Methods, devices, electronic equipment and media for boundary crossing detection

Abstract

This disclosure relates to a method, apparatus, electronic device, and medium for boundary crossing detection, applicable to the field of surveillance data processing. The boundary crossing detection method includes: acquiring electronic fence data corresponding to a monitored area or object; determining the inflection points of the electronic fence based on the electronic fence data; dividing the electronic fence into regions based on the inflection points to obtain polygonal regions after division; wherein the interior of the divided electronic fence contains at least one convex polygon; determining the relative position of the detection point to the electronic fence based on the divided polygonal regions; and generating a boundary crossing detection result of the detection point relative to the electronic fence based on the relative position. This method can improve the accuracy of the generated boundary crossing detection result, reduce errors in predicting the positional relationship of detection points for electronic fences with complex shapes, and, since the method is applicable to the determination of electronic fences of various shapes, it has a wide range of applications and good versatility.

Description

Technical Field

[0001] This disclosure relates to the field of surveillance data processing, and in particular to a method, apparatus, electronic device, and medium for boundary crossing detection. Background Technology

[0002] With the development of intelligent monitoring technology, electronic fence zones are set up within the monitored area to provide early warnings when other objects intrude into the monitored area. This requires accurate detection and determination of the relative position of the object to the monitored area. Generally, when processing electronic fence data offline (non-real-time) or online, the boundary of the area corresponding to the electronic fence is abstracted as a polygon, and then the relative positional relationship between the detection point and the electronic fence is determined based on the ray casting method.

[0003] In realizing the concept disclosed herein, the inventors discovered at least the following technical problems in the related technology: depending on different monitoring needs, the shape of the electronic fence area may be relatively complex, such as the shape of the electronic fence containing curved edges, the shape of the electronic fence containing self-intersecting polygons, etc. Using the ray method to detect the relative position of these complex shapes may result in errors in judgment in some cases, leading to errors in the monitoring results. Summary of the Invention

[0004] To solve the above-mentioned technical problems, or at least partially solve them, embodiments of this disclosure provide a method, apparatus, electronic device, and medium for boundary crossing detection.

[0005] In a first aspect, embodiments of this disclosure provide a method for boundary crossing detection. The method includes: acquiring electronic fence data corresponding to a monitored area or monitored object; determining inflection points of the electronic fence based on the electronic fence data; dividing the electronic fence into regions based on the inflection points to obtain a divided polygonal region; wherein the interior of the divided electronic fence contains at least one convex polygon; determining the relative position of a detection point to the electronic fence based on the divided polygonal region; and generating a boundary crossing detection result of the detection point relative to the electronic fence based on the relative position.

[0006] According to an embodiment of this disclosure, when there are multiple cut polygonal regions, determining the relative position of the detection point and the electronic fence based on the cut polygonal regions includes: determining the centroid position of each polygonal region among the multiple polygonal regions; determining the polygonal region whose centroid position is closest to the detection point as the target polygonal region based on the distance between the centroid position and the detection point; and determining a first relative position between the detection point and the target polygonal region, wherein the first relative position is used as the relative position between the detection point and the electronic fence.

[0007] According to embodiments of this disclosure, the aforementioned relative position includes one of the following: the detection point is located inside the electronic fence, the detection point is located at the boundary of the electronic fence, or the detection point is located outside the electronic fence. Based on the aforementioned relative position, generating a boundary crossing detection result for the detection point relative to the electronic fence includes: generating a boundary crossing detection result for the detection point relative to the electronic fence based on the aforementioned relative position and boundary crossing setting conditions; the boundary crossing setting conditions are used to indicate that the detection point is in a boundary crossing state when it is at a target relative position; the target relative position is one of the following: the detection point is located inside the electronic fence, the detection point is located at the boundary of the electronic fence, the detection point is located outside the electronic fence, the detection point is located both inside and at the boundary of the electronic fence, or the detection point is located both outside and at the boundary of the electronic fence.

[0008] According to embodiments of this disclosure, for electronic fences with shapes that are self-intersecting polygons, concave-convex fusion polygons, concave-convex nested polygons, or contain curved outlines, the polygonal regions obtained after region segmentation include the following two types: convex polygons with three or more sides composed of straight lines, and closed shapes containing two or more sides of curves.

[0009] According to embodiments of this disclosure, the electronic fence is divided into regions based on the aforementioned inflection points to obtain segmented polygonal regions. This includes: connecting adjacent inflection points with straight lines to obtain a first polygonal region and a second polygonal region after region segmentation; the first polygonal region is a convex polygon with three or more sides formed by straight lines; the second polygonal region includes curves and is a closed shape with two or more sides; or, the electronic fence is divided into regions based on a first connecting line between the inflection point and the concave point and the concave point of the electronic fence to obtain a third polygonal region and a fourth polygonal region; the third polygonal region is a convex polygon with three or more sides formed by straight lines; the fourth polygonal region includes curves and is a closed shape with two or more sides. The electronic fence can be divided into a fifth polygonal region and a sixth polygonal region based on the second connecting line between adjacent inflection points and the concave point of the electronic fence. The fifth polygonal region is a convex polygon with three or more sides formed by straight lines. The sixth polygonal region contains curves and is a closed figure with two or more sides. Alternatively, the electronic fence can be divided into a seventh polygonal region and an eighth polygonal region based on the first connecting line between the inflection point and the concave point, the second connecting line between adjacent inflection points, and the concave point of the electronic fence. The seventh polygonal region is a convex polygon with three or more sides formed by straight lines. The eighth polygonal region contains curves and is a closed figure with two or more sides.

[0010] According to embodiments of this disclosure, the electronic fence is divided into third and fourth polygonal regions based on a first connecting line between an inflection point and a concave point and the concave point of the electronic fence. This includes: extending the first connecting line between an inflection point and an adjacent concave point to intersect with the boundary of the electronic fence to obtain a first intersection point; and connecting the first intersection point, the concave point, and the inflection point to obtain multiple third and fourth polygonal regions. The electronic fence is also divided into fifth and sixth polygonal regions based on a second connecting line between adjacent inflection points and the concave point of the electronic fence. This includes: connecting the midpoint of the second connecting line between adjacent inflection points to the opposite concave point and extending it to intersect with the boundary of the electronic fence to obtain a second intersection point; and connecting the second intersection point, the concave point, and the inflection point to obtain multiple fifth and sixth polygonal regions. The electronic fence is divided into seventh and eighth polygonal regions based on the first connecting line between the inflection point and the concave point, the second connecting line between adjacent inflection points, and the concave point of the electronic fence. This includes: extending the first connecting line between the inflection point and the adjacent concave point to intersect with the boundary of the electronic fence to obtain a first intersection point; connecting the midpoint of the second connecting line between adjacent inflection points to the opposite concave point and extending it to intersect with the boundary of the electronic fence to obtain a second intersection point; and connecting the first intersection point, the second intersection point, the concave point, and the inflection point to obtain multiple seventh polygonal regions and multiple eighth polygonal regions.

[0011] According to embodiments of this disclosure, the boundary crossing detection method further includes: detecting whether a self-intersection point exists; if a self-intersection point exists, dividing the electronic fence into multiple discrete regions based on the self-intersection point. Specifically, dividing the electronic fence into regions based on the inflection point to obtain a divided polygonal region includes: for each of the multiple divided discrete regions, dividing the current discrete region into regions based on the inflection point to obtain a divided polygonal region.

[0012] According to an embodiment of this disclosure, determining the inflection point of an electronic fence based on the aforementioned electronic fence data includes: if the electronic fence data contains inflection point location identifiers, determining the location carrying the inflection point location identifier as the inflection point of the electronic fence; if the electronic fence data does not contain inflection point location identifiers, calculating the curvature of each location in the electronic fence based on the aforementioned electronic fence data; and determining the inflection point of the electronic fence based on the aforementioned curvature.

[0013] Secondly, embodiments of this disclosure provide an apparatus for boundary crossing detection. The apparatus includes: a fence data acquisition module, an inflection point determination module, a region cutting module, a position determination module, and a result generation module. The fence data acquisition module is used to acquire electronic fence data corresponding to a monitored area or monitored object. The inflection point determination module is used to determine the inflection points of the electronic fence based on the electronic fence data. The region cutting module is used to cut the electronic fence region based on the inflection points to obtain a cut polygonal region; wherein the interior of the cut electronic fence contains at least one convex polygon. The position determination module is used to determine the relative position of the detection point and the electronic fence based on the cut polygonal region. The result generation module is used to generate a boundary crossing detection result of the detection point relative to the electronic fence based on the relative position.

[0014] Thirdly, embodiments of this disclosure provide an electronic device. The electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, communication interface, and memory communicate with each other via the communication bus; the memory stores computer programs; and the processor, when executing the program stored in the memory, implements the out-of-bounds detection method as described above.

[0015] Fourthly, embodiments of this disclosure provide a computer-readable storage medium. The computer-readable storage medium stores a computer program that, when executed by a processor, implements the out-of-bounds detection method as described above.

[0016] The technical solutions provided in the embodiments of this disclosure have at least some or all of the following advantages:

[0017] By acquiring the electronic fence data corresponding to the monitored area or object, the electronic fence corresponding to the data is used to indicate the boundary of the spatial range and is a closed shape. Based on the electronic fence data, the inflection points of the electronic fence are determined. Based on the inflection points, the area of ​​the electronic fence is divided to obtain the cut polygonal area. By dividing the area of ​​the electronic fence based on the inflection points, the interior of electronic fences of various shapes can be divided into one or more convex polygons. Subsequently, in the process of determining the relative position of the detection point and the electronic fence based on the cut polygonal area, the relative position determination can be performed with high accuracy by the position detection method of the convex polygon. This can improve the accuracy of the generated boundary detection results, reduce the error in predicting the position relationship of the detection point for electronic fences with complex shapes, and since the above method is applicable to the determination of electronic fences of various shapes, it has a wide range of applications and good versatility. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0019] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0020] Figure 1 The system architecture of a method for boundary detection applicable to embodiments of this disclosure is illustrated schematically;

[0021] Figure 2 A flowchart illustrating a method for boundary detection according to an embodiment of the present disclosure is shown schematically.

[0022] Figure 3 A schematic diagram illustrating the calculation of the curvature of various points in an electronic fence based on electronic fence data according to an embodiment of the present disclosure is shown.

[0023] Figure 4 A schematic diagram illustrating the determination of the inflection point of an electronic fence based on curvature according to an embodiment of the present disclosure is shown.

[0024] Figure 5A The illustration schematically shows an electronic fence area segmentation based on inflection points according to an embodiment of the present disclosure, resulting in a segmented polygonal region, and a first relative position of the detection point X1 and the target polygonal region determined based on the centroid-based ray method.

[0025] Figure 5B The diagram illustrates an embodiment of the present disclosure of cutting an area of ​​an electronic fence based on an inflection point to obtain a cut polygonal region and determining the first relative position of the detection point X2 and the target polygonal region based on a ray method using the centroid.

[0026] Figure 6 A flowchart illustrating a method for boundary detection according to another embodiment of this disclosure is shown schematically;

[0027] Figure 7 The diagram illustrates the misjudgment effect of using the conventional ray method to determine relative position in the related technology; where (a) is a diagram of the misjudgment effect for self-intersecting polygons, and (b) is a diagram of the misjudgment effect for concave polygons containing curved contours.

[0028] Figure 8AThis diagram schematically illustrates the effect of a method for determining the boundary detection of an electronic fence with a concave polygonal curve profile according to an embodiment of the present disclosure.

[0029] Figure 8B This schematically illustrates another effect of the method for boundary detection provided in this disclosure for determining the electronic fence of a concave polygon with a curved profile.

[0030] Figure 9 A schematic block diagram of a boundary detection apparatus according to an embodiment of the present disclosure is shown.

[0031] Figure 10 A schematic block diagram of an electronic device provided in an embodiment of the present disclosure is shown. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0033] Figure 1 The system architecture of the out-of-bounds detection method applicable to embodiments of this disclosure is illustrated schematically.

[0034] Reference Figure 1 As shown, the system architecture 100 of the boundary detection method applicable to embodiments of this disclosure includes: terminal devices 101, 102, and 103, a network 104, and a server 105. The network 104 is a medium providing a communication link between the terminal devices 101, 102, and 103 and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0035] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Monitoring applications can be installed on terminal devices 101, 102, and 103, or the terminal devices themselves can be monitoring devices.

[0036] Terminal devices 101, 102, and 103 can be various electronic devices, including but not limited to the following: monitoring equipment, smartphones, tablets, laptops, desktop computers, intelligent robots, etc.

[0037] Server 105 can be a server that provides various services, such as a backend management server that provides data processing support for monitoring images or videos captured by users using terminal devices 101, 102, and 103 (this is just an example). The backend management server can perform data analysis and processing on the received monitoring image or video processing requests, and feed back the processing results (such as the boundary detection results) to the terminal devices.

[0038] It should be noted that the boundary detection method provided in this embodiment can generally be executed by server 105 or a terminal device with a certain computing power. Correspondingly, the boundary detection device provided in this embodiment can generally be located in server 105 or the aforementioned terminal device with a certain computing power. The boundary detection method provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with at least one of terminal devices 101, 102, 103 and server 105. Correspondingly, the boundary detection device provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with at least one of terminal devices 101, 102, 103 and server 105.

[0039] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0040] The first exemplary embodiment of this disclosure provides a method for boundary detection.

[0041] Figure 2 A flowchart illustrating a method for boundary detection according to an embodiment of the present disclosure is shown schematically.

[0042] Reference Figure 2 As shown, the boundary detection method provided in this embodiment includes the following steps: S210, S220, S230, S240 and S250.

[0043] In step S210, the electronic fence data corresponding to the monitored area or monitored object is obtained.

[0044] In some application scenarios, it is necessary to monitor certain designated areas and issue warnings if an object illegally enters. For example, in the scenario of guarding a smart warehouse, intelligent algorithms can be used to identify unauthorized objects entering the area. By delineating an electronic fence area as the guarded zone, when an unidentified object or unauthorized living person touches or enters the area, video is automatically saved and an alarm is issued.

[0045] In some application scenarios, it is necessary to monitor the activity range of the monitored object. If the activity range of the monitored object exceeds the set area, an early warning will be issued. In this case, an electronic fence can be generated based on the boundary of the activity range of the monitored object.

[0046] In the embodiments of this disclosure, the electronic fence corresponding to the electronic fence data is used to indicate the boundary of a spatial range, and the electronic fence is a closed graphic. The aforementioned electronic fence data may contain data including multiple boundary contour points. It can be generated from the outline of an area selected by the user on an electronic map, or it can be generated based on the latitude and longitude points corresponding to the boundary of the monitored area or the activity range of the monitored object measured in actual space. In some embodiments, to improve accuracy, marker point data or inflection point markers may be added.

[0047] In some embodiments, the electronic fence data may also be preprocessed, such as by filtering data outside the latitude and longitude range corresponding to the electronic fence, empty points, and single missing points.

[0048] In step S220, the inflection point of the electronic fence is determined based on the above electronic fence data.

[0049] In some embodiments, in step S220 above, determining the inflection point of the electronic fence based on the electronic fence data includes:

[0050] If the above electronic fence data includes inflection point markers, the points carrying inflection point markers will be identified as inflection points of the electronic fence.

[0051] If the above electronic fence data does not include inflection point markers, calculate the curvature of each point in the electronic fence based on the above electronic fence data; determine the inflection points of the electronic fence based on the above curvature.

[0052] Figure 3 A schematic diagram illustrating the calculation of the curvature of various points in an electronic fence based on electronic fence data according to an embodiment of the present disclosure is shown. Figure 4 A schematic diagram illustrating the determination of the inflection point of an electronic fence based on curvature according to an embodiment of the present disclosure is shown.

[0053] For example, refer to Figure 3 As shown, an example is an electronic fence with a self-intersecting shape and a curved profile. A coordinate system can be constructed based on the values ​​of each boundary profile point in the electronic fence data, and the graphic of the electronic fence can be generated in the coordinate system; the curvature of each point in the electronic fence can be calculated.

[0054] The expression for curvature is: curvature = |dθ / ds|, (1)

[0055] Where θ represents the angle between the tangent to the curve and the positive x-axis, s represents the arc length of the curve, dθ represents the derivative of θ, and ds represents the derivative of s. Therefore, curvature can be understood as the rate at which the tangent to the curve turns at a certain point, that is, the degree of curvature of the curve at that point.

[0056] In polygons, curves are composed of a series of line segments, therefore the curvature formula needs to be discretized. Assuming the polygon's boundary consists of n points, the line segment between every two adjacent points can be considered a curve, and the curvature value can be calculated for each segment. Specifically, for the line segment between the i-th point and the (i+1)-th point, the curvature value of that segment can be calculated, as shown in the following expression:

[0057] Curvature[i]=|θ[i+1]-θ[i]| / |s[i+1]-s[i]|, (2)

[0058] Where θ[i] represents the angle between the tangent at the i-th point and the positive x-axis, and s[i] represents the arc length from the i-th point to the starting point.

[0059] When the curvature value at a certain point exceeds a set threshold, that point can be considered an inflection point. For example, refer to... Figure 4 As shown, for an electronic fence with a self-intersecting shape and a curved profile, the inflection points obtained are site A, site B, site C, and site D.

[0060] In step S230, the area of ​​the electronic fence is cut according to the inflection point to obtain the cut polygonal area; wherein the interior of the cut electronic fence contains at least one convex polygon.

[0061] In some embodiments, for electronic fences that are self-intersecting polygons, concave-convex fusion polygons, concave-convex nested polygons, or contain curved outlines, the polygonal regions obtained after region segmentation include the following two types: convex polygons with three or more sides composed of straight lines, and closed shapes with two or more sides containing curves.

[0062] By detecting the inflection points of the fence edge, the edge and interior are separated, enabling effective boundary detection for curved edge fences. Furthermore, by cutting the interior of the fence into multiple triangles (as an example of a convex polygon), boundary detection for non-ordinary polygons (such as self-intersecting, concave-convex fused, or nested concave-convex polygons) can be effectively performed.

[0063] Figure 5A The illustration schematically shows an electronic fence area segmentation based on inflection points according to an embodiment of the present disclosure, resulting in a segmented polygonal region, and a first relative position of the detection point X1 to the target polygonal region determined by a ray method based on the centroid. Figure 5B The diagram schematically illustrates an embodiment of the present disclosure of an electronic fence region segmentation based on inflection points to obtain a segmented polygonal region and a first relative position of the detection point X2 to the target polygonal region determined by a ray method based on the centroid.

[0064] For example, refer to Figure 5A and Figure 5B As shown, the electronic fence area is divided according to inflection points A to D, resulting in a polygonal region. In this embodiment, since a self-intersecting polygon corresponding to the electronic fence is used, the electronic fence is first divided based on the self-intersection point J during area division, resulting in two separate regions. The division process is described in reference [reference needed]. Figure 4 As shown by the dashed line. Based on the aforementioned inflection points, the electronic fence area is divided to obtain the resulting polygonal regions. This includes: for each of the multiple discrete regions after division, the current discrete region is divided according to the aforementioned inflection points to obtain the resulting polygonal regions. For example, the eight polygonal regions obtained after division in Figure 5 are: a triangle formed by inflection point A, inflection point B, and self-intersection point J (belonging to the category of convex polygons with three or more sides formed by straight lines); a triangle formed by inflection point C, inflection point D, and self-intersection point J (belonging to the category of convex polygons with three or more sides formed by straight lines); a closed figure formed by arc AJ and straight line AJ (belonging to the category of closed figures containing two or more sides of a curve); and a closed figure formed by arc AB and straight line AB (belonging to the category of closed figures containing two or more sides of a curve). The following are examples of closed figures: figures with two or more sides; closed figures consisting of arc BJ and straight line BJ (belonging to the category of closed figures with two or more sides containing curves); closed figures consisting of arc CJ and straight line CJ (belonging to the category of closed figures with two or more sides containing curves); closed figures consisting of arc CD and straight line CD (belonging to the category of closed figures with two or more sides containing curves); and closed figures consisting of arc DJ and straight line DJ (belonging to the category of closed figures with two or more sides containing curves).

[0065] In other embodiments, if the shape of the electronic fence is not self-intersecting, then the division of discrete regions can be carried out without considering the self-intersection points during the region segmentation process.

[0066] In step S240, the relative position of the detection site and the electronic fence is determined based on the cut polygonal region.

[0067] In some application scenarios, for a monitored area, the detection point can be the real-time location of an object being identified near or within the monitored area. For a monitored object, the detection point can be the real-time location of the monitored object.

[0068] According to an embodiment of this disclosure, in step S250 above, when there are multiple cut polygonal regions, determining the relative position of the detection point and the electronic fence based on the cut polygonal regions includes: determining the centroid position of each polygonal region among the multiple polygonal regions; determining the polygonal region whose centroid position is closest to the detection point as the target polygonal region based on the distance between the centroid position and the detection point; and determining a first relative position between the detection point and the target polygonal region, wherein the first relative position is used as the relative position between the detection point and the electronic fence.

[0069] For example, refer to Figure 5A and Figure 5B As shown, black dots indicate the centroid positions of the various polygonal regions after cutting. (Refer to...) Figure 5A As shown, for detection point X1, since the centroid closest to detection point X1 is the centroid of the closed shape formed by arc CJ and straight line CJ, the closed shape formed by arc CJ and straight line CJ is taken as the target polygonal region. Based on the ray method passing through the centroid, the first relative position between the detection point and the target polygonal region is determined. For example, starting from detection point X1, a ray is drawn through the centroid. The number of intersections with the closed shape (target polygonal region) formed by arc CJ and straight line CJ is 2, which is an even number. The resulting first relative position is: the detection point is located outside the target polygonal region. This result is taken as the relative position between detection point X1 and the electronic fence.

[0070] Reference Figure 5B As shown, for detection point X2, since the centroid closest to detection point X2 is a triangle formed by inflection point C, inflection point D, and self-intersection point J, this triangle is taken as the target polygonal region. Based on the ray method passing through the centroid, the first relative position between the detection point and the target polygonal region is determined. For example, starting from detection point X2, a ray is drawn through the centroid. The number of intersections with the triangle formed by inflection point C, inflection point D, and self-intersection point J (target polygonal region) is 1, which is an odd number. The resulting first relative position is: the detection point is located within the target polygonal region. This result is taken as the relative position between detection point X2 and the electronic fence.

[0071] In other embodiments, if the detection point is located on the boundary of the segmented polygonal region, it can be directly identified based on the relationship between the coordinates of the detection point and the boundary equation of the polygonal region.

[0072] In step S250, based on the aforementioned relative positions, a boundary crossing detection result of the aforementioned detection site relative to the aforementioned electronic fence is generated.

[0073] According to embodiments of this disclosure, the aforementioned relative positions include one of the following: the detection point is located inside the electronic fence, the detection point is located at the boundary of the electronic fence, or the detection point is located outside the electronic fence.

[0074] In step S250 above, generating a boundary crossing detection result of the detection point relative to the electronic fence based on the relative position includes: generating a boundary crossing detection result of the detection point relative to the electronic fence based on the relative position and boundary crossing setting conditions. The boundary crossing setting conditions are used to indicate that the detection point is in a boundary crossing state when it is in a target relative position; the target relative position is one of the following: the detection point is located inside the electronic fence, the detection point is located at the boundary of the electronic fence, the detection point is located outside the electronic fence, the detection point is located inside and at the boundary of the electronic fence, and the detection point is located outside and at the boundary of the electronic fence.

[0075] For example, the boundary crossing condition is: the detection location is outside the electronic fence; when the relative position indicates that the detection point is outside the electronic fence, the generated boundary crossing detection result is: the detection point has crossed the boundary; when the relative position indicates that the detection point is inside the electronic fence or at the boundary, the generated boundary crossing detection result is: the detection point has not crossed the boundary.

[0076] In embodiments including steps S210 to S250, electronic fence data corresponding to the monitored area or monitored object is obtained. The electronic fence corresponding to the electronic fence data is used to indicate the boundary of the spatial range and is a closed shape. Based on the electronic fence data, the inflection point of the electronic fence is determined. Based on the inflection point, the area of ​​the electronic fence is cut to obtain the cut polygonal area. By cutting the area of ​​the electronic fence based on the inflection point, the interior of electronic fences of various shapes can be divided into one or more convex polygons. Subsequently, in the process of determining the relative position of the detection point and the electronic fence based on the cut polygonal area, the relative position determination can be performed by the method of position detection of convex polygons with high accuracy. This can improve the accuracy of the generated boundary detection results, reduce the error in predicting the position relationship of detection points for electronic fences of complex shapes, and since the above method is applicable to the determination of electronic fences of various shapes, it has a wide range of applications and good versatility.

[0077] Figure 6 A flowchart of a method for boundary detection according to another embodiment of this disclosure is illustrated schematically.

[0078] In some embodiments, refer to Figure 6 As shown, the boundary crossing detection method, in addition to steps S210 to S250 described above, also includes the following steps: S610 and S620. Steps S610 and S620 are performed before step S230.

[0079] In step S610, the existence of self-intersections is detected.

[0080] For example, in some embodiments, the detection method is as follows: establish a coordinate axis based on the electronic fence data; determine all the inflection points of the electronic fence; draw a ray from the inflection point of the lowest point of the electronic fence to the X-axis; move the ray from low to high in sequence and record the position and number of intersection points with the electronic fence; if there is a unique intersection point and the intersection point is neither the highest nor the lowest inflection point, it indicates that there is a self-intersection, and the unique intersection point is a self-intersection point.

[0081] In step S620, if self-intersections exist, the electronic fence is divided into multiple separate areas based on these self-intersections. For example, refer to Figure 4, where a dashed line passing through a self-intersection is used to illustrate dividing the electronic fence into two separate areas.

[0082] In step S230 above, the electronic fence area is divided according to the inflection point to obtain the divided polygonal area, including step S230a: for each of the multiple discrete areas after division, the current discrete area is divided according to the inflection point to obtain the divided polygonal area. For example, after dividing each discrete area, the following is obtained: Figure 5A and Figure 5B The diagram shows eight polygonal regions.

[0083] Figure 7 The diagram illustrates the misjudgment effect of using the conventional ray method for relative position determination in related technologies; where (a) is a schematic diagram of the misjudgment effect for self-intersecting polygons, and (b) is a schematic diagram of the misjudgment effect for concave polygons with curved contours.

[0084] Reference Figure 7 As shown in (a), for electronic fences with self-intersecting polygons (such as the butterfly shape in the example), the related technology uses the traditional ray method to determine the relative position. A ray is drawn from the detection point α. After the ray passes through the self-intersecting point α, the number of intersections with the electronic fence is 1, which is an odd number. This is considered to mean that the detection point α is inside the electronic fence. However, in reality, the detection point α is outside the electronic fence, resulting in a misjudgment.

[0085] In contrast, in the embodiments of this disclosure, by setting steps S610 to S620, determining whether the electronic fence contains self-intersections and dividing it into multiple discrete regions if self-intersections exist, and then cutting each discrete region, the accuracy of determining the relative positional relationship of the electronic fence for self-intersection polygons can be effectively improved.

[0086] Figure 8AThis diagram schematically illustrates the effect of a method for determining the boundary detection of an electronic fence with a concave polygonal curve profile according to an embodiment of the present disclosure. Figure 8B This schematically illustrates another effect diagram of the method for determining the boundary detection of an electronic fence with a concave polygonal curved profile according to an embodiment of the present disclosure.

[0087] As another comparative embodiment, refer to Figure 7 As shown in (b), for electronic fences with concave polygons containing curved contours, the relevant technology uses the traditional ray method to determine the relative position. A ray is drawn from the detection point α. The ray passes through point b on the line connecting one inflection point E and the concave point M and another inflection point F. The number of intersections with the electronic fence is 2, namely b and F, which is an even number. The detection point α is considered to be outside the electronic fence. However, in reality, the detection point α is inside the electronic fence, resulting in a misjudgment.

[0088] In contrast, in the embodiments of this disclosure, reference is made to... Figure 8A and Figure 8B As shown, for an electronic fence containing a concave polygon with a curved profile, by executing steps S210 to S250, the result that the detection point X3 is located within the electronic fence is obtained, which is a correct position determination result.

[0089] In some embodiments, step S230 above, which involves dividing the electronic fence region based on the inflection points to obtain a divided polygonal region, includes: connecting adjacent inflection points with straight lines to obtain a first polygonal region and a second polygonal region after region division; the first polygonal region is a convex polygon with three or more sides formed by straight lines; the second polygonal region contains curves and is a closed shape with two or more sides. For example, in some embodiments, only... Figure 4 In the example figure, half of the figure is divided into two parts. The corresponding self-intersection points change to inflection points. Connect the adjacent inflection points A and B with straight lines, connect the adjacent inflection points B and J with straight lines, and connect the adjacent inflection points J and A with straight lines. This results in the following four divided polygonal regions: triangle ABJ (the first polygonal region), a closed figure formed by arc AB and line AB (the second polygonal region), a closed figure formed by arc AJ and line AJ (the second polygonal region), and a closed figure formed by arc BJ and line BJ (the second polygonal region).

[0090] In some other embodiments, in step S230 above, the area of ​​the electronic fence is cut according to the inflection point to obtain the cut polygonal area, including: dividing the area of ​​the electronic fence according to the first connecting line between the inflection point and the concave point and the concave point of the electronic fence to obtain a third polygonal area and a fourth polygonal area; the third polygonal area is a convex polygon with three or more sides composed of straight lines; the fourth polygonal area contains curves and is a closed figure with two or more sides.

[0091] According to an embodiment of this disclosure, the electronic fence is divided into third polygonal regions and fourth polygonal regions based on the first connecting line between the inflection point and the concave point and the concave point of the electronic fence. This includes: extending the first connecting line between the inflection point and the adjacent concave point to intersect with the boundary of the electronic fence to obtain a first intersection point; and connecting the first intersection point, the concave point and the inflection point to obtain multiple third polygonal regions and multiple fourth polygonal regions.

[0092] For example, refer to Figure 8A As shown, the first connecting line between inflection point E and concave point M is extended to intersect the boundary of the aforementioned electronic fence, resulting in the first intersection point K11. The first connecting line between inflection point F and concave point M is extended to intersect the boundary of the aforementioned electronic fence, resulting in the first intersection point K12. Based on the first intersection points K11 and K12, concave point M, and inflection points E and F, the following three triangular regions (as examples of the third polygonal region) are obtained: the triangle formed by EM-K12, the triangle formed by MF-K11, and the triangle formed by M-K11-K12. The following three closed regions (as examples of the fourth polygonal region) are also obtained: the closed figure formed by line E-K12 and arc E-K12, the closed figure formed by line K11-K12 and arc K11-K12, and the closed figure formed by line K11-F and arc K11-F. After segmenting the polygonal regions, the target polygonal region closest to the test site X3 can be determined as the triangle formed by EM-K12 based on the centroid position. Starting from the test site X3, a ray is drawn towards the centroid position of the triangle formed by EM-K12. The number of intersections with the EM-K12 triangle is 1, which is an odd number. This indicates that the test site X3 is within the aforementioned electronic fence.

[0093] In some other embodiments, in step S230 above, the area of ​​the electronic fence is cut according to the inflection point to obtain the cut polygonal area, including: dividing the area of ​​the electronic fence according to the second connecting line between adjacent inflection points and the concave point of the electronic fence to obtain a fifth polygonal area and a sixth polygonal area; the fifth polygonal area is a convex polygon with three or more sides composed of straight lines; the sixth polygonal area contains curves and is a closed figure with two or more sides.

[0094] The electronic fence is divided into fifth and sixth polygonal regions based on the second connecting line between adjacent inflection points and the concave point of the electronic fence. This includes: connecting the midpoint of the second connecting line between adjacent inflection points to the corresponding concave point and extending it to intersect with the boundary of the electronic fence to obtain a second intersection point; and connecting the second intersection point, the concave point and the inflection point to obtain multiple fifth polygonal regions and multiple sixth polygonal regions.

[0095] For example, refer to Figure 8B As shown, the midpoint N of the second connecting line EF of adjacent inflection points is connected to the opposite concave point M and extended to intersect with the boundary of the electronic fence, resulting in the second intersection point K21. Based on the second intersection point K21, the concave point M is connected to the inflection points E and F, resulting in the following two triangular regions (as an example of the fifth polygonal region): the triangle formed by EM-K21 and the triangle formed by FM-K21; and the following two closed regions (as an example of the sixth polygonal region): the closed figure formed by the line E-K21 and the arc E-K21, and the closed figure formed by the line F-K21 and the arc F-K21. After segmenting the polygonal regions, the target polygonal region closest to the test site X3 can be determined based on the centroid position as the closed shape formed by the straight line E-K21 and the arc E-K21. Starting from the test site X3, a ray is drawn towards the centroid position of the closed shape formed by the straight line E-K21 and the arc E-K21. The number of intersections with the closed shape formed by the straight line E-K21 and the arc E-K21 is 1, which is an odd number. Therefore, the test site X3 is found to be within the aforementioned electronic fence.

[0096] In some other embodiments, step S230 above, which involves dividing the electronic fence region based on the inflection point to obtain a divided polygonal region, includes: dividing the electronic fence region based on the first connecting line between the inflection point and the concave point, the second connecting line between adjacent inflection points, and the concave point of the electronic fence to obtain a seventh polygonal region and an eighth polygonal region; the seventh polygonal region is a convex polygon with three or more sides formed by straight lines; the eighth polygonal region contains curves and is a closed figure with two or more sides.

[0097] The electronic fence is divided into seventh and eighth polygonal regions based on the first connecting line between the inflection point and the concave point, the second connecting line between adjacent inflection points, and the concave point of the electronic fence. This includes: extending the first connecting line between the inflection point and the adjacent concave point to intersect with the boundary of the electronic fence to obtain a first intersection point; connecting the midpoint of the second connecting line between adjacent inflection points to the opposite concave point and extending it to intersect with the boundary of the electronic fence to obtain a second intersection point; and connecting the first intersection point, the second intersection point, the concave point, and the inflection point to obtain multiple seventh polygonal regions and multiple eighth polygonal regions.

[0098] A second exemplary embodiment of this disclosure provides an apparatus for boundary detection.

[0099] Figure 9 A structural block diagram of an out-of-bounds detection apparatus according to an embodiment of the present disclosure is shown schematically.

[0100] Reference Figure 9 As shown, the boundary crossing detection device 900 provided in this embodiment includes: a fence data acquisition module 901, an inflection point determination module 902, a region cutting module 903, a position determination module 904, and a result generation module 905.

[0101] The aforementioned fence data acquisition module 901 is used to acquire electronic fence data corresponding to the monitored area or monitored object.

[0102] The aforementioned inflection point determination module 902 is used to determine the inflection point of the electronic fence based on the aforementioned electronic fence data.

[0103] The aforementioned region cutting module 903 is used to cut the region of the electronic fence based on the aforementioned inflection point to obtain a cut polygonal region; wherein the interior of the cut electronic fence contains at least one convex polygon.

[0104] The aforementioned position determination module 904 is used to determine the relative position of the detection point and the electronic fence based on the cut polygonal area.

[0105] The result generation module 905 is used to generate the boundary detection result of the detection site relative to the electronic fence based on the relative position.

[0106] According to embodiments of this disclosure, the boundary crossing detection device 900 further includes a self-crossing detection module.

[0107] The self-crossing detection module described above is used to detect whether a self-crossing point exists.

[0108] The aforementioned area segmentation module is also used to: divide the aforementioned electronic fence into multiple separate areas based on the self-intersection points when self-intersection points exist.

[0109] Specifically, the process of dividing the electronic fence into regions based on the aforementioned inflection points to obtain the resulting polygonal regions includes: for each of the multiple discrete regions after division, dividing the current discrete region into regions based on the aforementioned inflection points to obtain the resulting polygonal regions.

[0110] Further details or beneficial effects of this embodiment can be found in the description of the first embodiment, which will not be repeated here.

[0111] Any plurality of the functional modules included in the aforementioned device 900 may be combined into one module, or any one of the modules may be split into multiple modules. Alternatively, at least a portion of the functionality of one or more of these modules may be combined with at least a portion of the functionality of other modules and implemented in one module. At least one of the functional modules included in the device 900 may be at least partially implemented as hardware circuitry, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a System-on-Chip, a System-on-Substrate, a System-on-Package, an Application-Specific Integrated Circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in hardware or firmware, or in any one of software, hardware, and firmware implementations, or in a suitable combination of any of these. Alternatively, at least one of the functional modules included in the device 900 may be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0112] A third exemplary embodiment of this disclosure provides an electronic device.

[0113] Figure 10 A schematic block diagram of an electronic device provided in an embodiment of the present disclosure is shown.

[0114] Reference Figure 10 As shown, the electronic device 1000 provided in this embodiment includes a processor 1001, a communication interface 1002, a memory 1003, and a communication bus 1004. The processor 1001, the communication interface 1002, and the memory 1003 communicate with each other through the communication bus 1004. The memory 1003 is used to store computer programs. When the processor 1001 executes the program stored in the memory, it implements the out-of-bounds detection method as described above.

[0115] A fourth exemplary embodiment of this disclosure also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program that, when executed by a processor, implements the out-of-bounds detection method as described above.

[0116] The computer-readable storage medium may be included in the device or apparatus described in the above embodiments; or it may exist independently and not assembled into the device or apparatus. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0117] According to embodiments of this disclosure, the computer-readable storage medium can be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0118] It should be noted that the collection, gathering, updating, analysis, processing, use, transmission, and storage of user personal information involved in the technical solutions provided in this disclosure comply with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken to prevent unauthorized access to user personal information data and to safeguard user personal information security, network security, and national security.

[0119] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0120] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for boundary crossing detection, characterized in that, include: Obtain electronic fence data corresponding to the monitored area or monitored object; Based on the electronic fence data, the inflection points of the electronic fence are determined; wherein, a coordinate system is constructed based on the values ​​of each boundary contour point in the electronic fence data, and the graphic of the electronic fence is generated in the coordinate system; the curvature of each point in the electronic fence is calculated; when the curvature value at a certain point exceeds a set threshold, that point is considered to be an inflection point. The electronic fence is divided into regions based on the inflection points to obtain a polygonal region after the division; wherein the interior of the electronic fence after the division contains at least one convex polygon. Based on the cut polygonal region, determine the relative position of the detection point to the electronic fence; Based on the relative position, generate the boundary detection result of the detection site relative to the electronic fence; When there are multiple polygonal regions after cutting, the relative position of the detection point to the electronic fence is determined based on the cut polygonal regions, including: Determine the centroid position of each of the multiple polygon regions; Based on the distance between the centroid position and the detection point, the polygonal region whose centroid position is closest to the detection point is determined as the target polygonal region; A first relative position between the detection point and the target polygonal region is determined, and the first relative position is used as the relative position between the detection point and the electronic fence.

2. The method according to claim 1, characterized in that, The relative position includes one of the following: the detection point is located inside the electronic fence, the detection point is located at the boundary of the electronic fence, or the detection point is located outside the electronic fence; Based on the relative position, the boundary detection result of the detection site relative to the electronic fence is generated, including: Based on the relative position and boundary setting conditions, generate the boundary detection result of the detection site relative to the electronic fence; The boundary setting condition is used to indicate that the detection point is in a boundary-crossing state when it is in the target relative position; the target relative position is one of the following: the detection point is located inside the electronic fence, the detection point is located at the boundary of the electronic fence, the detection point is located outside the electronic fence, the detection point is located inside and at the boundary of the electronic fence, and the detection point is located outside and at the boundary of the electronic fence.

3. The method according to claim 1, characterized in that, For electronic fences with shapes that are self-intersecting polygons, concave-convex fusion polygons, concave-convex nested polygons, or contain curved outlines, the polygon regions obtained after region segmentation include the following two types: convex polygons with three or more sides composed of straight lines, and closed shapes with two or more sides containing curves.

4. The method according to any one of claims 1-3, characterized in that, The electronic fence area is divided according to the inflection point to obtain the divided polygonal area, including: Connecting each pair of adjacent inflection points with straight lines yields a first polygonal region and a second polygonal region after region segmentation. The first polygonal region is a convex polygon with three or more sides formed by straight lines. The second polygonal region contains curves and is a closed figure with two or more sides. Alternatively... The electronic fence is divided into a third polygonal region and a fourth polygonal region based on the first connecting line between the inflection point and the concave point and the concave point of the electronic fence; the third polygonal region is a convex polygon with three or more sides formed by straight lines; the fourth polygonal region contains curves and is a closed figure with two or more sides; or... The electronic fence is divided into a fifth polygonal region and a sixth polygonal region based on the second connecting line between adjacent inflection points and the concave point of the electronic fence; the fifth polygonal region is a convex polygon with three or more sides formed by straight lines; the sixth polygonal region contains curves and is a closed figure with two or more sides; or... The electronic fence is divided into a seventh polygonal region and an eighth polygonal region based on the first connecting line between the inflection point and the concave point, the second connecting line between adjacent inflection points, and the concave point of the electronic fence. The seventh polygonal region is a convex polygon with three or more sides formed by straight lines. The eighth polygonal region contains curves and is a closed figure with two or more sides.

5. The method according to claim 4, characterized in that, The electronic fence is divided into third and fourth polygonal regions based on the first connecting line between the inflection point and the concave point and the concave point of the electronic fence, including: Extend the first connecting line between the inflection point and the adjacent concave point to intersect with the boundary of the electronic fence to obtain the first intersection point; connect the first intersection point, the concave point and the inflection point to obtain multiple third polygon regions and multiple fourth polygon regions; The electronic fence is divided into a fifth polygonal region and a sixth polygonal region based on the second connecting line between adjacent inflection points and the concave point of the electronic fence, including: Connect the midpoint of the second connecting line between adjacent inflection points to the opposite concave point and extend it to intersect with the boundary of the electronic fence to obtain the second intersection point; connect the second intersection point, the concave point and the inflection point to obtain multiple fifth polygon regions and multiple sixth polygon regions; The electronic fence is divided into seven and eight polygonal regions based on the first connecting line between the inflection point and the concave point, the second connecting line between adjacent inflection points, and the concave point of the electronic fence. Extend the first connecting line between the inflection point and the adjacent concave point to intersect with the boundary of the electronic fence to obtain the first intersection point; connect the midpoint of the second connecting line between the adjacent inflection points and the opposite concave point and extend it to intersect with the boundary of the electronic fence to obtain the second intersection point; connect the first intersection point, the second intersection point, the concave point and the inflection point to obtain multiple seventh polygon regions and multiple eighth polygon regions.

6. The method according to any one of claims 1-3, characterized in that, Also includes: Detect the presence of self-intersections; In the presence of self-intersection points, the electronic fence is divided into multiple discrete areas based on these points; Specifically, the electronic fence area is divided according to the inflection point to obtain the divided polygonal area, including: For each of the multiple discrete regions after division, the region of the current discrete region is cut according to the inflection point to obtain the cut polygonal region.

7. The method according to claim 1, characterized in that, Based on the electronic fence data, the inflection points of the electronic fence are determined, including: If the electronic fence data includes inflection point markers, the points carrying inflection point markers will be identified as inflection points of the electronic fence. If the electronic fence data does not contain inflection point markers, the curvature of each point in the electronic fence is calculated based on the electronic fence data; the inflection points of the electronic fence are determined based on the curvature.

8. A boundary crossing detection device, characterized in that, include: The fence data acquisition module is used to acquire electronic fence data corresponding to the monitored area or monitored object; The inflection point determination module is used to determine the inflection points of the electronic fence based on the electronic fence data; wherein, a coordinate system is constructed based on the values ​​of each boundary contour point in the electronic fence data, and the graphic of the electronic fence is generated in the coordinate system; the curvature of each point in the electronic fence is calculated; when the curvature value at a certain point exceeds a set threshold, the point is considered to be an inflection point. A cutting module is used to cut the area of ​​the electronic fence according to the inflection point to obtain a cut polygonal area; wherein the interior of the cut electronic fence contains at least one convex polygon. The location determination module is used to determine the relative position of the detection point and the electronic fence based on the cut polygonal area; The result generation module is used to generate the boundary detection result of the detection site relative to the electronic fence based on the relative position; When there are multiple polygonal regions after cutting, the position determination module is also used for: Determine the centroid position of each of the multiple polygon regions; Based on the distance between the centroid position and the detection point, the polygonal region whose centroid position is closest to the detection point is determined as the target polygonal region; A first relative position between the detection point and the target polygonal region is determined, and the first relative position is used as the relative position between the detection point and the electronic fence.

9. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method of any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1-7.

Images