A special group aggregation behavior early detection and aggregation place prediction method and system

Abstract

The invention belongs to the field of group behavior management and control, and discloses a special group aggregation behavior early detection and aggregation place prediction method and system, andthe method comprises the steps: defining effective active members in a group through employing an aggregation behavior detection algorithm based on the moving average distance between the effective active members, and eliminating the interference of noise members on the aggregation behavior detection; For special groups with aggregation behaviors, the aggregation tendency of the groups is detectedin the early stage of group activities, and early warning is sent out; and screening out potential aggregation members by utilizing an aggregation prediction algorithm based on a least square fittingstraight line of the movement track of the potential aggregation members, and carrying out aggregation prediction. The method does not depend on a video monitoring system, only utilizes the historical moving track data of the group members to realize the rapid judgment of the special group aggregation behavior, gives an early warning for the group with the aggregation behavior in time, and can accurately predict the aggregation place of the group.

Description

technical field [0001] The invention belongs to the field of group behavior management and control, and in particular relates to a method and system for early detection of aggregation behavior of special groups and prediction of aggregation places. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: The gathering behavior of some special groups is likely to threaten public safety and even lead to illegal incidents, so early detection and prevention of gathering behavior of special groups is particularly important. For some special groups, relevant departments need to pay close attention to the gathering behavior of the group, and take preventive measures in a timely manner once they find that there is a tendency to gather. Since the monitoring cycle for special groups may be long, it is unrealistic to rely on manual monitoring and judgment, and manual monitoring and judgment have the defects of not timely discove...

AI Technical Summary

Problems solved by technology

[0007] (1) Relying on the video surveillance system, and can only judge crowd gathering behavior at specific places presented in the video image

For special groups, first of all, it is impossible to have a complete video surveillance system to monitor the group all the time, and secondly, the gathering place is not known in advance;

[0008] (2) Predicting hotspot areas based on the mobile phone access data of urban base stations can only predict the crowd density in the target area from a macro perspective, and cannot realize the location distribution, mobile behavior and aggregation of members in a specific group behavior analysis and prediction;

[0009] (3) Using the center-of-mass method to calculate the gathering place cannot exclude interfering members (that is, members who do not participate in the gathering), and the predicted gathering place is largely affected by factors such as the initial position, departure time, moving direction, and moving speed of the participating members The impact of the prediction accuracy is poor

Even after the target special group is locked, often not all members of the group participate in the gathering. Since we do not know the gathering place in advance, the interference members (members who do not participate in the gathering in the target special group) It is also more difficult to identify and exclude

These interfering members will greatly affect the detection of group gathering behavior and the prediction of gathering places

In addition, for the gathering situation, in practice, the initial position of the members of the special group is less related to the gathering place, and the distance from each member to the gathering place is different, and the departure time, moving speed, and arrival time are also different, and the possible set of gathering places is a large one. The continuous two-dimensional plane area of ​​the range (without considering the height for the time being), makes it extremely difficult to predict the gathering place in advance and accurately

[0012] In practice, it is difficult to continuously monitor special groups in the way of video surveillance, and how to continuously identify members of target special groups from a large-scale crowd has become a difficult point

Even after the target special group is locked, often not all members of the group participate in the gathering. Since the gathering place is not known in advance, the interference members (members who do not participate in the gathering in the target special group) It is also difficult to identify and exclude

These interfering members will greatly affect the detection of group gathering behavior and the prediction of gathering places

In addition, for the gathering situation, in practice, the initial position of the members of the special group is less related to the gathering place, and the distance from each member to the gathering place is different, and the departure time, moving speed, and arrival time are also different, and the possible set of gathering places is a large one. The continuous two-dimensional plane area of ​​the range makes it extremely difficult to predict the gathering place in advance and accurately, which is difficult to solve only by video surveillance

Images