Pedestrian motion trail evolution method and system based on social force model

The integration of physical and social forces in the social force model enhances the accuracy of crowd simulation by addressing collision and deformation issues, providing a realistic depiction of pedestrian movements.

CN119167653AActive Publication Date: 2024-12-20TONGJI UNIV
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411384899.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-30
Publication Date
2024-12-20
Estimated Expiration
2044-09-30

AI Technical Summary

Technical Problem

Current social force models fail to accurately account for pedestrian collisions and crowd extrusion deformation, leading to deviations in crowd distribution and unreasonable oscillations, especially during panic situations.

Method used

A pedestrian motion trajectory evolution method and system that integrates physical forces of collisions and obstacles into the social force model, using a pedestrian dynamics model to simulate interactions and update positions based on actual forces, combining physical and social forces to reflect real-world crowd dynamics.

Benefits of technology

The method and system provide a more accurate simulation of crowd behavior, accounting for multiple collisions and varying force conditions, aligning with actual crowd scenarios and improving dynamic analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119167653A_ABST
    Figure CN119167653A_ABST
Patent Text Reader

Abstract

The invention relates to a pedestrian motion trail evolution method and system based on a social force model, and the method comprises the following steps: setting a simulation environment, and obtaining the initial position of a pedestrian from a video; actual stress of the pedestrian at the collision moment and the non-collision moment is obtained according to a pedestrian dynamic model, the speed of the pedestrian is updated according to the change condition of the speed of the pedestrian along with time, and then the position of the pedestrian is updated; obtaining a pedestrian movement track according to the pedestrian position at each moment; the construction process of the pedestrian dynamics model comprises the following steps: obtaining the interaction force between a pedestrian and other individuals and the interaction force between the pedestrian and a wall based on a social force model; social force is constructed, and physical force and the time-varying condition of the pedestrian speed are constructed according to the contact or collision effect between the pedestrian and other individuals; and constructing a pedestrian dynamics model. Compared with the prior art, the method has the advantages that actual stress conditions among people in different situations can be reflected more accurately, and kinetic analysis is more in line with real conditions.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of crowd disturbance, and in particular to a pedestrian motion trajectory evolution method and system based on a social force model. Background Art

[0002] In recent years, with the increasing number of large-scale crowd activities in public places, crowd safety issues have become prominent. According to incomplete statistics, an average of thousands of people die in gathering activities every year around the world, and even more are injured. Therefore, crowd safety issues have attracted much attention, and a large number of studies have been conducted on the description, laws and guidance of group movement behavior. The unsafe state of crowds is composed of a variety of factors, involving external factors such as venue type, spatial structure, organizational management, safety measures, emergencies, and internal factors such as crowd type and crowd behavior characteristics. Many scholars have proposed a series of pedestrian flow models when studying crowd behavior and characteristics, including cellular automaton models, magnetic field force models, queuing models, social force models, and gas dynamics models. Among them, the social force model has received more and more attention.

[0003] The social force (SF) model assumes that individuals are affected by three forces during the evacuation process: driving force, force between people, and force between people and obstacles. It is impossible for pedestrians to maintain a constant speed during actual movement, but due to their own driving force, pedestrians will try to restore their actual speed to the original state within a specific time. At the same time, the speed change of pedestrians is also affected by external influences and the distance from adjacent pedestrians and walls. In addition, compared with the normal movement of rational pedestrians, the movement of panic pedestrians becomes disordered and chaotic due to the spread of panic emotions, and may cause collisions and falls of themselves or surrounding pedestrians.

[0004] There are still some shortcomings in the current research: 1) The pedestrian collision factor is not considered in the traditional social force model, resulting in a large deviation between the crowd distribution and the real scene; 2) The crowd extrusion deformation is not obvious, there are large gaps between pedestrians, and there are unreasonable oscillation phenomena. Summary of the invention

[0005] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and to provide a pedestrian motion trajectory evolution method and system based on a social force model, thereby realizing the dynamic analysis of pedestrians in different situations.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] A pedestrian motion trajectory evolution method based on a social force model includes the following steps:

[0008] The simulation environment is set up according to the real scene, and the initial position of pedestrians is obtained from the video using the target detection algorithm;

[0009] According to the pedestrian dynamics model, the actual forces on the pedestrian at the collision and non-collision moments during the movement are obtained, and the pedestrian's speed is updated according to the change of the pedestrian's speed over time, and then the pedestrian's position is updated;

[0010] The pedestrian's movement trajectory is obtained by visualizing the position of the pedestrian at each moment during the movement;

[0011] The construction process of the pedestrian dynamics model is as follows:

[0012] Based on the social force model, the interaction forces between pedestrians and other individuals and between pedestrians and walls are obtained;

[0013] The social force is constructed based on the interaction force between the pedestrian and other individuals and the interaction force between the pedestrian and the wall, and the physical force and the change of the pedestrian's speed over time are constructed based on the contact or collision between the pedestrian and other individuals;

[0014] A pedestrian dynamics model is constructed based on the temporal variation of pedestrian speed, physical forces and social forces.

[0015] Furthermore, the speed of the pedestrian changes over time as follows:

[0016]

[0017] In the formula, τ i It means that the pedestrian returns to the original speed within a certain time. represents the speed of pedestrian i, m i represents the quality of pedestrian i, represents the speed of pedestrian i at time t, represents the interaction force between pedestrian i and pedestrian j, represents the repulsive force of the wall on pedestrian i, Indicates the desired direction.

[0018] Furthermore, the interaction force between the pedestrian and other individuals is as follows:

[0019]

[0020] In the formula, A i The parameter representing the magnitude of the influence associated with pedestrian i, r ij represents the actual distance between pedestrian i and pedestrian j, d ij Indicates the set benchmark distance or reference distance, B iThe parameter that represents the decay rate of the exponential function related to pedestrian i, Indicates the direction of the force, represents the change in relative speed between person i and pedestrian j, represents the direction of the tangential component of the force, and k and k represent larger constants;

[0021] The interaction force between the pedestrian and the wall is as follows:

[0022]

[0023] In the formula, r i represents the distance between object i and the wall, d iw Indicates the set benchmark distance or reference distance. Indicates the direction of the force, represents the speed of pedestrian i, Indicates the direction of the tangential component of the force. Furthermore, the combined force on the pedestrian is as follows:

[0024] F i =a·F i,j_phy +b·F i_SF

[0025] a,b∈(0,1)

[0026] In the formula, F i,j_phy represents the physical force on pedestrian i, represents the social force on pedestrian i, and a and b are parameters.

[0027] Furthermore, the dynamic model of the pedestrian is as follows:

[0028]

[0029] a,b∈(0,1)

[0030] In the formula, m i represents the quality of pedestrian i, represents the speed of pedestrian i at time t.

[0031] Furthermore, the social forces are as follows:

[0032]

[0033] In the formula, τ i It means that the pedestrian returns to the original speed within a certain time. represents the speed of pedestrian i, m i represents the quality of pedestrian i, represents the speed of pedestrian i at time t, represents the interaction force between pedestrian i and pedestrian j, represents the repulsive force of the boundary or obstacle on pedestrian i, Indicates the desired direction.

[0034] Further, the physical force is as follows:

[0035]

[0036] Where m represents the mass of the pedestrian, u j represents the set of pedestrians moving together with pedestrian i, v k,- and v i,- represents the speed of pedestrian k and pedestrian i before the collision.

[0037] Furthermore, the physical force includes the interaction force between pedestrians and other individuals.

[0038] Furthermore, the physical force and social force are linearly combined by adjusting the parameters a and b, and the actual force conditions between pedestrians in different situations are reflected according to the combined force on the pedestrians.

[0039] According to another aspect of the present invention, a pedestrian motion trajectory evolution system based on a social force model is provided, comprising:

[0040] The initial position acquisition module is used to set up the simulation environment according to the real scene and use the target detection algorithm to obtain the initial position of the pedestrian from the video;

[0041] The pedestrian position update module is used to obtain the actual forces of pedestrians at collision and non-collision moments during movement according to the pedestrian dynamics model, update the pedestrian's speed according to the change of the pedestrian's speed over time, and then update the pedestrian's position;

[0042] A motion trajectory generating module, used for obtaining the motion trajectory of the pedestrian according to the position of the pedestrian at all times during the motion process;

[0043] The construction process of the pedestrian dynamics model is as follows:

[0044] Based on the social force model, the interaction forces between pedestrians and other individuals and between pedestrians and walls are obtained;

[0045] The social force is constructed based on the interaction force between the pedestrian and other individuals and the interaction force between the pedestrian and the wall, and the physical force and the change of the pedestrian's speed over time are constructed based on the contact or collision between the pedestrian and other individuals;

[0046] A pedestrian dynamics model is constructed based on the temporal variation of pedestrian speed, physical forces and social forces.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. The present invention integrates the physical forces of pedestrians’ contact with other individuals and obstacles into the classical social force model, which can describe multiple simultaneous contacts. The physical forces effectively solve the situation where multiple collisions are inevitable in the crowd, making the dynamic analysis results of the crowd more in line with the actual situation.

[0049] 2. The present invention constructs a dynamic model of pedestrians, linearly combines physical forces and social forces through parameters, and simulates the forces in different situations by adjusting the parameters, which can more accurately reflect the actual forces between pedestrians in different situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flowchart of a pedestrian motion trajectory evolution method based on a social force model proposed by the present invention;

[0051] Figure 2 The crowd scene when an earthquake occurs in a certain place in the embodiment, wherein (2a) is a real scene image, and (2b) is a simulation scene image, wherein the red, green and blue circles represent panicked, normal and calm pedestrians respectively, the green rectangle represents a safe exit, and the yellow circle represents a danger source;

[0052] Figure 3 The movement trajectory of a pedestrian collision in the embodiment, wherein brown and green represent two different pedestrians, the green rectangle represents a safe exit, and the yellow circle represents a danger source. DETAILED DESCRIPTION

[0053] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0054] Example 1

[0055] This embodiment provides a pedestrian motion trajectory evolution method based on a social force model. Figure 1 As shown, the following steps are included:

[0056] S1. Set up a simulation environment according to the real scene and use the target detection algorithm to get the initial position of the pedestrian from the video.

[0057] This embodiment uses a scene where a panicked crowd flees in a market when an earthquake occurs in a certain place, such as Figure 2 As shown, the real scene image is as follows Figure 2 as shown in (2a).

[0058] Before the earthquake, all pedestrians were in a normal state. At t = 3 seconds, the earthquake caused panic among the crowd, and pedestrians rushed out of the alley entrance to avoid the collapse of the house. Due to panic, pedestrians had different degrees of contact and collision when fleeing to the exit.

[0059] First, set up the simulation environment according to the real scene, set up the safety exit, and the danger source is located at point (644, 83). Figure 2 As shown in (2b), the target detection algorithm is used to obtain the initial position of pedestrians from the surveillance video, and the initial speed of all pedestrians is set to 0.

[0060] S2. According to the pedestrian dynamics model, the actual forces on the pedestrian at the collision and non-collision moments during the movement are obtained, and the pedestrian's speed is updated according to the change of the pedestrian's speed over time, and then the pedestrian's position is updated.

[0061] The construction process of the pedestrian dynamics model is as follows:

[0062] Based on the social force model, the interaction forces between pedestrians and other individuals and between pedestrians and walls are obtained;

[0063] The social force is constructed based on the interaction force between the pedestrian and other individuals and the interaction force between the pedestrian and the wall, and the physical force and the change of the pedestrian's speed over time are constructed based on the contact or collision between the pedestrian and other individuals;

[0064] A pedestrian dynamics model is constructed based on the temporal variation of pedestrian speed, physical forces and social forces.

[0065] The interaction forces between pedestrians and other individuals are as follows:

[0066]

[0067] In the formula, A i The parameter representing the magnitude of the influence associated with pedestrian i, exp is used to describe the nonlinear relationship between the force and the distance, r ij represents the actual distance between pedestrian i and pedestrian j, which is used to compare with the actual distance, d ij Indicates the set benchmark distance or reference distance, B i The parameter that represents the decay rate of the exponential function related to pedestrian i, Indicates the directionality of the force, pointing to pedestrian j, represents the change in relative speed between person i and pedestrian j, represents the direction of the tangential component of the force, k and k represent larger constants; r ij -d ijIt represents the difference between the actual distance and the reference distance, reflecting the relative position change between the two pedestrians. g(x) represents the coefficient of the force. If the pedestrians are not in contact with each other, d ij >r ij , then the function g(x) is equal to 0, otherwise g(x) is equal to the parameter (x).

[0068] The interaction force between pedestrians and walls is as follows:

[0069]

[0070] In the formula, r i represents the distance between object i and the wall, d iw Indicates the set benchmark distance or reference distance. Indicates the direction of the force, pointing to the wall w, represents the speed of pedestrian i, represents the direction of the tangential component of the force, r i -d iw It represents the difference between the actual distance and the reference distance, reflecting the change in the relative position between the person and the wall.

[0071] The speed of pedestrians changes with time as follows:

[0072]

[0073] In the formula, τ i It means that the pedestrian returns to the original speed within a certain time. represents the speed of pedestrian i, m i represents the quality of pedestrian i, represents the speed of pedestrian i at time t, represents the interaction force between pedestrian i and pedestrian j, represents the repulsive force of the wall on pedestrian i, Indicates the desired direction.

[0074] The combined forces on the pedestrian are as follows:

[0075] F i =a·F i,j_phy +b·F i_SF

[0076] a,b∈(0,1)

[0077] In the formula, F i,j_phy represents the physical force on pedestrian i, represents the social force on pedestrian i, and a and b are parameters.

[0078] The dynamic model of the pedestrian is as follows:

[0079]

[0080] a,b∈(0,1)

[0081] In the formula, m i represents the quality of pedestrian i, represents the speed of pedestrian i at time t.

[0082] By adjusting the parameters a and b, the physical force and social force are linearly combined, and the combined force on pedestrians is used to reflect the actual force conditions between pedestrians in different situations. At the moment of collision, a = 1, b = 0, the movement of pedestrians is completely affected by the collision, and the effect of social force is 0; while at the moment of non-collision, a = 0, b = 1, the movement of pedestrians is completely affected by social force.

[0083] Social forces are not directly generated by physical contact, but are based on the psychological state and behavioral rules of pedestrians. Social forces are as follows:

[0084]

[0085] In the formula, τ i It means that the pedestrian returns to the original speed within a certain time. represents the speed of pedestrian i, m i represents the quality of pedestrian i, represents the speed of pedestrian i at time t, represents the interaction force between pedestrian i and pedestrian j, represents the repulsive force of the boundary or obstacle on pedestrian i, Indicates the desired direction.

[0086] Physical forces consist of the interaction forces between objects in contact with each other. It reflects the direct physical interaction between pedestrians. The physical forces are as follows:

[0087]

[0088] Where m represents the mass of the pedestrian, u j represents the set of pedestrians moving together with pedestrian j, v k,- and v i,- represents the speed of pedestrian k and pedestrian i before the collision.

[0089] When a collision occurs between pedestrians, the action and reaction forces generated by the collision are measured, and the speed and mass of the colliding pedestrians are recorded. In this embodiment, a collision in a simulated scene is taken as an example, and the number of pedestrians designed is 2, and they are marked as i and j respectively.

[0090] Considering pedestrians as rigid disks, the physical force between pedestrians i and j is as follows:

[0091]

[0092] The pedestrian's speed is updated according to how it changes over time, and then the pedestrian's position is updated.

[0093] S3. Visualize the position of the pedestrian at each moment during the movement to obtain the pedestrian's movement trajectory.

[0094] The position of pedestrians at each moment in the entire movement process is visualized, such as Figure 3 As shown in the figure, brown represents pedestrian i and green represents pedestrian j. Since pedestrian i and pedestrian j collided, they were affected by F i,j_phy The trajectory of the pedestrian deviates from the original forward direction at a small angle after the collision, but the pedestrian still moves in the direction of the destination after the collision. This is consistent with the actual situation.

[0095] Example 2

[0096] This embodiment provides a pedestrian motion trajectory evolution system based on a social force model, including:

[0097] The initial position acquisition module is used to set up the simulation environment according to the real scene and use the target detection algorithm to obtain the initial position of the pedestrian from the video;

[0098] The pedestrian position update module is used to obtain the actual forces of pedestrians at collision and non-collision moments during movement according to the pedestrian dynamics model, update the pedestrian's speed according to the change of the pedestrian's speed over time, and then update the pedestrian's position;

[0099] A motion trajectory generating module, used for obtaining the motion trajectory of the pedestrian according to the position of the pedestrian at all times during the motion process;

[0100] The construction process of the pedestrian dynamics model is as follows:

[0101] Based on the social force model, the interaction forces between pedestrians and other individuals and between pedestrians and walls are obtained;

[0102] The social force is constructed based on the interaction force between the pedestrian and other individuals and the interaction force between the pedestrian and the wall, and the physical force and the change of the pedestrian's speed over time are constructed based on the contact or collision between the pedestrian and other individuals;

[0103] A pedestrian dynamics model is constructed based on the temporal variation of pedestrian speed, physical forces and social forces.

[0104] The rest is the same as in Example 1.

[0105] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.

Claims

1. A pedestrian trajectory evolution method based on social force model, It is characterized in that The following steps are involved: The simulation environment is set up according to the real scene, and the initial position of pedestrians is obtained from the video using the target detection algorithm; According to the pedestrian dynamics model, the actual forces on the pedestrian at the collision and non-collision moments during the movement are obtained, and the pedestrian's speed is updated according to the change of the pedestrian's speed over time, and then the pedestrian's position is updated; The pedestrian's movement trajectory is obtained by visualizing the position of the pedestrian at each moment during the movement; The construction process of the pedestrian dynamics model is as follows: Based on the social force model, the interaction forces between pedestrians and other individuals and between pedestrians and walls are obtained; The social force is constructed based on the interaction force between the pedestrian and other individuals and the interaction force between the pedestrian and the wall, and the physical force and the change of the pedestrian's speed over time are constructed based on the contact or collision between the pedestrian and other individuals; A pedestrian dynamics model is constructed based on the temporal variation of pedestrian speed, physical forces and social forces.

2. According to the pedestrian motion trajectory evolution method based on the social force model of claim 1, It is characterized in that The speed of the pedestrian changes with time as follows: In the formula, τ i It means that the pedestrian returns to the original speed within a certain time. represents the speed of pedestrian i, m i represents the quality of pedestrian i, represents the speed of pedestrian i at time t, represents the interaction force between pedestrian i and pedestrian j, represents the repulsive force of the wall on pedestrian i, Indicates the desired direction.

3. The pedestrian motion trajectory evolution method based on the social force model according to claim 1, It is characterized in that The interaction force between the pedestrian and other individuals is as follows: In the formula, A i The parameter representing the magnitude of the influence associated with pedestrian i, r ij represents the actual distance between pedestrian i and pedestrian j, d ij Indicates the set benchmark distance or reference distance, B i The parameter that represents the decay rate of the exponential function related to pedestrian i, Indicates the direction of the force, represents the change in relative speed between person i and pedestrian j, represents the direction of the tangential component of the force, k and κ represent larger constants; The interaction force between the pedestrian and the wall is as follows: In the formula, r i represents the distance between object i and the wall, d iw Indicates the set benchmark distance or reference distance. Indicates the direction of the force, represents the speed of pedestrian i, Indicates the direction of the tangential component of the force.

4. The pedestrian motion trajectory evolution method based on the social force model according to claim 1, It is characterized in that The combined forces on the pedestrian are as follows: F i =a·F i,j_phy +b·F i_SF a,b∈(0,1) In the formula, F i,j_phy represents the physical force on pedestrian i, represents the social force on pedestrian i, and a and b are parameters.

5. The pedestrian motion trajectory evolution method based on the social force model according to claim 4, It is characterized in that The dynamic model of the pedestrian is as follows: a,b∈(0,1) In the formula, m i represents the quality of pedestrian i, represents the speed of pedestrian i at time t.

6. The pedestrian motion trajectory evolution method based on the social force model according to claim 4, It is characterized in that The social forces are as follows: In the formula, τ i It means that the pedestrian returns to the original speed within a certain time. represents the speed of pedestrian i, m i represents the quality of pedestrian i, represents the speed of pedestrian i at time t, represents the interaction force between pedestrian i and pedestrian j, represents the repulsive force of the boundary or obstacle on pedestrian i, Indicates the desired direction.

7. The pedestrian motion trajectory evolution method based on the social force model according to claim 4, It is characterized in that The physical forces are as follows: Where m represents the mass of the pedestrian, u j represents the set of pedestrians moving together with pedestrian j, v k,- and v i,- Represents the speed of pedestrian k and pedestrian i before the collision.

8. The pedestrian motion trajectory evolution method based on the social force model according to claim 4, It is characterized in that The physical forces include interaction forces between pedestrians and other individuals.

9. The pedestrian motion trajectory evolution method based on the social force model according to claim 4, It is characterized in that The physical force and the social force are linearly combined by adjusting the parameters a and b, and the actual force conditions between pedestrians in different situations are reflected according to the combined force on the pedestrians.

10. A pedestrian trajectory evolution system based on social force model, It is characterized in that include: The initial position acquisition module is used to set up the simulation environment according to the real scene and use the target detection algorithm to obtain the initial position of the pedestrian from the video; The pedestrian position update module is used to obtain the actual forces of pedestrians at collision and non-collision moments during movement according to the pedestrian dynamics model, update the pedestrian's speed according to the change of the pedestrian's speed over time, and then update the pedestrian's position; A motion trajectory generating module, used for obtaining the motion trajectory of the pedestrian according to the position of the pedestrian at all times during the motion process; The construction process of the pedestrian dynamics model is as follows: Based on the social force model, the interaction forces between pedestrians and other individuals and between pedestrians and walls are obtained; The social force is constructed based on the interaction force between the pedestrian and other individuals and the interaction force between the pedestrian and the wall, and the physical force and the change of the pedestrian's speed over time are constructed based on the contact or collision between the pedestrian and other individuals; A pedestrian dynamics model is constructed based on the temporal variation of pedestrian speed, physical forces and social forces.

Citation Information

Patent Citations

  • Building disaster evacuation simulation method based on evacuation object social force evolutionary game model

    CN109271650A

  • Crowd simulation method for social force model based on relative speed

    CN110276123A

  • Disaster crowd behavior dynamics analysis method

    CN113011022A

  • Crowd emergency evacuation simulation method based on social force model and A star algorithm

    CN116523160A

  • Global optimization-based method for improving human crowd trajectory estimation and tracking

    WO2017156443A1