A method, device and system for detecting a line crossing

Abstract

The present application provides a line crossing detection method, device and system, wherein the line crossing detection method determines the position sequence of the target detection object based on the time information of each pulse signal in the target pulse sequence received by at least two UWB base stations, the target pulse sequence is sent by the UWB tag carried by the target detection object, and based on the position sequence of the target detection object, the motion trajectory of the target detection object is fitted, so that when the motion direction conforms to the preset motion direction, based on the detection area corresponding to the target line and the motion path of the target detection object, the target position point among each position point of the position sequence is determined, and when the target position point exists, based on the signal sending time of the pulse signal corresponding to the target position point, the moment when the target detection object passes the target line is determined, thereby effectively improving the accuracy of line crossing detection and having high convenience in the application process.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and more specifically, to a line crossing detection method, device and system in the field of data processing. Background Art

[0002] With the advancement of technology and the increasing demand for intelligence, line crossing detection is becoming more and more widely used in sports events, security, traffic management and other fields.

[0003] Existing line crossing detection methods usually use RFID (Radio Frequency Identification) tags, image recognition, etc. for line crossing detection, which has the problems of poor detection accuracy and low convenience during application. Therefore, it is necessary to provide a method that is easy to use and has high line crossing detection accuracy. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides a line crossing detection method, device and system to achieve the purpose of improving the accuracy of line crossing detection and the convenience in the application process.

[0005] To achieve the above technical objectives, the present application provides the following technical solutions:

[0006] In a first aspect, an embodiment of the present specification provides a line crossing detection method, comprising:

[0007] Determine the position sequence of the target detection object based on the time information of each pulse signal in the target pulse sequence received by at least two UWB base stations; wherein the target pulse sequence is sent by the UWB tag carried by the target detection object;

[0008] Fitting a motion trajectory of the target detection object based on a position sequence of the target detection object, wherein the motion trajectory includes a motion path and a motion direction;

[0009] When the motion direction conforms to the preset motion direction, a target position point among the position points of the position sequence is determined based on the detection area corresponding to the target line and the motion path of the target detection object; the target line includes a line to be subjected to line crossing detection, the detection area corresponding to the target line includes the target line and an area in a first area adjacent to the target line, the first area includes an area after passing the target line, and the target position point includes a position point representing a moment when the target detection object crosses the line;

[0010] When the target position point exists, the time when the target detection object passes through the target line is determined based on the signal sending time of the pulse signal corresponding to the target position point.

[0011] Optionally, determining the position sequence of the target detection objects based on the time information of each pulse signal in the target pulse sequence received by at least two UWB base stations includes:

[0012] Based on the time information of each pulse signal in the target pulse sequence received by each UWB base station and the signal sending time of each pulse signal, at least one ranging sequence is determined; the ranging sequence includes the distance information between the target detection object and the UWB base station or the distance difference between the target detection object and the two UWB base stations at the signal sending time of each pulse signal;

[0013] Filtering is performed on each of the distance measurement sequences, and based on each of the distance measurement sequences after filtering, a position sequence of the target detection object is determined.

[0014] Optionally, filtering the ranging sequence includes:

[0015] Acquire target feature data of each data point in the ranging sequence; the data point includes a distance estimation value at the time when the signal is sent;

[0016] Based on the target feature data, determining the sorting information of the feature distance between the data point and each sample point in the preset data set; the sample point includes a distance measurement value at the sample position;

[0017] Determining a preset number of target points from each of the sample points based on sorting information of characteristic distances between the data point and each of the sample points;

[0018] Based on the distance measurement value corresponding to each of the target points, the target distance corresponding to the data point is determined, and the distance estimation value corresponding to the data point is updated to the target distance.

[0019] Optionally, fitting the motion trajectory of the target detection object based on the position sequence of the target detection object includes:

[0020] Based on the coordinate information of each position point in the position sequence of the target detection object, a consistent random sampling method is used to determine the movement path of the target detection object, and based on the coordinate information of each position point and the signal sending time of the pulse signal corresponding to each position point, the movement direction of the target detection object is determined.

[0021] Optionally, the determining the target position point among the position points in the position sequence based on the detection area corresponding to the target line and the motion path of the target detection object includes:

[0022] Acquire each position point in the position sequence of the target detection object whose distance from the motion path of the target detection object is less than a preset distance, and use them as candidate points;

[0023] The target position point is determined based on the coordinate information of each candidate point located in the detection area and / or the signal sending time of the corresponding pulse signal.

[0024] Optionally, it also includes:

[0025] When the target position point does not exist, determining a first position point and a second position point based on the coordinate information of each of the candidate points; the first position point is located in the first area, the second position point is located in the second area, and the second area includes an area before passing the target line;

[0026] The time when the target detection object passes through the target line is determined based on the signal sending time of the pulse signal corresponding to the first position point and the signal sending time of the pulse signal corresponding to the second position point.

[0027] Optionally, determining the time when the target detection object passes through the target line based on the signal sending time of the pulse signal corresponding to the first position point and the signal sending time of the pulse signal corresponding to the second position point includes:

[0028] Based on the signal sending time of the pulse signal corresponding to the first position point, the signal sending time of the pulse signal corresponding to the second position point, the coordinate information of the first position point, the coordinate information of the second position point, and the coordinate information of the intersection of the motion path of the target detection object and the target line, the time when the target detection object passes through the target line is determined by interpolation.

[0029] In a second aspect, an embodiment of the present specification provides a line crossing detection device, including:

[0030] A first processing module, configured to determine a position sequence of a target detection object based on time information of each pulse signal in a target pulse sequence received by at least two UWB base stations; wherein the target pulse sequence is sent by a UWB tag carried by the target detection object;

[0031] A second processing module, configured to fit a motion trajectory of the target detection object based on a position sequence of the target detection object, wherein the motion trajectory includes a motion path and a motion direction;

[0032] A third processing module is used to determine, when the motion direction conforms to a preset motion direction, a target position point among the position points of the position sequence based on a detection area corresponding to a target line and a motion path of the target detection object; the target line includes a line to be subjected to line crossing detection, the detection area corresponding to the target line includes the target line and an area in a first area adjacent to the target line, the first area includes an area after passing through the target line, and the target position point includes a position point representing a moment when the target detection object crosses the line;

[0033] The fourth processing module is used to determine the time when the target detection object passes through the target line based on the signal sending time of the pulse signal corresponding to the target position point when the target position point exists.

[0034] In a third aspect, the embodiments of this specification provide a line crossing detection system, including: a controller, at least two UWB base stations and at least one UWB tag; the UWB tag is used to be carried to a target detection object;

[0035] The UWB tag is used to send a target pulse sequence to each of the UWB base stations, and feed back the signal sending time of each pulse signal in the target pulse sequence to the controller;

[0036] The UWB base station is used for feeding back the time information of receiving each pulse signal in the target pulse sequence to the controller when receiving the target pulse sequence;

[0037] The controller includes at least one processor and at least one memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the line crossing detection method as described in any one of the above items is implemented.

[0038] In a fourth aspect, an embodiment of the present specification provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the line crossing detection method as described in any one of the above items is implemented.

[0039] In a fifth aspect, an embodiment of the present specification provides a computer program product or a computer program, wherein the computer program product includes a computer program, and the computer program is stored in a computer-readable storage medium; the processor of the computer device reads the computer program from the computer-readable storage medium, and the processor implements the over-the-line detection method as described in any one of the above items when executing the computer program.

[0040] It can be seen from the above technical scheme that the embodiments of the present application provide a line crossing detection method, device and system, wherein the line crossing detection method determines the position sequence of the target detection object based on the time information of each pulse signal in the target pulse sequence received by at least two UWB base stations, the target pulse sequence is sent by the UWB tag carried by the target detection object, and based on the position sequence of the target detection object, fits the motion trajectory of the target detection object, the motion trajectory includes a motion path and a motion direction, so that when the motion direction conforms to the preset motion direction, based on the detection area corresponding to the target line and the motion path of the target detection object, the target position point in each position point of the position sequence is determined, and when the target position point exists, based on the signal sending time of the pulse signal corresponding to the target position point, the moment when the target detection object passes the target line is determined, thereby effectively reducing the influence of the positioning accuracy error on the detection accuracy of the moment when the target detection object passes the target line, thereby achieving effective improvement of the line crossing detection accuracy, and having high convenience in the application process. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0042] Figure 1 A schematic flow chart of a line crossing detection method provided for one embodiment of this specification;

[0043] Figure 2 A schematic structural diagram of a line crossing detection device provided for one embodiment of this specification;

[0044] Figure 3 A schematic diagram of the structure of a line crossing detection system provided for one embodiment of the present specification. DETAILED DESCRIPTION

[0045] Unless otherwise defined, the technical terms or scientific terms used in the embodiments of this specification shall have the common meanings understood by persons with ordinary skills in the field to which this specification belongs. The words "first", "second" and similar words used in the embodiments of this specification do not indicate any order, quantity or importance, but are only used to avoid confusion of constituent elements.

[0046] Unless the context requires otherwise, throughout the specification, "plurality" means "at least two", and "including" is interpreted as an open, inclusive meaning, that is, "including, but not limited to". In the description of the specification, the terms "one embodiment", "some embodiments", "exemplary embodiments", "examples", "specific examples" or "some examples" are intended to indicate that a particular feature, structure, material or characteristic associated with the embodiment or example is included in at least one embodiment or example of the specification. The schematic representation of the above terms does not necessarily refer to the same embodiment or example.

[0047] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0048] Overview

[0049] As described in the background technology, with the advancement of science and technology and the increasing demand for intelligence, line crossing detection is being used more and more widely in the fields of sports events, security, traffic management, etc. For example, the time detection of athletes crossing the finish line in sports events, the time detection of entering and exiting gates, building entrances and exits, parking lot entrances and exits, aisles, corridors, roads, intersections, T-junctions, etc. Sports events may include middle- and long-distance running, marathon competitions, physical training, etc.

[0050] Existing line crossing detection methods usually use RFID tags, image recognition, etc. for line crossing detection, which has the problems of poor detection accuracy and low convenience in application.

[0051] For example, when RFID tags are applied to the process of crossing the line detection at the entrance and exit, the object of detection needs to swipe the card at close range, which greatly reduces the efficiency of passage and cannot avoid the problem of tailgating in and out; in addition, it is not suitable for the monitoring and management of pedestrian and / or vehicle flows in aisles, corridors, roads, intersections, T-junctions, etc.; when RFID tags are applied to sports events, the standard detection distance of RFID is only about 5 meters, and it is difficult to achieve centimeter-level accuracy; at the same time, if active tags are used, the power consumption of active devices is very large. For example, a marathon will continue to work for about 8 hours, and the battery capacity is large and difficult to wear; if passive tags are used, wired receiving equipment needs to be temporarily deployed on the track, which is cumbersome to deploy and can only provide time. The accuracy of the provided time cannot be guaranteed, and 100% reading cannot be achieved, which can easily lead to the loss of athletes' scores.

[0052] When applying facial recognition to the process of crossing the line detection at entrances and exits, facial information needs to be entered in advance. It is usually applied to gates and key entrances and exits, and has strict requirements on the installation environment. The accuracy rate is low during outdoor environment detection, the experience is poor, and the cost is high. It requires close-range face scanning, and the pass rate is lower than traditional RFID. In addition, it needs to be used in conjunction with gate machines, and the deployment and transformation project is complicated. When applying facial recognition to sports events, due to the high density of participants, it is easy to fail due to facial obstruction, outdoor light, etc.

[0053] License plate recognition is usually only applicable to the management of vehicle access at parking lots and gates, and needs to be used in conjunction with gates. The deployment and transformation project is complex, which greatly reduces the access rate of vehicles. At the same time, manual participation is required when encountering recognition problems, and it cannot be completely unmanned, nor can it be applied to the monitoring and management of pedestrian and / or vehicle flows on roads, intersections, T-junctions, etc.

[0054] In the process of counting people based on cameras or radars, the accuracy is poor, usually less than 70%, which cannot meet the accuracy requirements. In addition, it does not have the function of identifying objects, making it difficult to judge whether people are following in and out.

[0055] Therefore, it is necessary to provide a method that is easy to use and has high line crossing detection accuracy.

[0056] In order to solve the problems of poor accuracy of traditional methods in line crossing detection and low convenience in application, in the technical solution of the present application, based on the time information of each pulse signal in the target pulse sequence received by at least two UWB base stations, the position sequence of the target detection object is determined, the target pulse sequence is sent by the UWB tag carried by the target detection object, and based on the position sequence of the target detection object, the motion trajectory of the target detection object is fitted, the motion trajectory includes a motion path and a motion direction, so that when the motion direction conforms to the preset motion direction, based on the detection area corresponding to the target line and the motion path of the target detection object, the target position point among each position point of the position sequence is determined, and when the target position point exists, based on the signal sending time of the pulse signal corresponding to the target position point, the moment when the target detection object passes the target line is determined, thereby effectively reducing the influence of the positioning accuracy error on the detection accuracy of the moment when the target detection object passes the target line, thereby achieving effective improvement of the line crossing detection accuracy, and having high convenience in the application process.

[0057] At the same time, in order to further improve the detection accuracy when the target detection object passes through the target line, the line crossing detection method provided in the implementation mode of this specification also defines a specific method for determining the position sequence of the target detection object and a specific method for fitting the motion trajectory of the target detection object.

[0058] Based on the above-mentioned inventive concept, the line crossing detection method provided in the embodiment of this specification is exemplarily described below.

[0059] Exemplary Methods

[0060] The embodiments of this specification provide a method for detecting a line crossing, such as Figure 1 As shown, including:

[0061] S101. Determine a position sequence of a target detection object based on time information of each pulse signal in a target pulse sequence received by at least two UWB (Ultra-Wide Band) base stations; wherein the target pulse sequence is sent by a UWB tag carried by the target detection object.

[0062] Specifically, the target detection object is an object to be detected for crossing the line, such as a person, a car, etc., and the number of the target detection objects can be one or more.

[0063] Each target detection object can carry a UWB tag, and the target detection object and the carried UWB tag can be bound in advance.

[0064] After the UWB tag is turned on, it can send pulse signals based on a preset frequency, and the pulse signals sent at each moment constitute a target pulse sequence. For any UWB base station, after receiving a pulse signal in the target pulse sequence, the time information of receiving the pulse signal can be recorded. Among them, the UWB base station can be set near the target line, and the target line is the line to be detected. For example, in sports events, the target line can be the finish line. In the process of entrance and exit detection, the target line can be a line representing the entrance and exit gates, building entrances and exits, parking lot entrances and exits, aisles, corridors, roads, intersections, and T-junctions.

[0065] In implementation, the position sequence of the target detection object can be determined based on the time information of each UWB base station receiving each pulse signal in the target pulse sequence. The position sequence can include the position points corresponding to the signal transmission time of each pulse signal in the target pulse sequence. For any position point, the position point can be used to characterize the calculation result of the position of the target detection object at the corresponding signal transmission time.

[0066] Among them, for any signal sending moment, the signal transmission duration can be determined based on the difference between the moment when the UWB base station receives the pulse signal sent by the UWB tag carried by the target detection object at the signal sending moment and the signal sending moment, and the distance between the target detection object and the UWB base station at the signal sending moment can be determined based on the signal transmission duration and the signal transmission speed. Therefore, based on the distance between the target detection object and the two UWB base stations and the distance between the two UWB base stations, the position of the target detection object at the signal sending moment can be determined by the trigonometric function method.

[0067] In addition, for any signal sending moment, the distance difference between the target detection object and each UWB base station can be determined based on the time difference of the pulse signal sent by the UWB tag carried by the target detection object at the signal sending moment received by at least two UWB base stations, and based on the time difference and the signal transmission speed, thereby determining the hyperbola corresponding to each UWB base station based on the distance difference, that is, for any UWB base station, the hyperbola corresponding to the UWB base station includes all position coordinates that meet the distance difference, and the intersection of the hyperbola corresponding to each UWB base station can be used as the position of the target detection object at the signal sending moment. Through this method, there is no need to add a special timestamp to synchronize the clocks of multiple UWB base stations, so that the detection accuracy of the position sequence of the target detection object is greatly improved. It can be understood that when using this method, three or more UWB base stations can be set to ensure effective detection of the position sequence of the target detection object.

[0068] UWB technology can achieve long-distance perception, without the need for close-range card swiping, and the accuracy can reach the centimeter level, and there is no tailing problem. Therefore, it provides technical support for improving the accuracy and convenience of line crossing detection. At the same time, through the method of this embodiment, only at least two UWB base stations need to be set up near the target line, and there is no need to modify the entrance and exit, and there is no need to use it in conjunction with the gate. It is wirelessly deployed, the project is simple, and people, vehicles, and objects can travel together. There is no need to swipe cards or face recognition, and the traffic efficiency is high. It can be applied to sports events and various situations such as entering and exiting gates, building entrances and exits, parking lot entrances and exits, aisles, corridors, roads, intersections, T-junctions, etc., which further improves the convenience during the application process.

[0069] S102: Fitting a motion trajectory of the target detection object based on a position sequence of the target detection object, where the motion trajectory includes a motion path and a motion direction.

[0070] Specifically, each position point in the position sequence of the target detection object can be fitted to obtain the motion path of the target detection object. At the same time, the motion direction of the target detection object can be determined based on the coordinate information of each position point in the position sequence of the target detection object and the signal sending time of the pulse signal corresponding to each position point. Thus, the motion path and motion direction can be used as the motion trajectory of the target detection object.

[0071] S103. When the movement direction conforms to the preset movement direction, based on the detection area corresponding to the target line and the movement path of the target detection object, determine the target position point among the position points of the position sequence; the target line includes the line to be detected for crossing the line, the detection area corresponding to the target line includes the target line and the area adjacent to the target line in the first area, the first area includes the area after passing the target line, and the target position point includes the position point representing the crossing moment of the target detection object.

[0072] Specifically, the preset movement direction may be a predefined direction of line crossing detection, for example, from a first side of the target line to a second side of the target line.

[0073] In implementation, when the movement direction of the target detection object does not conform to the preset movement direction, there is no need to perform line crossing detection. When the movement direction of the target detection object conforms to the preset movement direction, the target position point in each position point of the position sequence can be determined based on the detection area corresponding to the target line and the movement path of the target detection object. Among them, the detection area corresponding to the target line is the area used for line crossing detection. For example, when the target detection object moves in the preset movement direction, the moment when the target detection object moves to the detection area can be used as the moment when the target detection object passes the target line.

[0074] The detection area corresponding to the target line may include the target line and the area adjacent to the target line in the first area. The first area includes the area after passing the target line during movement in a preset movement direction. The width of the detection area can be determined based on the line crossing detection accuracy. The smaller the width, the higher the detection accuracy, and vice versa.

[0075] Among them, in the process of determining the target position point among the position points of the position sequence based on the detection area corresponding to the target line and the motion path of the target detection object, the position point among the position points of the position sequence whose distance from the motion path is less than the preset distance and is located in the detection area can be used as the target position point, that is, the signal sending time corresponding to the target position point can be used to characterize the time when the target detection object crosses the line. It can be understood that the number of target position points can be one or more, which can be set according to actual needs.

[0076] S104. When the target position point exists, determine the time when the target detection object passes through the target line based on the signal sending time of the pulse signal corresponding to the target position point.

[0077] Specifically, considering that the motion path of the target detection object is obtained by fitting, there may be no position point in the position sequence whose distance from the motion path is less than a preset distance and is located in the detection area, that is, there is no target position point.

[0078] When the target position point exists, the time when the target detection object passes through the target line can be determined based on the signal sending time of the pulse signal corresponding to the target position point. For example, the signal sending time of the pulse signal corresponding to the target position point can be directly used as the time when the target detection object passes through the target line. The signal sending time of the pulse signal corresponding to the target position point can also be corrected, and the result of the correction processing can be used as the time when the target detection object passes through the target line. For example, the size of the compensation value can be determined based on the distance between the target position point and the target line, and the corresponding relationship between the distance and the compensation value, and the signal sending time of the pulse signal corresponding to the target position point can be corrected according to the size of the compensation value. The movement speed of the target detection object can also be determined based on the distance between the target position point and the designated position point in the motion trajectory of the target detection object, and the signal sending time of the pulse signal corresponding to the target position point and the designated position point, and the compensation duration can be determined based on the movement speed and the distance between the target position point and the target line, so as to correct the signal sending time of the pulse signal corresponding to the target position point according to the compensation duration. The designated position point can be a position point among the position points in the position sequence, the distance between which and the motion path is less than the preset distance, and which is located before the target position point, thereby further improving the detection accuracy of the moment when the target detection object passes the target line.

[0079] In order to further improve the detection accuracy of the moment when the target detection object passes through the target line, in one embodiment of the present specification, the determining of the position sequence of the target detection object based on the moment information of each pulse signal in the target pulse sequence received by at least two UWB base stations includes:

[0080] Based on the time information of each pulse signal in the target pulse sequence received by each UWB base station and the signal sending time of each pulse signal, at least one ranging sequence is determined; the ranging sequence includes the distance information between the target detection object and the UWB base station or the distance difference between the target detection object and the two UWB base stations at the signal sending time of each pulse signal;

[0081] Filtering is performed on each of the distance measurement sequences, and based on each of the distance measurement sequences after filtering, a position sequence of the target detection object is determined.

[0082] Specifically, the number of ranging sequences may be one or more. For example, if the ranging sequence includes the distance information between the target detection object and the UWB base station at the signal sending moment of each pulse signal in the target pulse sequence, then the ranging sequence corresponding to each UWB base station may be included; if the ranging sequence includes the distance difference between the target detection object and two UWB base stations at the signal sending moment of each pulse signal in the target pulse sequence, then any two UWB base stations may correspond to one ranging sequence. For example, when two UWB base stations are included, the number of ranging sequences may be one, and when three UWB base stations are included, the number of ranging sequences may be three.

[0083] For any ranging sequence, filtering processing may be performed on the ranging sequence, and the filtering processing may include low-pass filtering, median filtering, etc.

[0084] As a preferred implementation, each ranging sequence may be low-pass filtered to filter out high-frequency noise; and then each ranging sequence after low-pass filtering may be median filtered to remove random noise, pulse noise, etc. It is understandable that each ranging sequence after median filtering may be sent to a preset display device for display, so that the user may select ROI (Region Of Interest) to further remove noise interference in each ranging sequence. For example, in response to the user's deletion or selection operation of data points in the ranging sequence after median filtering, data points may be deleted or selected to achieve ROI selection. In addition, before low-pass filtering, each ranging sequence may be pre-processed, such as signal synchronization, DC component removal, normalization, etc. After ROI selection, each ranging sequence may be post-processed, such as de-jittering, smoothing, etc., to further improve the reliability of the ranging sequence.

[0085] During implementation, the position sequence of the target detection object can be determined based on each ranging sequence after filtering, thereby effectively reducing the influence of interference factors such as occlusion between UWB tags and metal surface reflection on the accuracy of each distance information in the ranging sequence, and further improving the detection accuracy of the target detection object when it passes the target line.

[0086] Among them, when the ranging sequence includes the distance information between the target detection object and the UWB base station at the signal sending moment of each pulse signal in the target pulse sequence, for any signal sending moment, the position of the target detection object at the signal sending moment can be determined by a trigonometric function method based on the distance information at the signal sending moment in the ranging sequence after filtering corresponding to each UWN base station and the distance between the two UWB base stations. When the ranging sequence includes the distance difference between the target detection object and the two UWB base stations at the signal sending moment of each pulse signal in the target pulse sequence, for any signal sending moment, the hyperbola corresponding to the UWB base station can be determined based on the distance difference between the target detection object and the UWB base station and other UWB base stations at the signal sending moment in each ranging sequence after filtering, and the position of the target detection object at the signal sending moment is determined according to the intersection of the hyperbolas corresponding to each UWB base station, so as to effectively ensure the detection accuracy of the position sequence of the target detection object.

[0087] In a feasible implementation manner, filtering the ranging sequence includes:

[0088] Acquire target feature data of each data point in the ranging sequence; the data point includes a distance estimation value at the time when the signal is sent;

[0089] Based on the target feature data, determining the sorting information of the feature distance between the data point and each sample point in the preset data set; the sample point includes a distance measurement value at the sample position;

[0090] Determining a preset number of target points from each of the sample points based on sorting information of characteristic distances between the data point and each of the sample points;

[0091] Based on the distance measurement value corresponding to each of the target points, the target distance corresponding to the data point is determined, and the distance estimation value corresponding to the data point is updated to the target distance.

[0092] Specifically, for any data point in the ranging sequence, the data point may include a distance estimation value at the corresponding signal transmission time, and the distance estimation value is the distance information between the target detection object and the UWB base station or the distance difference between the target detection object and two UWB base stations. The target feature data of the data point may include the distance estimation value, and may also include the relative relationship between the data point and adjacent data points, such as a difference, a ratio, etc., which may be set according to actual needs.

[0093] The preset data set may include multiple sample points. For any sample point, the sample point may include a distance measurement value at the corresponding sample position, that is, the actual distance at the corresponding sample position. The sample position is the coordinate information corresponding to the sample point on the ground.

[0094] In implementation, the characteristic distance between the data point and each sample point in the preset data set can be determined based on the target characteristic data. The characteristic distance can include Euclidean distance, Manhattan distance, etc., and the characteristic distance between the data point and each sample point in the preset data set is sorted to obtain the sorting information of the characteristic distance between the data point and each sample point in the preset data set, and based on the sorting information, a preset number of target points are determined from each sample point in the preset data set. The preset number is greater than 1, and the specific value can be set according to actual needs. For example, based on the sorting information, a preset number of target points can be selected in the order of characteristic distance from small to large.

[0095] After determining the target point, the target distance corresponding to the data point can be determined based on the distance measurement value corresponding to each target point. For example, the median or mean of the distance measurement value corresponding to each target point can be used as the target distance corresponding to the data point, and the distance estimation value corresponding to the data point is updated to the target distance, thereby effectively improving the accuracy of each data point in the distance measurement sequence and providing a data basis for improving the detection accuracy of the target detection object when it passes through the target line.

[0096] In order to further improve the detection accuracy of the moment when the target detection object passes through the target line, in one embodiment of the present specification, fitting the motion trajectory of the target detection object based on the position sequence of the target detection object includes:

[0097] Based on the coordinate information of each position point in the position sequence of the target detection object, a consistent random sampling method is used to determine the movement path of the target detection object, and based on the coordinate information of each position point and the signal sending time of the pulse signal corresponding to each position point, the movement direction of the target detection object is determined.

[0098] Specifically, in the process of fitting the motion trajectory of the target detection object, the motion path of the target detection object can be determined by using a random sampling consensus method based on the coordinate information of each position point in the position sequence of the target detection object.

[0099] Among them, the random sampling consistency method uses an iterative manner to determine the motion trajectory of the target detection object; for any iteration, a group of position points can be randomly selected from each position point in the position sequence, and the number of selected position points must be greater than or equal to the minimum number of position points required when fitting the motion path, and less than the number of position points in the position sequence, and a curve equation is fitted according to the group of position points, and a tolerance interval is determined according to the fitted curve equation and the tolerance value, and the tolerance value is an acceptable error, and the number of position points in each position point of the position sequence that are within the tolerance interval is judged; through continuous iteration, when the number of position points within the tolerance interval is greater than or equal to the quantity threshold, the fitted curve equation can be used as the motion path of the target detection object, which effectively eliminates the influence of abnormal position points in the position sequence, so that when a large number of abnormal position points are contained in the position sequence, the motion path of the target detection object can still be accurately fitted.

[0100] It is understandable that the motion path of the target detection object can also be determined by the least squares method based on the coordinate information of each position point in the position sequence of the target detection object. However, the least squares method considers all the position points in the position sequence to fit the motion path. When the position sequence contains a large number of abnormal position points, the reliability of the fitted motion path cannot be guaranteed.

[0101] In addition, the movement direction of the target detection object can also be determined based on the coordinate information of each position point in the position sequence of the target detection object and the signal sending time of the pulse signal corresponding to each position point. For example, based on the coordinate information of each position point in the specified direction and the signal sending time corresponding to each position point, when the number of position points representing the movement of the target detection object in the same movement direction among the consecutive N position points is greater than or equal to n, the movement direction can be used as the movement direction of the target detection object in the time interval corresponding to the N position points, where N is a positive integer greater than 2, 1≤n≤N; when the number of position points representing the movement of the target detection object in the same movement direction among the consecutive N position points is less than n, the number of N can be reduced, and the movement direction of the target detection object in the time interval corresponding to the N position points can be re-determined.

[0102] It should be noted that the running path of the target detection object can be fitted in the same motion direction. For example, the motion path can be fitted when the target detection object moves from the first side of the target line to the second side of the target line, and from the second side of the target line to the first side of the target line.

[0103] In order to further improve the detection accuracy of the moment when the target detection object passes through the target line, in one embodiment of the present specification, the determination of the target position point among the position points of the position sequence based on the detection area corresponding to the target line and the motion path of the target detection object includes:

[0104] Acquire each position point in the position sequence of the target detection object whose distance from the motion path of the target detection object is less than a preset distance, and use them as candidate points;

[0105] The target position point is determined based on the coordinate information of each candidate point located in the detection area and / or the signal sending time of the corresponding pulse signal.

[0106] Specifically, the distance between each position point in the position sequence of the target detection object and the fitted motion path can be obtained, and each position point whose distance to the fitted motion path is less than a preset distance can be used as a candidate point. The preset distance can adopt the tolerance value in the motion path fitting process, and can also be set to other values ​​according to requirements.

[0107] After the candidate points are determined, the candidate points located in the detection area can be determined based on the coordinate information of each candidate point, and the target position point can be determined based on the coordinate information of each candidate point located in the detection area and / or the signal sending time of the corresponding pulse signal. For example, the distance between each candidate point located in the detection area and the target line can be determined based on the coordinate information of each candidate point located in the detection area, and the candidate point with the smallest distance from the target line can be used as the target position point, wherein, when there are multiple candidate points with the smallest distance from the target line, the candidate point with the smallest signal sending time can be used as the target position point according to the signal sending time of the pulse signal corresponding to each candidate point; in addition, the candidate point with the earliest signal sending time can be used as the target position point according to the signal sending time of the pulse signal corresponding to each candidate point located in the detection area, thereby more accurately determining the time when the target detection object passes through the target line according to the signal sending time of the pulse signal corresponding to the target position point.

[0108] In a feasible implementation, it also includes:

[0109] When the target position point does not exist, determining a first position point and a second position point based on the coordinate information of each of the candidate points; the first position point is located in the first area, the second position point is located in the second area, and the second area includes an area before passing the target line;

[0110] The time when the target detection object passes through the target line is determined based on the signal sending time of the pulse signal corresponding to the first position point and the signal sending time of the pulse signal corresponding to the second position point.

[0111] Specifically, the second area includes an area before the target line during movement in the preset movement direction.

[0112] When the target position point does not exist, it indicates that all position points in the position sequence of the target detection object whose distance from the motion path is less than the preset distance are not in the detection area. At this time, the first position point and the second position point can be determined based on the coordinate information of each candidate point, wherein the first position point is located in the first area and the second position point is located in the second area. For example, based on the coordinate information of each candidate point, the candidate point closest to the target line among the candidate points located in the first area can be used as the first position point, and the candidate point closest to the target line among the candidate points located in the second area can be used as the second position point.

[0113] Therefore, the moment when the target detection object passes the target line can be determined based on the signal sending time of the pulse signal corresponding to the first position point and the signal sending time of the pulse signal corresponding to the second position point, thereby ensuring the validity of the detection result at the moment when the target detection object passes the target line.

[0114] In a feasible implementation manner, determining the time when the target detection object passes through the target line based on the signal sending time of the pulse signal corresponding to the first position point and the signal sending time of the pulse signal corresponding to the second position point includes:

[0115] Based on the signal sending time of the pulse signal corresponding to the first position point, the signal sending time of the pulse signal corresponding to the second position point, the coordinate information of the first position point, the coordinate information of the second position point, and the coordinate information of the intersection of the motion path of the target detection object and the target line, the time when the target detection object passes through the target line is determined by interpolation.

[0116] Specifically, it is possible to determine whether the first position point, the second position point, and the intersection of the motion path of the target detection object and the target line are collinear based on the coordinate information of the first position point, the coordinate information of the second position point, and the coordinate information of the intersection of the motion path of the target detection object and the target line.

[0117] Among them, when the first position point, the second position point and the intersection point of the target line with the motion path of the target detection object are collinear, the time length between the first position point and the intersection point can be determined by linear interpolation according to the distance between the first position point and the intersection point, the distance between the first position point and the second position point, and the time length between the first position point and the second position point, and the time corresponding to the intersection of the motion path of the target detection object and the target line can be determined according to the signal sending time of the pulse signal corresponding to the first position point and the time length between the first position point and the intersection point, so as to use the time as the time when the target detection object passes the target line.

[0118] When the first position point, the second position point and the intersection of the motion path of the target detection object and the target line are not colinear, the first projection point of the first position point on the motion path and the second projection point of the second position point on the motion path can be obtained, and the signal sending time of the pulse signal corresponding to the first position point is used as the time corresponding to the first projection point, and the signal sending time of the pulse signal corresponding to the second position point is used as the time corresponding to the second projection point, so as to determine the time corresponding to the intersection of the motion path of the target detection object and the target line by linear interpolation method according to the time corresponding to the first projection point, the time corresponding to the second projection point, the coordinate information of the first projection point, the coordinate information of the second projection point and the coordinate information of the intersection, and use the time as the time when the target detection object passes the target line.

[0119] Therefore, the method of this embodiment can quickly and effectively determine the moment when the target detection object passes through the target line.

[0120] Taking sports events as an example, the implementation process of the line crossing detection method of this embodiment is illustrated. The competition event can be a middle-distance race or a marathon, and the target line is the finish line. Two UWB base stations are arranged side by side on the outside of the runway 5-10 meters away from the finish line, and multiple UWB tags (such as 30, which are determined according to the number of contestants) are configured. The UWB tags can be configured in the bracelet for the convenience of athletes to carry. The sports bracelet can adopt an ultra-small size and ultra-light weight design, such as a size of 43×23×13 mm, a weight of 25 grams, a built-in 160 mAh lithium battery, and a waterproof, ultra-long standby, easy-to-charge design. It can also monitor the athlete's heart rate, body temperature, blood oxygen, step counting and other health data at the same time and report them in real time. It can also be configured with a wearing detection function (such as an alarm when wearing and removing), and can also be configured with physical buttons and support motor vibration. In addition, it can also be configured with an LCD display to support receiving and displaying the alarm information sent.

[0121] The signal refresh rate of the UWB tag can be 5Hz-10Hz, which can be specifically controlled by the base station via Bluetooth. The size of the detection area corresponding to the finish line can be set according to on-site needs. The UWB base station can be equipped with a battery to support mobile deployment. Two UWB base stations are connected by wire or wireless. The athlete's crossing data is transmitted to the management platform by the POE (Power over Ethernet) interface of the UWB base station. The crossing data may include the crossing time, the identification information of the UWB tag, and the crossing direction.

[0122] During the competition, the UWB tags in the sports bracelets worn by athletes send pulse signals to the UWB base station 5 times per second. The UWB base station receives the pulse signals sent by each UWB tag and determines the time when each athlete passes the finish line. At the same time, the sports bracelets carried by athletes also report the wearer's heart rate, body temperature, blood oxygen, step count and other health data to the UWB base station, which is analyzed by the UWB base station and transmitted to the management platform. If the management platform finds abnormal data, it can send a motor vibration signal to the wearer of the sports bracelet to remind the wearer.

[0123] Through experiments, it is found that there is no missed report or false report when the line crossing detection is performed by the method of this embodiment. At the same time, when there is a lot of data, the delay can be guaranteed to be less than 10 seconds, and the accuracy of line crossing detection is significantly improved.

[0124] Exemplary devices and systems

[0125] refer to Figure 2 The present specification also provides a line-crossing detection device, including:

[0126] The first processing module 201 is used to determine the position sequence of the target detection object based on the time information of each pulse signal in the target pulse sequence received by at least two UWB base stations; wherein the target pulse sequence is sent by the UWB tag carried by the target detection object;

[0127] A second processing module 202, configured to fit a motion trajectory of the target detection object based on a position sequence of the target detection object, wherein the motion trajectory includes a motion path and a motion direction;

[0128] The third processing module 203 is used to determine the target position point among the position points of the position sequence based on the detection area corresponding to the target line and the motion path of the target detection object when the motion direction conforms to the preset motion direction; the target line includes the line to be detected for crossing the line, the detection area corresponding to the target line includes the target line and the area adjacent to the target line in the first area, the first area includes the area after passing the target line, and the target position point includes the position point representing the crossing moment of the target detection object;

[0129] The fourth processing module 204 is used to determine the time when the target detection object passes through the target line based on the signal sending time of the pulse signal corresponding to the target position point when the target position point exists.

[0130] In a feasible implementation manner, the first processing module 201 is specifically used for:

[0131] Based on the time information of each pulse signal in the target pulse sequence received by each UWB base station and the signal sending time of each pulse signal, at least one ranging sequence is determined; the ranging sequence includes the distance information between the target detection object and the UWB base station or the distance difference between the target detection object and the two UWB base stations at the signal sending time of each pulse signal;

[0132] Filtering is performed on each of the distance measurement sequences, and based on each of the distance measurement sequences after filtering, a position sequence of the target detection object is determined.

[0133] In a feasible implementation manner, the first processing module 201 is specifically used for:

[0134] Acquire target feature data of each data point in the ranging sequence; the data point includes a distance estimation value at the time when the signal is sent;

[0135] Based on the target feature data, determining the sorting information of the feature distance between the data point and each sample point in the preset data set; the sample point includes a distance measurement value at the sample position;

[0136] Determining a preset number of target points from each of the sample points based on sorting information of characteristic distances between the data point and each of the sample points;

[0137] Based on the distance measurement value corresponding to each of the target points, the target distance corresponding to the data point is determined, and the distance estimation value corresponding to the data point is updated to the target distance.

[0138] In a feasible implementation manner, the second processing module 202 is specifically configured to:

[0139] Based on the coordinate information of each position point in the position sequence of the target detection object, a consistent random sampling method is used to determine the movement path of the target detection object, and based on the coordinate information of each position point and the signal sending time of the pulse signal corresponding to each position point, the movement direction of the target detection object is determined.

[0140] In a feasible implementation manner, the third processing module 203 is specifically used for:

[0141] Acquire each position point in the position sequence of the target detection object whose distance from the motion path of the target detection object is less than a preset distance, and use them as candidate points;

[0142] The target position point is determined based on the coordinate information of each candidate point located in the detection area and / or the signal sending time of the corresponding pulse signal.

[0143] In a feasible embodiment, a fifth processing module is further included, wherein the fifth processing module is used to:

[0144] When the target position point does not exist, determining a first position point and a second position point based on the coordinate information of each of the candidate points; the first position point is located in the first area, the second position point is located in the second area, and the second area includes an area before passing the target line;

[0145] The time when the target detection object passes through the target line is determined based on the signal sending time of the pulse signal corresponding to the first position point and the signal sending time of the pulse signal corresponding to the second position point.

[0146] In a feasible implementation manner, the fifth processing module is specifically used for:

[0147] Based on the signal sending time of the pulse signal corresponding to the first position point, the signal sending time of the pulse signal corresponding to the second position point, the coordinate information of the first position point, the coordinate information of the second position point, and the coordinate information of the intersection of the motion path of the target detection object and the target line, the time when the target detection object passes through the target line is determined by interpolation.

[0148] The line-crossing detection device provided in this embodiment belongs to the same application concept as the line-crossing detection method provided in the above embodiments of this application, and can execute the line-crossing detection method provided in any of the above embodiments of this application, and has the corresponding functional modules and beneficial effects of executing the line-crossing detection method. For technical details not fully described in this embodiment, please refer to the specific processing content of the line-crossing detection method provided in the above embodiments of this application, and will not be repeated here.

[0149] refer to Figure 3 The present specification also provides a line crossing detection system, including: a controller ( Figure 3 (not shown), at least two UWB base stations 301 and at least one UWB tag 302; the UWB tag 302 is used to carry to the target detection object;

[0150] The UWB tag 302 is used to send a target pulse sequence to each of the UWB base stations 301, and feed back the signal sending time of each pulse signal in the target pulse sequence to the controller;

[0151] The UWB base station 301 is used for feeding back the time information of receiving each pulse signal in the target pulse sequence to the controller when receiving the target pulse sequence;

[0152] The controller includes at least one processor and at least one memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the line crossing detection method as described in any of the above embodiments is implemented.

[0153] The controller may be a computing device in any one of the at least two UWB base stations 301, each UWB base station 301 may be connected by wire or wirelessly, and the UWB tag may be wirelessly connected to each UWB base station 301. The UWB base station 301 may be arranged at the target line 303, and the crossing time of the target detection object may be determined according to the time when the target detection object is located in the detection area 304 corresponding to the target line 303.

[0154] The controller can also be connected to the management platform and send the line crossing detection data of each target detection object to the management platform. At the same time, the UWB tag 302 can be set in a sports bracelet and send the status data of the target detection object collected by the sports bracelet (such as heart rate, body temperature, blood oxygen, step counting and other health data) to the management platform.

[0155] Exemplary computer program products and storage media

[0156] In addition to the above-mentioned methods and devices, the line crossing detection method provided in the embodiments of this specification may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the line crossing detection method according to various embodiments of this specification described in the above "Exemplary Method" section of this specification.

[0157] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the embodiments of the present specification, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0158] In addition, an embodiment of the present specification also provides a computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to execute the steps of the line crossing detection method according to various embodiments of the present specification described in the above "Exemplary Method" section of the present specification.

[0159] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this specification can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0160] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0161] The above-mentioned embodiments only express several implementation methods of this specification, and the descriptions are relatively specific and detailed, but they cannot be understood as limiting the scope of the solutions provided by the embodiments of this specification. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of this specification, which all belong to the protection scope of this specification. Therefore, the protection scope of the patent of this specification shall be based on the attached claims.

Claims

1. A line crossing detection method, characterized in that: include: Determine the position sequence of the target detection object based on the time information of each pulse signal in the target pulse sequence received by at least two UWB base stations; wherein the target pulse sequence is sent by the UWB tag carried by the target detection object; Fitting a motion trajectory of the target detection object based on a position sequence of the target detection object, wherein the motion trajectory includes a motion path and a motion direction; When the motion direction conforms to the preset motion direction, a target position point among the position points of the position sequence is determined based on the detection area corresponding to the target line and the motion path of the target detection object; the target line includes a line to be subjected to line crossing detection, the detection area corresponding to the target line includes the target line and an area in a first area adjacent to the target line, the first area includes an area after passing the target line, and the target position point includes a position point representing a moment when the target detection object crosses the line; When the target position point exists, the time when the target detection object passes through the target line is determined based on the signal sending time of the pulse signal corresponding to the target position point.

2. The method according to claim 1, characterized in that The determining of the position sequence of the target detection object based on the time information of each pulse signal in the target pulse sequence received by at least two UWB base stations includes: Based on the time information of each pulse signal in the target pulse sequence received by each UWB base station and the signal sending time of each pulse signal, at least one ranging sequence is determined; the ranging sequence includes the distance information between the target detection object and the UWB base station or the distance difference between the target detection object and the two UWB base stations at the signal sending time of each pulse signal; Filtering is performed on each of the distance measurement sequences, and based on each of the distance measurement sequences after filtering, a position sequence of the target detection object is determined.

3. The method according to claim 2, characterized in that The filtering process is performed on the ranging sequence, comprising: Acquire target feature data of each data point in the ranging sequence; the data point includes a distance estimation value at the time when the signal is sent; Based on the target feature data, determining the sorting information of the feature distance between the data point and each sample point in the preset data set; the sample point includes a distance measurement value at the sample position; Determining a preset number of target points from each of the sample points based on sorting information of characteristic distances between the data point and each of the sample points; Based on the distance measurement value corresponding to each of the target points, the target distance corresponding to the data point is determined, and the distance estimation value corresponding to the data point is updated to the target distance.

4. The method according to claim 1, characterized in that The step of fitting the motion trajectory of the target detection object based on the position sequence of the target detection object comprises: Based on the coordinate information of each position point in the position sequence of the target detection object, a consistent random sampling method is used to determine the movement path of the target detection object, and based on the coordinate information of each position point and the signal sending time of the pulse signal corresponding to each position point, the movement direction of the target detection object is determined.

5. The method according to any one of claims 1 to 4, characterized in that: The step of determining the target position point among the position points in the position sequence based on the detection area corresponding to the target line and the motion path of the target detection object includes: Acquire each position point in the position sequence of the target detection object whose distance from the motion path of the target detection object is less than a preset distance, and use them as candidate points; The target position point is determined based on the coordinate information of each candidate point located in the detection area and / or the signal sending time of the corresponding pulse signal.

6. The method according to claim 5, characterized in that Also includes: When the target location point does not exist, determining a first location point and a second location point based on coordinate information of each of the candidate points; The first position point is located in the first area, the second position point is located in a second area, and the second area includes an area before passing the target line; The time when the target detection object passes through the target line is determined based on the signal sending time of the pulse signal corresponding to the first position point and the signal sending time of the pulse signal corresponding to the second position point.

7. The method according to claim 6, characterized in that The determining the time when the target detection object passes through the target line based on the signal sending time of the pulse signal corresponding to the first position point and the signal sending time of the pulse signal corresponding to the second position point includes: Based on the signal sending time of the pulse signal corresponding to the first position point, the signal sending time of the pulse signal corresponding to the second position point, the coordinate information of the first position point, the coordinate information of the second position point, and the coordinate information of the intersection of the motion path of the target detection object and the target line, the time when the target detection object passes through the target line is determined by interpolation.

8. A line-crossing detection device, characterized in that: include: A first processing module, configured to determine a position sequence of a target detection object based on time information of each pulse signal in a target pulse sequence received by at least two UWB base stations; wherein the target pulse sequence is sent by a UWB tag carried by the target detection object; A second processing module, configured to fit a motion trajectory of the target detection object based on a position sequence of the target detection object, wherein the motion trajectory includes a motion path and a motion direction; A third processing module is used to determine, when the motion direction conforms to a preset motion direction, a target position point among the position points of the position sequence based on a detection area corresponding to a target line and a motion path of the target detection object; the target line includes a line to be subjected to line crossing detection, the detection area corresponding to the target line includes the target line and an area in a first area adjacent to the target line, the first area includes an area after passing through the target line, and the target position point includes a position point representing a moment when the target detection object crosses the line; The fourth processing module is used to determine the time when the target detection object passes through the target line based on the signal sending time of the pulse signal corresponding to the target position point when the target position point exists.

9. A line crossing detection system, characterized in that: include: A controller, at least two UWB base stations and at least one UWB tag; The UWB tag is used to be carried to the target detection object; The UWB tag is used to send a target pulse sequence to each of the UWB base stations, and feed back the signal sending time of each pulse signal in the target pulse sequence to the controller; The UWB base station is used for feeding back the time information of receiving each pulse signal in the target pulse sequence to the controller when receiving the target pulse sequence; The controller includes at least one processor and at least one memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the line crossing detection method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the line crossing detection method according to any one of claims 1 to 7 is implemented.

Images