Detection event detection method based on historical track space intersection

Abstract

The invention provides a detection event detection method based on historical track space intersection, and relates to the technical field of simulation. The method comprises the following steps: S10, according to a track storage mode of a detected target simulation model, generating a historical track function T (s) of the detected target simulation model; s20, according to the motion state parameters of the detection system simulation model, constructing a mathematical expression of a detection area D of the detection system simulation model; s30, performing spatial intersection calculation on the historical trajectory function T (s) and the mathematical expression of the detection area D to obtain an intersection point set; and S40, according to the intersection point set, calculating an accumulated stay time length of the detected target simulation model in the detection area D, and when the accumulated stay time length is greater than or equal to a preset threshold value, determining that the detected target simulation model triggers a detection event. According to the method, while the large-step simulation efficiency is maintained, the detection accuracy of the detection event is ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of simulation technology, in particular to a detection event detection method based on historical trajectory space intersection. BACKGROUND

[0002] In the time step-based simulation system, the distance constraint detection is the key indicator to trigger the detection event. The traditional detection method usually detects at discrete time steps, that is, at the end of each time step, the "point-surface" or "point-point" distance between the detected target simulation model and the detection system simulation model is calculated, and whether the detection event is triggered is determined according to the length of time the detected target simulation model stays in the detection area. However, when the simulation step is large, such as Figure 1 As shown, the displacement of the detected target simulation model between adjacent time steps may be far beyond the detection constraint tolerance. At this time, if the detected target simulation model quickly crosses the constraint range between adjacent steps, the system will miss the key detection event due to the detection of only the state of the discrete time point.

[0003] The prior art mainly uses adaptive step reduction to alleviate this problem. When a potential event is detected, the step is dynamically reduced until the accuracy is met. However, this method greatly increases the simulation calculation amount, affecting the simulation efficiency, especially in large-scale complex systems. The core contradiction that the prior art has not solved is the fundamental conflict between large time steps and detection event detection accuracy in the time-space dimension. SUMMARY

[0004] Therefore, it is necessary to provide a detection event detection method based on historical trajectory space intersection to solve the above technical problems, which comprises:

[0005] S10, generating a historical trajectory function T(s) of the detected target simulation model according to a trajectory storage mode of the detected target simulation model; wherein the detected target simulation model is a model for simulating the detected target, the trajectory storage mode is used to distinguish different storage forms of trajectory information, and the historical trajectory function is a mathematical function for describing the motion trajectory of the detected target simulation model;

[0006] S20, constructing a mathematical expression of a detection area D of a detection system simulation model according to a motion state parameter of the detection system simulation model; wherein the detection system simulation model is a model for simulating the detection system, and the mathematical expression is a mathematical representation of the trigger domain of the detection area;

[0007] S30, performing space intersection calculation on the historical trajectory function T(s) and the mathematical expression of the detection area D to obtain a set of intersection points;

[0008] S40, calculating a cumulative residence time of the detected target simulation model in the detection region D according to the set of intersection points, and determining that the detected target simulation model triggers a detection event when the cumulative residence time is greater than or equal to a preset threshold.

[0009] In one of the embodiments, the step S10 comprises:

[0010] S101, if the trajectory storage mode of the detected target simulation model is storage of a plurality of trajectory points, performing spline interpolation on the plurality of trajectory points to generate a historical trajectory function T(s) of the detected target simulation model;

[0011] S102, if the trajectory storage mode of the detected target simulation model is storage of a trajectory analytical equation, determining the trajectory analytical equation as the historical trajectory function T(s) of the detected target simulation model;

[0012] S103, if the trajectory storage mode of the detected target simulation model is storage of only a trajectory starting point P n-1 and an ending point P n , constructing the historical trajectory function T(s) of the detected target simulation model based on the following formula,

[0013]

[0014] wherein H i (s) represents a cubic Hermite function satisfying an endpoint position or velocity constraint, s = (t n -t n-1 ) / Δt represents a normalized time progress parameter, Δt = t n -t n-1 represents a time step, v n-1 represents a velocity of the detected target simulation model, and a n-1 represents an acceleration of the detected target simulation model.

[0015] In one of the embodiments, the step S20 comprises:

[0016] S201, constructing a mathematical expression of the detection region D of the detection system simulation model according to a detection radius of the detection system simulation model and a center position of the detection region of the detection system simulation model, wherein the mathematical expression is as follows:

[0017]

[0018] wherein O(t) represents the center position of the detection region of the detection system simulation model, and R(X, t) represents the detection radius of the detection system simulation model, which is determined based on a position X and a time t of the detection system simulation model.

[0019] In one embodiment, step S201 includes:

[0020] If the detection system simulation model is a static model, then O(t) is fixed to O0, R(X,t) is fixed to R0,

[0021]

[0022] The mathematical expression of the detection area D is as follows:

[0023] D static ={X|||X-O0||≤R0};

[0024] The detection area D is a sphere with O0 as the center and R0 as the radius.

[0025] In one embodiment, step S201 includes:

[0026] If the detection system simulation model is a motion model, then O(t) is a time-dependent function and R(X,t) is a time-varying function;

[0027] The mathematical expression of the detection area D is as follows:

[0028] D dynamic ={X|‖XO(t)||≤R(X,t)}.

[0029] In one embodiment, step S30 includes:

[0030] S301, based on the mathematical expression of the detection area D, spatially segment the detection area D to generate a spatial segmentation structure; the spatial segmentation structure is a tree data structure, and the leaf nodes of the tree data structure correspond to the sub-areas formed by the segmentation;

[0031] S302, discretize the historical trajectory function T(s) into a line segment set {L k};

[0032] S303, the line segment set {L k} and the spatial subdivision structure to perform intersection calculation to obtain an intersection point set.

[0033] In one embodiment, step S302 includes:

[0034] S302a, if the historical trajectory function T(s) is a linear function, connect the lines between the trajectory points As line segment L k ;

[0035] S302b, if the historical trajectory function T(s) is a nonlinear function, generating a line segment L according to the following formula by curvature adaptive segmentation k :

[0036]

[0037] wherein s k ,s k+1 respectively represent the start and end normalized time parameters of the kth trajectory line segment, κ(X) represents the curvature of the trajectory at X, and κ max represents a preset maximum curvature threshold.

[0038] In one of the embodiments, the step S303 comprises:

[0039] S303a, storing the line segment set {L k} into a bounding volume hierarchy;

[0040] S303b, traversing nodes in the spatial subdivision structure to detect leaf nodes intersecting the bounding volume hierarchy;

[0041] S303c, extracting geometric primitives G j in the intersected leaf nodes;

[0042] S303d, calculating the intersection point set of the line segment set {L k} and the geometric primitive G j .

[0043] In one of the embodiments, the step S303d comprises:

[0044] If the probe system simulation model is a static model, the detection region D is a sphere, and the intersection point set is obtained by solving the following quadratic equation:

[0045] ||L(s)-O0|| 2 =R 2 .

[0046] wherein L(s) = A + s(B-A); A represents the starting position of the trajectory; B represents the ending position of the trajectory;

[0047] If the probe system simulation model is a moving model, the detection region D is a polyhedron, and for each triangular facet T i , the following equation is solved:

[0048] (A+s(B-A)-V0)·N i =0.

[0049] wherein V0 represents a vertex of the triangular facet, and N i represents a normal vector of the triangular facet.

[0050] In one embodiment, step S40 includes:

[0051] S401, the intersection point set Sort the intersection points in and generate an ordered sequence 0≤s c,1 <…<s c,m ≤1;

[0052] S402, extracting a set L of normalized time intervals within the detection area D inside =∪ j [s c,2j-1 ,s c,2j ]; where 2j represents an even number, that is, an even number from 1 to m;

[0053] S403, calculate the normalized stay time T inside =Δt∑ j (s c，2j -s c，2j-1 );

[0054] S404, when the accumulated stay time T inside When the value is greater than or equal to a preset threshold, it is determined that the detected target simulation model triggers a detection event.

[0055] The present invention provides a detection event detection method based on spatial intersection of historical trajectories. By performing a spatial intersection calculation between the historical trajectory function of the detected target simulation model and the mathematical expression of the detection area of ​​the detection system simulation model, this method accurately analyzes the geometric relationship between the target's continuous motion trajectory and the detection area. This method does not rely on state detection at discrete time points. Even if the target does not enter the detection area at the start and end points of the step, as long as its continuous trajectory crosses the detection area, the moment the target enters and exits the detection area can be accurately determined through intersection calculation, thus avoiding the missed detection of "rapid crossing" events. This method ensures the accuracy of detection event detection while maintaining the efficiency of large-step simulations, effectively overcoming the limitations of traditional "point-to-surface" or "point-to-point" detection intersection models. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A schematic diagram of a discrete time step loss detection event in one embodiment;

[0057] Figure 2 Schematic diagram of detection intersection based on historical trajectories in one embodiment. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0059] In one embodiment, referring to Figure 2 , a detection event detection method based on historical trajectory space rendezvous is provided, which comprises the following steps:

[0060] S10, generating a historical trajectory function T(s) of the detected target simulation model according to the trajectory storage mode of the detected target simulation model.

[0061] The detected target simulation model is a model for simulating the detected target, which can be specifically understood as a digital target model constructed based on the physical properties and motion law of the detected target, which is used to simulate the dynamic behavior of the real target in the virtual scene.

[0062] The trajectory storage mode is used to distinguish different storage forms of trajectory information, such as a plurality of trajectory point storage, trajectory analytical equation storage, and only storing the starting point and ending point of the trajectory, etc. storage strategy. Different trajectory storage modes are adopted according to the data support capability of the simulation system. If the data support capability of the simulation system is high, such as a strong computing system, high-precision storage modes such as a plurality of trajectory point storage and trajectory analytical equation storage are adopted; if the data support capability of the simulation system is low, such as a resource-limited system, light-weight storage modes such as only storing the starting point and ending point of the trajectory are adopted.

[0063] The historical trajectory function is a mathematical function for describing the motion trajectory of the detected target simulation model, which is used to reconstruct the mathematical expression of the motion trajectory of the detected target.

[0064] As an embodiment of step S10, it specifically comprises the following sub-steps:

[0065] S101, if the trajectory storage mode of the detected target simulation model is a plurality of trajectory point storage, spline interpolation is performed on the plurality of trajectory points to generate the historical trajectory function T(s) of the detected target simulation model.

[0066] S102, if the trajectory storage mode of the detected target simulation model is trajectory analytical equation storage, the trajectory analytical equation is determined as the historical trajectory function T(s) of the detected target simulation model.

[0067] Specifically, if the trajectory storage mode of the detected target simulation model is a high-precision storage mode, a parameterized trajectory function is calculated as the historical trajectory function T(s).

[0068] Extracting the time interval [t n-1t n Parameterized trajectory function within [0, 1] :

[0069] T(s) = f model (s), s ∈ [0, 1] ;

[0070] where f model represents the trajectory parameterization function, s = (t n -t n-1 ) / Δt represents the normalized time progress parameter, and Δt = t n -t n-1 represents the time step.

[0071] According to the trajectory storage mode, f model may be a discrete sequence and an analytical equation.

[0072] If it is a discrete sequence {P n-1 , P1, …, P k , P n}, a continuous trajectory function can be generated by spline interpolation, where P n-1 and P n are two end point coordinates of the start point and the end point, respectively, and {P1, P2, …, P k} are trajectory coordinates stored in the time step.

[0073] If it is an analytical equation, the equation can be directly used as the parameterized trajectory function, such as a parabolic trajectory function:

[0074]

[0075] where v n-1 represents the speed of the simulated model of the detected target, and a n-1 represents the acceleration of the simulated model of the detected target.

[0076] S103, if the trajectory storage mode of the simulated model of the detected target is to store only the start point P n-1 and the end point P n of the trajectory, then based on the following formula, the historical trajectory function T(s) of the simulated model of the detected target is constructed,

[0077]

[0078] where H i (s) represents a cubic Hermite function that satisfies the end point position or speed constraint.

[0079] S20, a mathematical expression of a detection region D of a simulated model of a detection system is constructed according to motion state parameters of the simulated model of the detection system. The simulated model of the detection system is a model for simulating the detection system, and the mathematical expression is a mathematical representation of a trigger domain of the detection region.

[0080] As an embodiment of step S20, it specifically comprises the following sub-steps:

[0081] S201, according to the detection radius of the detection system simulation model and the center position of the detection area of the detection system simulation model, a mathematical expression of the detection area D of the detection system simulation model is constructed, wherein the mathematical expression is as follows:

[0082]

[0083] Wherein, O(t) represents the center position of the detection area of the detection system simulation model, R(X,t) represents the detection radius of the detection system simulation model, and the detection radius is determined based on the position X and time t of the detection system simulation model.

[0084] Specifically, the detection area D defines the spatial range monitored by the detection system simulation model. When the detected target enters this area and accumulates for a certain time, a detection event is triggered.

[0085] Further, the implementation of step S201 is as follows:

[0086] (I) If the detection system simulation model is a static model, O(t) is a fixed O0, and R(X,t) is a fixed R0,

[0087]

[0088] The mathematical expression of the detection area D is as follows:

[0089] D static ={X|‖X-O0||≤R0};

[0090] Wherein, the detection area D is a sphere with O0 as the center and R0 as the radius.

[0091] (II) If the detection system simulation model is a motion model, O(t) is a time-dependent function, and R(X,t) is a time-varying function;

[0092] The mathematical expression of the detection area D is as follows:

[0093] D dynamic ={X|‖X-O(t)||≤R(X,t)}.

[0094] Wherein, the motion trajectory of O(t) is generated using the same reconstruction method as the detected target simulation model, that is, referring to the implementation process of repeating step S10, the stored trajectory is used first, then the kinematic reconstruction, and then the linear reconstruction.

[0095] S30, performing a space intersection calculation on the mathematical expression of the historical trajectory function T(s) and the detection region D to obtain a set of intersection points.

[0096] As an embodiment of step S30, it specifically includes the following sub-steps:

[0097] S301, performing a spatial segmentation on the detection region D based on the mathematical expression of the detection region D to generate a spatial subdivision structure.

[0098] The spatial subdivision structure is a tree data structure, and the leaf nodes on the tree data structure correspond to the sub-regions formed by the segmentation.

[0099] Specifically, any one of the following three spatial segmentation methods can be used:

[0100] (1) Octree recursive subdivision: recursively octanting the circumscribed cube of the detection region D until the size of the leaf node is smaller than the threshold value δ oct .

[0101] (2) Axis-aligned bounding box hierarchical tree (AABB Tree): constructing an axis-aligned bounding box hierarchical tree of the event trigger domain geometric primitives (triangular patches / spheres / cylinders).

[0102] (3) Adaptive KD-Tree subdivision: adaptively segmenting the space along the main direction of the trajectory.

[0103] S302, discretizing the historical trajectory function T(s) into a set of line segments {L k}.

[0104] Further, the specific implementation of step S302 is as follows:

[0105] S302a, if the historical trajectory function T(s) is a linear function, connecting the trajectory points to form a line segment L as a line segment L k ;

[0106] S302b, if the historical trajectory function T(s) is a nonlinear function, using the following formula to adaptively segment the line segment L k :

[0107]

[0108] Where s k ,s k+1 represent the start and end normalized time parameters of the kth trajectory line segment, κ(X) represents the curvature of the trajectory at X, and κ max represents a preset maximum curvature threshold.

[0109] Optionally, for the non-linear trajectory, CGAL::Subdivision_method_3 is adopted for adaptive discretization.

[0110] S303, intersection calculation is performed on the line segment set {L k} and the spatial subdivision structure by using the spatial index, to obtain the set of intersection points. Optionally, CGAL::AABB_tree is used to construct the spatial index of the event trigger domain.

[0111] Further, the specific implementation of step S303 is as follows:

[0112] S303a, the line segment set {L k} is stored in a bounding volume hierarchy (BVH);

[0113] S303b, the nodes in the spatial subdivision structure are traversed to detect the leaf nodes intersecting with the bounding volume hierarchy;

[0114] S303c, the geometric primitives G j in the intersecting leaf nodes are extracted;

[0115] S303d, the set of intersection points of the line segment set {L k} and the geometric primitives G j is calculated.

[0116] Specifically, if the probe system simulation model is a static model, the detection region D is a sphere, and the set of intersection points is obtained by solving the following quadratic equation:

[0117] ||L(s)-O0|| 2 =R 2 ;

[0118] Wherein: L(s) = A + s(B-A); A represents the starting position of the trajectory; B represents the ending position of the trajectory;

[0119] If the probe system simulation model is a moving model, the detection region D is a polyhedron, and for each triangular facet T i of the polyhedron, the following equation is solved:

[0120] (A+s(B-A)-V0)·N i =0;

[0121] Wherein, V0 represents the vertex of the triangular facet, and N i represents the normal vector of the triangular facet.

[0122] Optionally, use CGAL::Surface_mesh to define the polyhedron detection area and call CGAL::intersection(Line_3,Triangle_3) to calculate the line segment-triangle patch intersection.

[0123] S40, calculating the cumulative stay time of the detected target simulation model in the detection area D according to the intersection point set, and determining that the detected target simulation model triggers a detection event when the cumulative stay time is greater than or equal to a preset threshold.

[0124] As an implementation manner of step S40, step S40 specifically includes:

[0125] S401, intersection point set Sort the intersection points in and generate an ordered sequence 0≤s c,1 <…<s c,m ≤1;

[0126] S402, extracting a set L of normalized time intervals within the detection area D inside =∪ j [s c,2j-1 ,s c,2j ]; where 2j represents an even number, that is, an even number from 1 to m;

[0127] S403, calculate the normalized stay time T inside =Δt∑ j (s c，2j -s c，2j-1 );

[0128] S404, when the accumulated stay time T inside When the value is greater than or equal to the preset threshold, it is determined that the detected target simulation model triggers a detection event; otherwise, it is determined that the detection event is not triggered.

[0129] This detection event detection method based on spatial intersection of historical trajectories accurately analyzes the geometric relationship between the target's continuous motion trajectory and the detection area by performing a spatial intersection calculation between the historical trajectory function of the detected target simulation model and the mathematical expression of the detection area of ​​the detection system simulation model. This method does not rely on state detection at discrete time points. Even if the target does not enter the detection area at the start and end points of the step, as long as its continuous trajectory crosses the detection area, the intersection calculation accurately determines the time when the target enters and exits the detection area, thus avoiding the missed detection of "rapid crossing" events. This method ensures the accuracy of detection event detection while maintaining the efficiency of large-step simulations, effectively overcoming the limitations of traditional "point-to-surface" or "point-to-point" detection intersection models.

[0130] Any combination of the technical features in the above embodiments can be made, and for the sake of brevity, not all possible combinations are described above, however, as long as the combination of the technical features does not exist in contradiction, it shall be considered within the scope of the present disclosure.

[0131] The above embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it shall not be understood as a limitation on the patent scope of the present application. It shall be pointed out that, for ordinary skilled persons in the art, several modifications and improvements can be made without departing from the concept of the present application, and these shall be within the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A detection event detection method based on historical trajectory spatial intersection, characterized in that: The following steps are involved: S10, generating a historical trajectory function T(s) of the detected target simulation model according to a trajectory storage mode of the detected target simulation model; wherein the detected target simulation model is a model for simulating the detected target, the trajectory storage mode is used to distinguish different storage forms representing trajectory information, and the historical trajectory function is a mathematical function that describes the motion trajectory of the detected target simulation model; S20, constructing a mathematical expression for a detection area D of the detection system simulation model based on the motion state parameters of the detection system simulation model; wherein the detection system simulation model is a model for simulating the detection system, and the mathematical expression is a mathematical representation of a trigger domain of the detection area; S30, performing spatial intersection calculation on the mathematical expression of the historical trajectory function T(s) and the detection area D to obtain a set of intersection points; S40, calculating the cumulative stay time of the detected target simulation model in the detection area D according to the intersection point set, and determining that the detected target simulation model triggers a detection event when the cumulative stay time is greater than or equal to a preset threshold.

2. The method for detecting a detection event based on spatial intersection of historical trajectories according to claim 1, characterized in that: The step S10 includes: S101, if the trajectory storage mode of the detected target simulation model is to store a plurality of trajectory points, performing spline interpolation on the plurality of trajectory points to generate a historical trajectory function T(s) of the detected target simulation model; S102, if the trajectory storage mode of the detected target simulation model is trajectory analytical equation storage, determining the trajectory analytical equation as the historical trajectory function T(s) of the detected target simulation model; S103, if the trajectory storage mode of the detected target simulation model is to store only the trajectory starting point P n-1 and the end point P n , then based on the following formula, the historical trajectory function T(s) of the detected target simulation model is constructed, Among them, H i (s) represents the cubic Hermitian function that satisfies the endpoint position or velocity constraints, s=(t n -t n-1 ) / Δt represents the normalized time progress parameter, Δt=t n -t n-1 represents the time step, v n-1 Indicates the speed of the detected target simulation model, a n-1 Represents the acceleration of the detected target simulation model.

3. The method for detecting a detection event based on spatial intersection of historical trajectories according to claim 1, characterized in that: The step S20 includes: S201: Construct a mathematical expression for the detection area D of the detection system simulation model according to the detection radius of the detection system simulation model and the center position of the detection area of ​​the detection system simulation model. The mathematical expression is as follows: Wherein, O(t) represents the center position of the detection area of ​​the detection system simulation model, and R(X, t) represents the detection radius of the detection system simulation model, which is determined based on the position X and time t of the detection system simulation model.

4. The method for detecting a detection event based on spatial intersection of historical trajectories according to claim 3, characterized in that: The step S201 includes: If the detection system simulation model is a static model, then O(t) is fixed to O0, R(X,t) is fixed to R0, The mathematical expression of the detection area D is as follows: D static ={X|||X-O0||≤R0}; The detection area D is a sphere with O0 as the center and R0 as the radius.

5. The method for detecting a detection event based on historical trajectory spatial intersection according to claim 3, characterized in that: The step S201 includes: If the detection system simulation model is a motion model, then O(t) is a time-dependent function and R(X,t) is a time-varying function; The mathematical expression of the detection area D is as follows: D dynamic ={X|||X-O(t)||≤R(X,t)}。 6. The method for detecting a detection event based on spatial intersection of historical trajectories according to claim 1, characterized in that: The step S30 includes: S301, based on the mathematical expression of the detection area D, spatially segment the detection area D to generate a spatial segmentation structure; the spatial segmentation structure is a tree data structure, and the leaf nodes of the tree data structure correspond to the sub-areas formed by the segmentation; S302, discretize the historical trajectory function T(s) into a line segment set {L k }; S303, the line segment set {L k } and the spatial subdivision structure to perform intersection calculation to obtain an intersection point set.

7. The method for detecting a detection event based on spatial intersection of historical trajectories according to claim 6, characterized in that: The step S302 includes: S302a, if the historical trajectory function T(s) is a linear function, connect the lines between the trajectory points As line segment L k ; S302b, if the historical trajectory function T(s) is a nonlinear function, the following formula is used to generate the line segment L by adaptive segmentation according to the curvature: k : Among them, s k , s k+1 They represent the normalized time parameters of the start and end of the kth trajectory segment, κ(X) represents the curvature of the trajectory at X, and κ max Indicates the preset maximum curvature threshold.

8. The method for detecting a detection event based on historical trajectory spatial intersection according to claim 7, characterized in that: The step S303 includes: S303a, the line segment set {L k }Store in bounding volume hierarchy; S303b, traversing the nodes in the spatial subdivision structure, and detecting leaf nodes intersecting with the bounding volume hierarchy structure; S303c, extracting the geometric primitive G in the intersecting leaf node j ; S303d, calculate the line segment set {L k } with the geometric primitive G j The set of intersection points.

9. The method for detecting a detection event based on spatial intersection of historical trajectories according to claim 8, characterized in that: The step S303d includes: If the detection system simulation model is a stationary model, the detection area D is a sphere. The intersection point set is obtained by analyzing the following quadratic equation: ||L(s)-O0|| 2 =R 2 ; Where, L(s)=A+s(BA); A represents the starting position of the trajectory; B represents the end position of the trajectory; If the detection system simulation model is a motion model, the detection area D is a polyhedron, and for each triangular face T of the polyhedron i Solution: (A+s(B-A)-V0)·N i =0; Among them, V0 represents the vertex of the triangle, N i Represents the normal vector of the triangle.

10. The method for detecting a detection event based on historical trajectory spatial intersection according to claim 1, characterized in that: The step S40 includes: S401, the intersection point set Sort the intersection points in and generate an ordered sequence 0≤s c,1 <…<s c,m ≤1; S402, extracting a set L of normalized time intervals within the detection area D inside =∪ j [s c,2j-1 ,s c,2j ]; S403, calculate the normalized stay time T inside =ΔtΣ j (s c，2j -s c，2j-1 ); S404, when the accumulated stay time T inside When the value is greater than or equal to a preset threshold, it is determined that the detected target simulation model triggers a detection event.

Images