parameter; Obtaining a visual discrimination value according to the visual image parameter; Obtaining a comprehensive discrimination index according to the temperature difference discrimination value, displacement discrimination value, infrared discrimination value and visual discrimination value; Determining whether the comprehensive discrimination index exceeds a preset dual-threshold decision interval; If the comprehensive discrimination index exceeds the preset dual-threshold decision interval, it is determined to be a non-bird accidental touch and a graded protection response is triggered; If the comprehensive discrimination index does not exceed the preset dual-threshold decision interval, it is determined to be a normal state and the original state of the gate is maintained.

[0006] Optionally, the step of obtaining a temperature difference discrimination value according to the temperature difference characteristic parameter includes: Obtaining a real-time temperature difference sequence and an ambient reference temperature in the temperature difference characteristic parameters; Acquire multiple temperature difference values at adjacent moments according to the real-time temperature difference sequence, and generate a temperature difference change rate sequence according to the multiple temperature difference values at adjacent moments; Obtaining the absolute value of the temperature difference and the duration of the temperature difference according to the temperature difference change rate sequence and the ambient reference temperature; Obtaining a temperature difference-duration change rate according to the absolute value of the temperature difference and the duration of the temperature difference; The temperature difference-duration change rate is mapped to a preset interval to obtain a temperature difference judgment value.

[0007] Optionally, the step of obtaining a displacement discrimination value according to the displacement characteristic parameter includes: Acquire multiple three-dimensional displacement coordinates and time stamp sequences according to the displacement characteristic parameters; Obtaining displacement vector differences at adjacent moments according to a plurality of three-dimensional displacement coordinates and a time stamp sequence, and obtaining a displacement velocity according to the displacement vector differences at adjacent moments; Obtaining a displacement distance according to the displacement speed; Acquire a displacement trajectory curve graph according to the displacement distance and timestamp sequence; Obtaining a motion trajectory curvature according to the displacement trajectory curve graph; A displacement discrimination value is obtained according to the displacement speed, displacement distance and motion trajectory curvature.

[0008] Optionally, the step of obtaining an infrared discrimination value according to the infrared blocking parameter includes: Acquire multiple shading areas according to the infrared shading parameters; Obtaining a total number of occluded pixels at multiple moments according to the occluded area, and obtaining an area of the occluded area according to the total number of occluded pixels; Obtaining a pixel area ratio of the occluded area according to the occluded area; Obtaining the occlusion duration according to the pixel area ratio of the occlusion region; Acquire a region direction change sequence according to the occlusion duration and the pixel area ratio of the occlusion region; An infrared discrimination value is obtained according to the region direction change sequence.

[0009] Optionally, the step of obtaining a visual discrimination value according to the visual image parameter includes: Obtaining target bounding box coordinates and category image information according to the visual image parameters; Obtaining a target aspect ratio according to the target bounding box coordinates; Obtaining the bottom coordinates of the bounding box according to the target bounding box coordinates; Obtaining the center of gravity height according to the bottom coordinates of the bounding box and the target aspect ratio; Obtaining category similarity from a preset library based on the category image information; A visual discrimination value is obtained according to the target aspect ratio, center of gravity height and category similarity.

[0010] Optionally, the step of obtaining a comprehensive discrimination index according to the temperature difference discrimination value, the displacement discrimination value, the infrared discrimination value and the visual discrimination value includes: Obtaining a first weight coefficient according to the temperature difference discrimination value; Obtaining a second weight coefficient according to the displacement discrimination value; Obtaining a third weight coefficient according to the infrared discrimination value; Obtaining a fourth weight coefficient according to the visual discrimination value; Obtain environmental compensation coefficient; A comprehensive discrimination index is obtained according to the temperature difference discrimination value, the displacement discrimination value, the infrared discrimination value, the visual discrimination value, the first weight coefficient, the second weight coefficient, the third weight coefficient, the fourth weight coefficient and the environmental compensation coefficient.

[0011] In a second aspect, the present application provides a non-bird accidental touch gate dynamic protection system based on the fusion of temperature difference and displacement dual thresholds, including: A data acquisition module is used to obtain real-time monitoring data of the gated area, wherein the real-time monitoring data includes temperature difference characteristic parameters, displacement characteristic parameters, infrared shielding parameters and visual image parameters; A temperature difference analysis module, configured to obtain a temperature difference discrimination value based on the temperature difference characteristic parameters; A displacement analysis module, configured to obtain a displacement discrimination value based on the displacement characteristic parameters; An infrared analysis module, configured to obtain an infrared discrimination value based on the infrared blocking parameter; A visual analysis module, configured to obtain a visual discrimination value based on the visual image parameters; A fusion decision module is used to obtain a comprehensive discrimination index based on the temperature difference discrimination value, the displacement discrimination value, the infrared discrimination value and the visual discrimination value; A decision module, configured to determine whether the comprehensive discrimination index exceeds a preset dual-threshold decision interval; If the comprehensive discrimination index exceeds the preset dual-threshold decision interval, it is determined to be a non-bird accidental touch and a graded protection response is triggered; If the comprehensive discrimination index does not exceed the preset dual-threshold decision interval, it is determined to be a normal state and the original state of the gate is maintained.

[0012] Optionally, the temperature difference analysis module includes: A temperature difference sequence acquisition unit is used to acquire the real-time temperature difference sequence and the ambient reference temperature in the temperature difference characteristic parameter; a change rate generating unit, configured to obtain a plurality of temperature difference values at adjacent moments according to the real-time temperature difference sequence, and generate a temperature difference change rate sequence according to the plurality of temperature difference values at adjacent moments; a temperature difference parameter calculation unit, configured to obtain an absolute value of the temperature difference and a duration of the temperature difference according to the temperature difference change rate sequence and the ambient reference temperature; a temperature difference-duration change rate calculation unit, configured to obtain the temperature difference-duration change rate based on the absolute value of the temperature difference and the duration of the temperature difference; The mapping unit is used to map the temperature difference-duration change rate to a preset interval to obtain a temperature difference judgment value.

[0013] Optionally, the displacement analysis module includes: A coordinate sequence acquisition unit, configured to acquire a plurality of three-dimensional displacement coordinates and time stamp sequences according to the displacement characteristic parameters; a velocity calculation unit, configured to obtain displacement vector differences between adjacent moments according to a plurality of three-dimensional displacement coordinates and a timestamp sequence, and obtain a displacement velocity according to the displacement vector differences between adjacent moments; a distance calculation unit, configured to obtain a displacement distance according to the displacement speed; A trajectory fitting unit, configured to obtain a displacement trajectory curve graph according to the displacement distance and timestamp sequence; a curvature calculation unit, configured to obtain a motion trajectory curvature according to the displacement trajectory curve graph; The displacement discrimination value generating unit is used to obtain the displacement discrimination value according to the displacement speed, displacement distance and motion trajectory curvature.

[0014] Optionally, the infrared analysis module includes: an occlusion area recognition unit, configured to obtain a plurality of occlusion areas according to the infrared occlusion parameters; a pixel statistics unit, configured to obtain a total number of occluded pixels at a plurality of moments according to the occluded area, and obtain an area of the occluded area according to the total number of occluded pixels; an area ratio calculation unit, configured to obtain a pixel area ratio of the occluded area according to the area of the occluded area; A duration calculation unit, configured to obtain an occlusion duration according to a pixel area ratio of the occlusion region; A direction change analysis unit, configured to obtain a region direction change sequence according to the occlusion duration and the pixel area ratio of the occlusion region; The infrared discrimination value generating unit is configured to obtain an infrared discrimination value according to the region direction change sequence.

[0015] Compared with related technologies, the non-bird false touch gate dynamic protection method based on temperature difference and displacement dual threshold fusion provided by this application has at least the following technical effects: Through the collaborative analysis of multi-dimensional data such as temperature difference, displacement, infrared occlusion, and visual images, it can effectively distinguish between living and non-living contacts and improve detection accuracy in complex scenarios; introduce an environmental adaptive mechanism to dynamically adjust the weight coefficient and compensation factor according to real-time temperature, humidity, light and other parameters to enhance the stability of the system in extreme environments; based on the bird-specific exclusion algorithm of target morphological characteristics and movement patterns, it reduces interference from natural factors and lowers the false alarm rate; through a graded response strategy, it realizes multi-level protection from warning to locking, balancing safety and traffic efficiency.

[0016] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 This is a flow chart of a non-bird false touch gated dynamic protection method based on temperature difference and displacement dual threshold fusion according to an exemplary embodiment; Figure 2 It is a system diagram showing a non-bird false touch gated dynamic protection method based on the fusion of temperature difference and displacement dual thresholds according to an exemplary embodiment. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is described and illustrated below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely used to explain this application and are not intended to limit this application. Based on the embodiments provided in this application, all other embodiments obtained by those of ordinary skill in the art without making any creative efforts are within the scope of protection of this application.

[0019] Obviously, the drawings described below are merely examples or embodiments of the present application. Those skilled in the art can, without inventive effort, apply the present application to other similar scenarios based on these drawings. Furthermore, it is also understood that, although the effort involved in such a development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, changes in design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as an insufficiency of the content disclosed in this application.

[0020] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments unless there is a conflict.

[0021] Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by persons of ordinary skill in the art to which this application belongs. The terms "a," "an," "an," "the," and similar expressions used herein do not denote quantitative limitations and may refer to either the singular or the plural. The terms "comprise," "include," "have," and any variations thereof, used herein, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or modules (units) is not limited to the listed steps or units but may also include steps or units not listed, or may include other steps or units inherent to the process, method, product, or apparatus. The terms "connected," "connected," "coupled," and similar expressions used herein are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. As used herein, "plurality" means two or more. "And / or" describes an association between associated objects, indicating that three possible relationships exist. For example, "A and / or B" may mean: A exists alone; A and B exist simultaneously; or B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific order for the objects.

[0022] Example 1 The embodiment of the present invention provides a dynamic protection method for non-bird false touch gate control based on the fusion of temperature difference and displacement dual thresholds. Figure 1 FIG. 1 is a flow chart of a method according to an exemplary embodiment. Figure 1 As shown, the method includes: Step S101: acquiring real-time monitoring data of a gated area, wherein the real-time monitoring data includes temperature difference characteristic parameters, displacement characteristic parameters, infrared shielding parameters, and visual image parameters; Step S102: obtaining a temperature difference discrimination value according to the temperature difference characteristic parameter; Step S103: obtaining a displacement discrimination value according to the displacement characteristic parameter; Step S104: obtaining an infrared discrimination value according to the infrared blocking parameter; Step S105: obtaining a visual discrimination value according to the visual image parameters; Step S106: obtaining a comprehensive discrimination index according to the temperature difference discrimination value, the displacement discrimination value, the infrared discrimination value, and the visual discrimination value; Step S107: determining whether the comprehensive discrimination index exceeds a preset dual-threshold decision interval; If the comprehensive discrimination index exceeds the preset dual-threshold decision interval, it is determined to be a non-bird accidental touch and a graded protection response is triggered; If the comprehensive discrimination index does not exceed the preset dual-threshold decision interval, it is determined to be a normal state and the original state of the gate is maintained.

[0023] In summary, the embodiment of the present invention provides a dynamic protection method for non-bird accidental touch gate control based on the fusion of temperature difference and displacement dual thresholds. The pyroelectric sensors, MEMS accelerometers, 16×16 infrared matrices, low-light cameras and other devices deployed around the door body synchronously collect temperature difference characteristic parameters (including real-time temperature difference sequence, ambient reference temperature), displacement characteristic parameters (including three-dimensional displacement coordinates, timestamp sequence), infrared occlusion parameters (including occlusion area, total number of occlusion pixels), visual image parameters (including target bounding box coordinates, category image information) and other real-time monitoring data of the gated area. The data of each dimension is then deeply processed: the temperature difference difference at adjacent moments is calculated from the temperature difference characteristic parameters to generate a temperature difference change rate sequence, the absolute value and duration of the temperature difference are obtained by combining the ambient reference temperature, and the temperature difference-duration change rate is mapped to the preset interval to obtain the temperature difference discrimination value; the displacement vector difference at adjacent moments is calculated from the displacement characteristic parameters to obtain the displacement velocity, the displacement distance is obtained by integration, and the curvature is calculated by fitting the displacement trajectory curve. The three are combined and weighted to obtain Displacement discrimination value; the total number of obscured pixels is counted from the infrared obscuration parameters to obtain the area percentage, the entropy of the obscuration duration and regional directional change sequence is calculated, and the infrared discrimination value is calculated using a formula; the target aspect ratio and center of gravity height are obtained from the visual image parameters, and the category similarity is obtained by comparison with the preset library. The visual discrimination value is calculated based on whether it meets the bird characteristic interval. Each discrimination value is then combined with the first to fourth weight coefficients and environmental compensation coefficient determined based on the temperature difference, displacement, infrared, and visual discrimination values, respectively, to calculate a comprehensive discrimination index using a weighted fusion formula. For example, this index is compared with the preset dual-threshold decision interval consisting of a primary threshold T1=0.6 and a secondary threshold T2=0.8. If the comprehensive discrimination index exceeds T2 and the target category similarity excludes birds, it is determined to be a non-bird false touch and triggers a graded protection response such as electronic lock locking and cloud alarm. If it does not exceed T1 and the target category similarity matches birds, it is determined to be normal and the original gate state is maintained. If it is between T1 and T2, a primary response such as an audible and visual alarm is triggered. This solution constructs a complete logical chain covering data collection, feature acquisition, risk assessment, and hierarchical decision-making through the spatiotemporal alignment and feature-level fusion of multimodal sensor data, adaptive adjustment of dynamic thresholds with parameters such as ambient temperature and door age, and a bird exclusion mechanism based on target morphological characteristics and behavioral patterns. It effectively solves problems such as weak anti-interference ability of a single sensor, poor environmental adaptability of fixed thresholds, and high misjudgment rate of birds and non-bird targets. The final dynamic protection method for non-bird false touch gates takes into account the impact of complex environments and door characteristics, and optimizes the effect of non-bird false touch detection.

[0024] In one embodiment, step S102 specifically includes: Step S1021: obtaining a real-time temperature difference sequence and an ambient reference temperature in the temperature difference characteristic parameters; Step S1022: acquiring a plurality of temperature difference values at adjacent moments according to the real-time temperature difference sequence, and generating a temperature difference change rate sequence according to the plurality of temperature difference values at adjacent moments; Step S1023: Obtain the absolute value of the temperature difference and the duration of the temperature difference according to the temperature difference change rate sequence and the ambient reference temperature; Step S1024: obtaining a temperature difference-duration change rate according to the absolute value of the temperature difference and the duration of the temperature difference; Step S1025: Map the temperature difference-duration change rate to a preset interval to obtain a temperature difference judgment value.

[0025] In step S1021 of the present invention, the "real-time temperature difference sequence" is derived from real-time, continuous temperature sampling by a pyroelectric sensor within the gated area. This sensor continuously acquires the temperature of the surrounding environment and objects at a fixed frequency, forming a chronological temperature data sequence that dynamically reflects temperature changes within the gated area. The "ambient reference temperature" is obtained by statistically analyzing the historical data of the real-time temperature difference sequence, taking the average temperature value over a period of time. This serves as a reference value for determining whether the current temperature is abnormal. This serves as a stable comparison baseline for temperature difference analysis. The system typically updates the ambient reference temperature periodically (e.g., hourly) to adapt to environmental changes. These two systems work together to initially identify the nature of temperature fluctuations by comparing the real-time temperature with the reference temperature.

[0026] In step S1022, the "adjacent temperature difference" sequence processes the real-time temperature difference sequence moment by moment, calculating the absolute difference between the current temperature value and the previous temperature value. This difference reflects the magnitude of temperature change per unit time. By taking the absolute value, the influence of temperature fluctuation direction is eliminated, focusing on the analysis of the rate of change. The "temperature difference rate of change sequence" is a sequence formed by arranging the temperature difference values of multiple adjacent moments in chronological order, which is used to illustrate the evolution of the temperature change rate over time. The calculation process is to traverse the real-time temperature difference sequence, calculate the absolute temperature difference between two adjacent time points, and store it in the sequence. The purpose of this sequence is to distinguish rapid temperature fluctuations (such as changes in body temperature radiation caused by rapid movement of an organism) from slow temperature fluctuations (such as natural temperature rise or fall in the environment) by analyzing the speed of temperature change, providing a basis for the speed dimension for subsequent judgment.

[0027] In step S1023, the "absolute value of temperature difference" is the absolute value of the difference between the real-time temperature value and the ambient reference temperature value. It measures the degree to which the current temperature deviates from the normal reference temperature; a larger absolute value indicates a more significant temperature anomaly. The "duration of temperature difference" refers to the continuous duration that the absolute value of the temperature difference exceeds a preset threshold (such as 0.5°C, set by the system). This is used to determine whether the temperature anomaly is a brief, momentary disturbance or a persistent, stable change. During calculation, the system monitors the absolute value of the temperature difference in real time. When it exceeds the preset threshold, a timing function is initiated, and the timing is stopped until the absolute value of the temperature difference falls below the threshold, thereby determining the duration. The combined effect of these two functions effectively filters out transient temperature disturbances caused by gusts of wind and brief changes in light intensity, while focusing on persistent temperature anomalies caused by sustained contact or presence of an organism.

[0028] In step S1024, the "temperature difference-duration change rate" is a composite indicator derived by arithmetically multiplying the absolute value of the temperature difference by the duration of the temperature difference. This indicator integrates two key factors: the degree of temperature deviation from the baseline and the duration of the anomaly. It aims to comprehensively assess the contribution of temperature anomalies to the risk of false touches. Its calculation logic is as follows: a larger absolute value of the temperature difference indicates a more significant temperature anomaly; a longer duration indicates a more stable abnormal state. The product of the two more comprehensively reflects the potential for false touches. A larger value generally indicates a higher probability of non-bird objects or organisms contacting the door. This indicator serves as an important intermediate parameter connecting single-dimensional temperature analysis with comprehensive risk assessment.

[0029] In step S1025, the "preset interval" is a numerical range pre-set by the system to measure the risk level of false touches corresponding to the temperature difference-duration change rate. This range is typically [0, 1], facilitating unified calculations with discriminant values from other dimensions. The "mapping" process linearly converts the actual range of the temperature difference-duration change rate to the preset interval through mathematical methods such as normalization, yielding the temperature difference discriminant value. During the calculation, the system determines the minimum and maximum values of the temperature difference-duration change rate based on historical data statistics (e.g., the minimum value is 0 under normal conditions, and the maximum value is a specific value under typical false touch scenarios). The system then calculates the corresponding ratio using the formula (temperature difference-duration change rate - minimum value) ÷ (maximum value - minimum value), resulting in a temperature difference discriminant value within the preset interval. This discriminant value converts temperature-related physical quantities into a uniformly dimensional risk probability value, facilitating subsequent weighted fusion with discriminant values from other dimensions, such as displacement, infrared, and visual, to form a comprehensive discriminant index, providing a standardized temperature dimension basis for the final false touch determination.

[0030] Continue to refer to Figure 1 , after step S102, step S103 is performed, specifically as follows: Step S1031: Acquire multiple three-dimensional displacement coordinates and time stamp sequences according to the displacement characteristic parameters; Step S1032: obtaining displacement vector differences at adjacent moments according to the plurality of three-dimensional displacement coordinates and the timestamp sequence, and obtaining displacement velocity according to the displacement vector differences at adjacent moments; Step S1033: obtaining a displacement distance according to the displacement speed; Step S1034: obtaining a displacement trajectory curve graph according to the displacement distance and timestamp sequence; Step S1035: obtaining the motion trajectory curvature according to the displacement trajectory curve graph; Step S1036: Obtain a displacement discrimination value according to the displacement speed, displacement distance, and motion trajectory curvature.

[0031] In step S1031, the "multiple three-dimensional displacement coordinates" are collected collaboratively by a MEMS accelerometer and a laser displacement meter deployed on the door. The MEMS accelerometer infers displacement by sensing changes in acceleration, while the laser displacement meter directly acquires distance data through laser ranging. The two are combined to generate the object's position coordinates in the X, Y, and Z axes. Each coordinate is associated with a precise "timestamp" to mark the moment of acquisition, with millisecond-level accuracy, ensuring the temporal sequence of the displacement data. This data is used to construct the spatiotemporal trajectory of the object within the gated area, providing raw data support for subsequent motion feature analysis. The system continuously collects and stores coordinates and timestamps at a fixed frequency (e.g., 50 Hz), forming a continuous displacement-time dataset.

[0032] In step S1032, the “adjacent time displacement vector difference” is calculated by performing vector subtraction on the three-dimensional displacement coordinates corresponding to adjacent time stamps, that is, calculating the coordinate difference in the X, Y, and Z axis directions respectively ( , ), the displacement vector change from the previous moment to the current moment is obtained; the "displacement speed" is the modulus of the vector difference divided by the time interval, and the calculation formula is , where Δt is the time interval between adjacent timestamps. This process converts spatial displacement into a velocity indicator, which can be used to measure the speed and direction of an object's movement. For example, a high-frequency, small-amplitude vector difference might correspond to the rapid micro-movement of a bird's wingbeat, while a low-frequency, large-amplitude vector difference might correspond to the movement of a human or pet.

[0033] In step S1033, the “displacement distance” is obtained by time-integrating the displacement velocity, i.e., the cumulative value of the product of the velocity and the time interval from the initial moment to the current moment ( This metric reflects the total path length of an object within the gated area. It helps determine the duration and scale of movement: short-distance movement may be caused by accidental contact or small animal activity, while long-distance movement is more likely to indicate normal traffic or the movement of a large object. The system dynamically accumulates velocity increments within each time interval, updating the displacement distance in real time to form a cumulative value that grows over time.

[0034] In step S1034, the "Displacement Trajectory Graph" uses the timestamp as the horizontal axis and the displacement distance as the vertical axis. Interpolation algorithms (such as cubic spline interpolation) are used to continuously fit the discrete displacement distance data to generate a smooth curve. This graph visually displays the trend of an object's movement distance over time, facilitating analysis of trajectory morphology. For example, a bird's flight may exhibit an irregular, fluctuating curve, while a person walking or an object impacting a door may exhibit a smooth, straight line or low-frequency fluctuation. By visualizing trajectory morphology, the system can further understand the trajectory's geometric characteristics.

[0035] In step S1035, the “curvature of the motion trajectory” is calculated using differential geometry methods. Specifically, the second-order derivative of the displacement trajectory curve is obtained to obtain the acceleration, and the curvature of the curve is calculated by combining the first-order derivative (speed). The formula is: , where K represents the curvature of the trajectory, S represents the displacement distance, and d represents the displacement velocity. A larger curvature value indicates a more curved trajectory, while a smaller curvature value indicates a closer-to-a-straight trajectory. Its significance lies in distinguishing the behavioral patterns of different moving entities: birds, due to their high maneuverability, typically have higher trajectory curvature; humans, pets, or objects have relatively lower trajectory curvature, especially when moving in a straight line, where the curvature approaches zero. This metric provides a morphological basis for determining whether a movement is initiated by a non-avian organism.

[0036] In step S1036, the “displacement discrimination value” is obtained by weighted fusion of displacement speed, displacement distance, and motion trajectory curvature, and the calculation formula is e= ,in, is a weighting factor, set based on the contribution of each indicator to the risk of accidental contact (e.g., speed has a higher weight for sensitivity to rapid movement, while curvature has a lower weight for distinguishing movement patterns). This process transforms multi-dimensional displacement characteristics into a unified risk quantification metric: faster speed, longer distance, and lower curvature (closer to a straight line) indicate a higher displacement discrimination value, indicating a greater risk of non-bird accidental contact. Conversely, slower speed, shorter distance, and higher curvature indicate a lower risk of accidental contact involving a bird or natural disturbance. The system calculates the weighted sum of the three indicators in real time to generate a dynamic displacement discrimination value, providing key displacement dimension parameters for comprehensive decision-making.

[0037] Continue to refer to Figure 1 , after step S103, step S104 is performed, specifically as follows: Step S1041: Acquire multiple shielding areas according to the infrared shielding parameters; Step S1042: obtaining the total number of occluded pixels at multiple moments according to the occluded area, and obtaining the area of the occluded area according to the total number of occluded pixels; Step S1043: Obtaining the pixel area ratio of the occluded area according to the area of the occluded area; Step S1044: Obtain the occlusion duration according to the pixel area ratio of the occlusion region; Step S1045: obtaining a region direction change sequence according to the occlusion duration and the pixel area ratio of the occlusion region; Step S1046: Obtain an infrared discrimination value according to the region direction change sequence.

[0038] In step S1041, the "infrared obstruction parameter" is derived from the 16×16 infrared matrix sensor installed in the door. This sensor uses independent detection units distributed in a grid pattern to sense obstructions within the gated area in real time. Each unit outputs a binary signal (1 for obstruction, 0 for unobstructed). The "multiple obstruction regions" are clusters of continuous obstruction units identified by performing connected region analysis on the binary matrix output by the sensor using an image processing algorithm. These clusters are used to determine the specific spatial location and range of the obstruction. Their significance lies in converting the obstruction status of the infrared signal into analyzable spatial distribution data, providing a foundation for subsequent quantitative analysis. The calculation process involves the sensor scanning at a fixed period to generate a binary matrix. The system then uses algorithms such as contour detection and connected domain labeling to identify independent obstruction regions.

[0039] In step S1042, the "total number of occluded pixels" is the result of counting the number of occluded sensor cells within each occlusion region. This is calculated by traversing all cells within the region and summing the number of pixels set to 1. The "occluded region area" is represented by this statistical value and is used to quantify the spatial coverage of the occlusion event. This helps distinguish between minor occlusions (such as insects flying by) and major occlusions (such as contact with an organism's body). The calculation process involves performing a summation operation on the binary matrix of each occlusion region. The value directly reflects the physical extent of the occlusion. For example, if an occlusion region contains several consecutive cells, the total number of pixels is the quantified area of the region.

[0040] In step S1043, the "occluded area pixel ratio" is calculated by dividing the total number of occluded pixels by the total number of pixels in the infrared matrix (16 × 16 = 256). This ratio, ranging from 0 to 1, is used to convert occluded areas of varying sizes into a standardized metric with a unified dimension, eliminating the influence of sensor grid resolution and facilitating cross-temporal and cross-scene comparisons of occlusion intensity. The calculation is a simple division operation. For example, when the total number of occluded pixels is a certain value, the ratio is calculated by dividing by 256. This metric intuitively reflects the relative size of the occluded area within the entire monitoring range.

[0041] In step S1044, the "Occlusion Duration" function is calculated by monitoring the pixel area ratio curve of the obscured area in real time. When this ratio continuously exceeds a preset threshold (such as the system's minimum effective occlusion ratio), a timer function is activated and the time difference between the first time it exceeds the threshold and the first time it falls below the threshold is recorded. This function is used to distinguish between momentary occlusion (such as a falling leaf) and persistent occlusion (such as an object leaning against a door). This function is used to screen out occlusion events that pose a real risk over time. The calculation process dynamically tracks changes in the area ratio, starting and stopping the timer when the value continuously meets the conditions, thus forming a record of the duration of effective occlusion.

[0042] In step S1045, the "region direction change sequence" determines the direction of movement of the occluded region by calculating the change in its center of mass coordinates at consecutive moments. The center of mass coordinates are calculated using a weighted average method (e.g., the coordinates of each occluded cell are multiplied by its state value, the sum is then divided by the total number of occluded pixels). The vector difference between the center of mass at adjacent moments is used to determine the direction (e.g., Δx > 0 indicates rightward movement, Δy > 0 indicates upward movement), forming a chronological direction sequence (e.g., "leftward movement - stationary - rightward movement"). Its significance lies in capturing the motion patterns of occluded objects. Bird flight often involves high-frequency directional changes, while non-bird accidental touches (e.g., pets scratching at doors) are often unidirectional or low-frequency reciprocating motions. The calculation process involves dynamic updating of the center of mass coordinates and categorizing the directions.

[0043] In step S1046, the "infrared discrimination value" is obtained by fusing the area ratio of the occlusion area, the occlusion duration and the Shannon entropy of the direction change sequence. First, the probability distribution of the direction sequence is calculated. , and then through the Shannon entropy formula Measures the uncertainty of direction changes (the larger the entropy value, the more random the direction, where H represents the corrected entropy value, The final discriminant value is calculated using the formula "area ratio × duration × (1-entropy / ln4)", where (1-entropy / ln4) is used to suppress the influence of random movement (such as birds). Its function is to integrate spatial coverage, temporal continuity, and regularity of movement patterns into a single risk indicator. Higher values indicate a greater likelihood of non-bird accidental contact. The calculation process involves the nonlinear combination of multi-dimensional data, achieving a hierarchical transformation from raw signals to risk discrimination.

[0044] Continue to refer to Figure 1 , after step S104, step S105 is performed, specifically as follows: Step S1051: obtaining target bounding box coordinates and category image information according to the visual image parameters; Step S1052: Obtain a target aspect ratio according to the target bounding box coordinates; Step S1053: Obtain the bottom coordinates of the bounding box according to the target bounding box coordinates; Step S1054: Obtain the center of gravity height according to the bottom coordinates of the bounding box and the target aspect ratio; Step S1055: obtaining category similarity from a preset library according to the category image information; Step S1056: Obtain a visual discrimination value according to the target aspect ratio, center of gravity height, and category similarity.

[0045] In step S1051, the "visual image parameters" are collected in real time by a low-light camera installed in the gate. This device can obtain RGB images and depth data of the gated area under 0.01 lux lighting conditions. The "target bounding box coordinates" are generated by inferring the image using the YOLOv5s lightweight object detection model. The model outputs the target's position coordinates in the image (e.g., upper left corner (x1, y1), lower right corner (x2, y2)). The "category image information" is the model-predicted target category label (e.g., "bird," "pet," "human") and the corresponding feature vector (including multidimensional visual features such as color, texture, and outline). Its function is to convert visual information into quantifiable spatial position and category probability data. The calculation process involves the camera continuously capturing image frames, the model analyzing and identifying each frame, and outputting the bounding box coordinates and category confidence (e.g., a confidence score of 0.8 for "bird" indicates an 80% probability of being a bird).

[0046] In step S1052, the “target aspect ratio” is calculated using the target bounding box coordinates using the formula: the ratio of the bounding box width to its height ( ), a metric used to describe the two-dimensional morphological characteristics of a target. Birds, due to their ellipsoidal shape, typically have an aspect ratio between 0.8 and 1.2. Non-avian targets (such as the rectangular silhouette of a standing human or the vertically elongated bodies of pets) often have aspect ratios greater than 1.5 or less than 0.8. This ratio is calculated by directly dividing the difference in bounding box coordinates to produce a dimensionless ratio. A value closer to 1 indicates a more avian-like morphology, while a lower value indicates a more non-avian morphological characteristic.

[0047] In step S1053, the "bounding box bottom coordinate" is the lowest row coordinate (y2) of the target bounding box in the image. This value must be physically calibrated based on the camera's installation height and viewing angle (e.g., by pre-measuring and mapping image pixels to actual distances) to convert pixel coordinates into actual physical heights. For example, if the camera is installed at a height of 2.5 meters and has a vertical viewing angle of 60 degrees, the ground height corresponding to the bottom pixel of the image can be calculated. A larger y2 bounding box bottom coordinate indicates a lower target height (e.g., a y2 closer to the bottom of the image indicates a target closer to the ground). This value is used to determine the target's vertical position. Birds typically move below 0.6 meters, while non-bird targets (such as standing people) often have a center of gravity above 0.8 meters.

[0048] In step S1054, the "center of gravity height" is estimated based on the bottom coordinates of the bounding box and the aspect ratio of the target. Assuming that the center of gravity of the target is located in the middle and lower part of the bounding box in the vertical direction (such as 1 / 3 of the height above the bottom), the calculation formula is center of gravity height = is the bounding box height. This estimation method is based on the distribution of the center of gravity of common targets (for example, birds have a lower center of gravity, while humans have a center of gravity approximately in the middle of the torso). The image coordinates of the center of gravity are calculated by scaling the bounding box height. This is then converted to an actual height using physical calibration. This helps determine whether the target is a low-altitude bird. For example, if the calculated center of gravity height is 0.5 meters, it is likely a bird; if it is 1.2 meters, it is more likely a person or a large pet.

[0049] In step S1055, "category similarity" is determined by comparing the target's visual feature vector with a bird feature template in a preset library. This library stores typical features (such as feather texture distribution and wing shape parameters) trained on a large number of bird images. A cosine similarity algorithm is used to calculate the degree of match between the target's features and the bird template, with the output value ranging from 0 to 1 (larger values indicate greater similarity). This algorithm uses prior knowledge from machine learning to make a probabilistic judgment about the target's category. For example, a category similarity of 0.9 indicates a high degree of confidence that the target is a bird, thus directly eliminating false detections. A similarity of 0.3 indicates significant differences between the target and bird features, requiring further analysis based on other dimensional data.

[0050] In step S1056, the "visual discrimination value" is generated by weighted fusion of the target's aspect ratio, center of gravity height, and category similarity. H is the bird center of gravity height threshold (e.g., 0.6 meters), and C is the category similarity. The specific calculation logic is: ① The smaller the aspect ratio deviates from 1, the closer (1-|AR-1|) is to 1, indicating a more bird-like appearance. ② If the center of gravity height ≥ H, the object is considered non-bird, and the corresponding item is 1; otherwise, it is 0. ③ The lower the category similarity, the closer (1-C) is to 1, indicating a higher probability of non-bird contact. The weighted sum of these three items yields a discrimination value in the 0-1 range. Higher values indicate a higher risk of mistouching a non-bird object.

[0051] Continue to refer to Figure 1 , after step S105, step S106 is performed, specifically as follows: Step S1061: obtaining a first weight coefficient according to the temperature difference discrimination value; Step S1062: obtaining a second weight coefficient according to the displacement discrimination value; Step S1063: obtaining a third weight coefficient according to the infrared discrimination value; Step S1064: obtaining a fourth weight coefficient according to the visual discrimination value; Step S1065: Obtaining an environmental compensation coefficient; Step S1066: Obtain a comprehensive discrimination index according to the temperature difference discrimination value, the displacement discrimination value, the infrared discrimination value, the visual discrimination value, the first weight coefficient, the second weight coefficient, the third weight coefficient, the fourth weight coefficient and the environmental compensation coefficient.

[0052] The acquisition of the "first weight coefficient" in step S1061 of the present invention is based on a dynamic evaluation mechanism for temperature difference discrimination values. Its vocabulary originates from the reliability of temperature difference data in different environments, and its significance lies in reflecting the contribution of temperature difference characteristics to the discrimination of non-bird false touches. Specifically, the system pre-establishes a mapping relationship between temperature difference discrimination values and weight coefficients. This relationship is derived from the statistical response sensitivity of temperature difference indicators to false touch events in historical data. For example, in low-temperature environments, temperature differences are more indicative of biological contact, and the corresponding first weight coefficient is automatically increased when the temperature difference discrimination value is higher. Its function is to dynamically adjust the weight of temperature difference data in the comprehensive decision-making process based on its credibility. During calculation, the corresponding weight is obtained by searching a preset nonlinear mapping table (such as a piecewise function or neural network model output), achieving adaptive weighting of the temperature difference dimension.

[0053] In step S1062, the "second weight coefficient" is associated with the displacement discrimination value. Its terminology is derived from the ability of displacement characteristics to distinguish motion patterns, and its meaning is to quantify the comprehensive impact of displacement speed, distance, curvature and other characteristics on the risk of false touch. During the calculation process, the system uses exponential or polynomial functions to adjust the weight according to the size of the displacement discrimination value. For example, when the displacement discrimination value is low (such as low-speed long-distance movement), it is considered to be normal traffic behavior, and the second weight coefficient is automatically reduced; when the discrimination value is high (such as high-speed short-distance vibration), it is determined to be a high-risk false touch, and the weight coefficient is increased accordingly. The purpose is to highlight the indicative role of high-risk motion patterns in displacement data through a nonlinear weight distribution strategy, and to enhance sensitivity to scenarios such as pet collisions and object collisions.

[0054] The determination of the "third weight coefficient" in step S1063 depends on the infrared discrimination value. Its vocabulary originates from the persistence and directional characteristics of infrared occlusion, and its significance lies in distinguishing effective occlusion from natural interference (such as fallen leaves and gusts of wind). The specific method is as follows: a threshold for the infrared discrimination value is preset. When the infrared discrimination value is greater than the threshold (such as continuous and stable occlusion), the third weight coefficient takes a higher value, indicating that the occlusion event has a higher risk of false touch; when the discrimination value is less than the threshold (such as instantaneous random occlusion), the weight coefficient takes a lower value. The purpose is to filter out invalid interference in the infrared data through tiered weight setting. During calculation, the weight assignment after threshold comparison is implemented through conditional judgment statements, ensuring that the infrared dimension plays an important role only in effective occlusion scenarios.

[0055] In step S1064, the "fourth weight coefficient" is determined by the visual discrimination value. Its terminology stems from the visual image's ability to directly identify the target category, and its purpose is to prioritize visual features to exclude bird targets. The calculation logic is as follows: when the visual discrimination value is low (e.g., the target category similarity matches bird), the fourth weight coefficient automatically decreases, reducing the weight of visual data in the overall decision-making process; when the discrimination value is high (e.g., the target is a pet or a person), the weight coefficient increases, reinforcing the dominant role of visual features. This function is to quickly filter out bird-related false positives through a category-priority strategy. The calculation utilizes a combination of logical reasoning and linear interpolation, dynamically assigning weights based on the visual discrimination value range (e.g., [0, 0.5], (0.5, 1]), effectively distinguishing between birds and non-bird targets.

[0056] In step S1065, the "environmental compensation coefficient" is derived from real-time environmental parameters, including temperature, light intensity, and wind speed. Its origin is related to the impact of environmental factors on sensor performance, and its purpose is to eliminate the interference of environmental noise on data of various dimensions. The specific process is: Environmental sensors deployed in the gated area (such as thermometers, hygrometers, light sensors, and anemometers) collect parameters in real time, and a pre-established compensation model is used to calculate the compensation factor. For example, in high-temperature environments, the drift of the temperature difference sensor is small, so the compensation coefficient increases the temperature difference weight. In strong light environments, the false alarm rate of the infrared matrix increases, so the compensation coefficient attenuates the infrared weight. Dynamic calibration of the weights of each dimension ensures system stability in complex environments such as a wide temperature range of -25°C to +60°C and low light levels of 0.01 lux.

[0057] The calculation of the "comprehensive discrimination index" in step S1066 is the core link of multi-dimensional data fusion. The process is as follows: first, the temperature difference discrimination value, displacement discrimination value, infrared discrimination value, and visual discrimination value are multiplied by the corresponding first to fourth weight coefficients respectively to obtain the weighted value of each dimension; then the weighted values are summed to form a preliminary comprehensive index; finally, multiplied by the environmental compensation coefficient to obtain the final comprehensive discrimination index. The calculation formula can be expressed as: ,in, Indicates the temperature difference discrimination value, Indicates the displacement discrimination value, Indicates infrared discrimination value, represents the visual discrimination value, represents the first weight coefficient, represents the second weight coefficient, represents the third weight coefficient, Indicates that the fourth weight coefficient is the weight coefficient, Represents the environmental compensation coefficient. The significance of this indicator lies in converting four types of heterogeneous data—temperature difference, displacement, infrared, and visual—into a unified risk value, providing the sole basis for subsequent dual-threshold decision-making. During the calculation process, the weight distribution of each dimension of data reflects the principle of "morphological characteristics first, dynamic environmental calibration." For example, when bird morphological characteristics are obvious (low visual discrimination value), even if the discrimination values of other dimensions are high, the comprehensive indicator will be suppressed due to the reduced visual weight, avoiding misjudgment. When non-bird targets continuously contact the door (high discrimination values of all dimensions and a gain in the environmental compensation coefficient), the comprehensive indicator quickly exceeds the threshold, triggering a graded protection response.

[0058] Example 2 Embodiment 2 of the present invention provides a non-bird false touch gate control dynamic protection system based on the fusion of temperature difference and displacement dual thresholds. Figure 2 FIG. 1 is a system block diagram according to an exemplary embodiment. Figure 2 As shown in the figure, the non-bird accidental touch gate dynamic protection system based on the fusion of temperature difference and displacement dual thresholds includes: Data acquisition module 1, used to obtain real-time monitoring data of the gated area, wherein the real-time monitoring data includes temperature difference characteristic parameters, displacement characteristic parameters, infrared shielding parameters and visual image parameters; Temperature difference analysis module 2, used for obtaining a temperature difference discrimination value according to the temperature difference characteristic parameter; A displacement analysis module 3, configured to obtain a displacement discrimination value based on the displacement characteristic parameters; Infrared analysis module 4, used to obtain infrared discrimination value according to the infrared blocking parameter; A visual analysis module 5, configured to obtain a visual discrimination value based on the visual image parameters; A fusion decision module 6 is used to obtain a comprehensive discrimination index based on the temperature difference discrimination value, the displacement discrimination value, the infrared discrimination value and the visual discrimination value; Decision module 7, used to determine whether the comprehensive discrimination index exceeds a preset double-threshold decision interval; If the comprehensive discrimination index exceeds the preset dual-threshold decision interval, it is determined to be a non-bird accidental touch and a graded protection response is triggered; If the comprehensive discrimination index does not exceed the preset dual-threshold decision interval, it is determined to be a normal state and the original state of the gate is maintained.

[0059] In one embodiment, the temperature difference analysis module 2 includes: A temperature difference sequence acquisition unit is used to acquire the real-time temperature difference sequence and the ambient reference temperature in the temperature difference characteristic parameter; a change rate generating unit, configured to obtain a plurality of temperature difference values at adjacent moments according to the real-time temperature difference sequence, and generate a temperature difference change rate sequence according to the plurality of temperature difference values at adjacent moments; a temperature difference parameter calculation unit, configured to obtain an absolute value of the temperature difference and a duration of the temperature difference according to the temperature difference change rate sequence and the ambient reference temperature; a temperature difference-duration change rate calculation unit, configured to obtain the temperature difference-duration change rate based on the absolute value of the temperature difference and the duration of the temperature difference; The mapping unit is used to map the temperature difference-duration change rate to a preset interval to obtain a temperature difference judgment value.

[0060] In one embodiment, the displacement analysis module 3 includes: A coordinate sequence acquisition unit, configured to acquire a plurality of three-dimensional displacement coordinates and time stamp sequences according to the displacement characteristic parameters; a velocity calculation unit, configured to obtain displacement vector differences between adjacent moments according to a plurality of three-dimensional displacement coordinates and a timestamp sequence, and obtain a displacement velocity according to the displacement vector differences between adjacent moments; a distance calculation unit, configured to obtain a displacement distance according to the displacement speed; A trajectory fitting unit, configured to obtain a displacement trajectory curve graph according to the displacement distance and timestamp sequence; a curvature calculation unit, configured to obtain a motion trajectory curvature according to the displacement trajectory curve graph; The displacement discrimination value generating unit is used to obtain the displacement discrimination value according to the displacement speed, displacement distance and motion trajectory curvature.

[0061] In one embodiment, the infrared analysis module 4 includes: an occlusion area recognition unit, configured to obtain a plurality of occlusion areas according to the infrared occlusion parameters; a pixel statistics unit, configured to obtain a total number of occluded pixels at a plurality of moments according to the occluded area, and obtain an area of the occluded area according to the total number of occluded pixels; an area ratio calculation unit, configured to obtain a pixel area ratio of the occluded area according to the area of the occluded area; A duration calculation unit, configured to obtain an occlusion duration according to a pixel area ratio of the occlusion region; A direction change analysis unit, configured to obtain a region direction change sequence according to the occlusion duration and the pixel area ratio of the occlusion region; The infrared discrimination value generating unit is configured to obtain an infrared discrimination value according to the region direction change sequence.

[0062] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A dynamic protection method for non-bird false touch gate control based on the fusion of temperature difference and displacement dual thresholds, characterized by: The method comprises: Acquiring real-time monitoring data of the gated area, wherein the real-time monitoring data includes temperature difference characteristic parameters, displacement characteristic parameters, infrared shielding parameters, and visual image parameters; Obtaining a temperature difference discrimination value according to the temperature difference characteristic parameter; Obtaining a displacement discrimination value according to the displacement characteristic parameter; Obtaining an infrared discrimination value according to the infrared blocking parameter; Obtaining a visual discrimination value according to the visual image parameter; Obtaining a comprehensive discrimination index according to the temperature difference discrimination value, displacement discrimination value, infrared discrimination value and visual discrimination value; Determining whether the comprehensive discrimination index exceeds a preset dual-threshold decision interval; If the comprehensive discrimination index exceeds the preset dual-threshold decision interval, it is determined to be a non-bird accidental touch and a graded protection response is triggered; If the comprehensive discrimination index does not exceed the preset dual-threshold decision interval, it is determined to be a normal state and the original state of the gate is maintained.

2. The non-bird false touch gate dynamic protection method based on temperature difference and displacement dual threshold fusion according to claim 1 is characterized in that: The step of obtaining the temperature difference discrimination value according to the temperature difference characteristic parameter comprises: Obtaining a real-time temperature difference sequence and an ambient reference temperature in the temperature difference characteristic parameters; Acquire multiple temperature difference values at adjacent moments according to the real-time temperature difference sequence, and generate a temperature difference change rate sequence according to the multiple temperature difference values at adjacent moments; Obtaining the absolute value of the temperature difference and the duration of the temperature difference according to the temperature difference change rate sequence and the ambient reference temperature; Obtaining a temperature difference-duration change rate according to the absolute value of the temperature difference and the duration of the temperature difference; The temperature difference-duration change rate is mapped to a preset interval to obtain a temperature difference judgment value.

3. The non-bird false touch gate control dynamic protection method based on temperature difference and displacement dual threshold fusion according to claim 1 is characterized in that: The step of obtaining a displacement discrimination value according to the displacement characteristic parameter comprises: Acquire multiple three-dimensional displacement coordinates and time stamp sequences according to the displacement characteristic parameters; Obtaining displacement vector differences at adjacent moments according to a plurality of three-dimensional displacement coordinates and a time stamp sequence, and obtaining a displacement velocity according to the displacement vector differences at adjacent moments; Obtaining a displacement distance according to the displacement speed; Acquire a displacement trajectory curve graph according to the displacement distance and timestamp sequence; Obtaining a motion trajectory curvature according to the displacement trajectory curve graph; A displacement discrimination value is obtained according to the displacement speed, displacement distance and motion trajectory curvature.

4. The non-bird false touch gate control dynamic protection method based on temperature difference and displacement dual threshold fusion according to claim 1 is characterized in that: The step of obtaining the infrared discrimination value according to the infrared blocking parameter includes: Acquire multiple shading areas according to the infrared shading parameters; Obtaining a total number of occluded pixels at multiple moments according to the occluded area, and obtaining an area of the occluded area according to the total number of occluded pixels; Obtaining a pixel area ratio of the occluded area according to the occluded area; Obtaining the occlusion duration according to the pixel area ratio of the occlusion region; Acquire a region direction change sequence according to the occlusion duration and the pixel area ratio of the occlusion region; An infrared discrimination value is obtained according to the region direction change sequence.

5. The non-bird false touch gate control dynamic protection method based on temperature difference and displacement dual threshold fusion according to claim 1 is characterized in that: The step of obtaining a visual discrimination value according to the visual image parameter comprises: Obtaining target bounding box coordinates and category image information according to the visual image parameters; Obtaining a target aspect ratio according to the target bounding box coordinates; Obtaining the bottom coordinates of the bounding box according to the target bounding box coordinates; Obtaining the center of gravity height according to the bottom coordinates of the bounding box and the target aspect ratio; Obtaining category similarity from a preset library based on the category image information; A visual discrimination value is obtained according to the aspect ratio, center of gravity height and category similarity of the target.

6. The non-bird false touch gate dynamic protection method based on temperature difference and displacement dual threshold fusion according to claim 1 is characterized in that: The step of obtaining a comprehensive discrimination index according to the temperature difference discrimination value, the displacement discrimination value, the infrared discrimination value and the visual discrimination value comprises: Obtaining a first weight coefficient according to the temperature difference discrimination value; Obtaining a second weight coefficient according to the displacement discrimination value; Obtaining a third weight coefficient according to the infrared discrimination value; Obtaining a fourth weight coefficient according to the visual discrimination value; Obtain environmental compensation coefficient; A comprehensive discrimination index is obtained according to the temperature difference discrimination value, the displacement discrimination value, the infrared discrimination value, the visual discrimination value, the first weight coefficient, the second weight coefficient, the third weight coefficient, the fourth weight coefficient and the environmental compensation coefficient.

7. Non-bird accidental touch gate dynamic protection system based on temperature difference and displacement dual threshold fusion, characterized by: include: A data acquisition module is used to obtain real-time monitoring data of the gated area, wherein the real-time monitoring data includes temperature difference characteristic parameters, displacement characteristic parameters, infrared shielding parameters and visual image parameters; A temperature difference analysis module, configured to obtain a temperature difference discrimination value based on the temperature difference characteristic parameters; A displacement analysis module, configured to obtain a displacement discrimination value based on the displacement characteristic parameters; An infrared analysis module, configured to obtain an infrared discrimination value based on the infrared blocking parameter; A visual analysis module, configured to obtain a visual discrimination value based on the visual image parameters; A fusion decision module is used to obtain a comprehensive discrimination index based on the temperature difference discrimination value, the displacement discrimination value, the infrared discrimination value and the visual discrimination value; A decision module, configured to determine whether the comprehensive discrimination index exceeds a preset dual-threshold decision interval; If the comprehensive discrimination index exceeds the preset dual-threshold decision interval, it is determined to be a non-bird accidental touch and a graded protection response is triggered; If the comprehensive discrimination index does not exceed the preset dual-threshold decision interval, it is determined to be a normal state and the original state of the gate is maintained.

8. The non-bird accidental touch gate dynamic protection system based on temperature difference and displacement dual threshold fusion according to claim 7 is characterized in that: The temperature difference analysis module includes: A temperature difference sequence acquisition unit is used to acquire the real-time temperature difference sequence and the ambient reference temperature in the temperature difference characteristic parameter; a change rate generating unit, configured to obtain a plurality of temperature difference values at adjacent moments according to the real-time temperature difference sequence, and generate a temperature difference change rate sequence according to the plurality of temperature difference values at adjacent moments; A temperature difference parameter calculation unit is used to obtain the absolute value of the temperature difference and the duration of the temperature difference according to the temperature difference change rate sequence and the ambient reference temperature; a temperature difference-duration change rate calculation unit, configured to obtain the temperature difference-duration change rate based on the absolute value of the temperature difference and the duration of the temperature difference; The mapping unit is used to map the temperature difference-duration change rate to a preset interval to obtain a temperature difference judgment value.

9. The non-bird accidental touch gate dynamic protection system based on temperature difference and displacement dual threshold fusion according to claim 7 is characterized in that: The displacement analysis module includes: A coordinate sequence acquisition unit, configured to acquire a plurality of three-dimensional displacement coordinates and time stamp sequences according to the displacement characteristic parameters; a velocity calculation unit, configured to obtain displacement vector differences between adjacent moments according to a plurality of three-dimensional displacement coordinates and a timestamp sequence, and obtain a displacement velocity according to the displacement vector differences between adjacent moments; a distance calculation unit, configured to obtain a displacement distance according to the displacement speed; A trajectory fitting unit, configured to obtain a displacement trajectory curve graph according to the displacement distance and timestamp sequence; a curvature calculation unit, configured to obtain a motion trajectory curvature according to the displacement trajectory curve graph; The displacement discrimination value generating unit is used to obtain the displacement discrimination value according to the displacement speed, displacement distance and motion trajectory curvature.

10. The non-bird accidental touch gate dynamic protection system based on temperature difference and displacement dual threshold fusion according to claim 7 is characterized in that: The infrared analysis module includes: an occlusion area recognition unit, configured to obtain a plurality of occlusion areas according to the infrared occlusion parameters; a pixel statistics unit, configured to obtain a total number of occluded pixels at a plurality of moments according to the occluded area, and obtain an area of the occluded area according to the total number of occluded pixels; an area ratio calculation unit, configured to obtain a pixel area ratio of the occluded area according to the area of the occluded area; A duration calculation unit, configured to obtain an occlusion duration according to a pixel area ratio of the occlusion region; A direction change analysis unit, configured to obtain a region direction change sequence according to the occlusion duration and the pixel area ratio of the occlusion region; The infrared discrimination value generating unit is configured to obtain an infrared discrimination value according to the region direction change sequence.

Images