Search

CN-122024176-A - Tracking method and device for mobile booth, electronic equipment and storage medium

CN122024176ACN 122024176 ACN122024176 ACN 122024176ACN-122024176-A

Abstract

The application is applicable to the technical field of artificial intelligence, and provides a tracking method of a mobile booth, which comprises the steps of determining event persistence and moving direction of the mobile booth to be tracked when a fixed camera in a current area detects the mobile booth to be tracked; determining a next area to which a mobile booth to be tracked goes according to event persistence and a moving direction, searching a patrol robot in a preset area if an untracked distance between the next area and a current area is larger than a preset distance, wherein the preset distance is dynamically set according to event occurrence probability between the current area and the next area, and when the event discovery probability of the patrol robot is smaller than a preset event discovery probability, scheduling the patrol robot to execute a tracking task aiming at the event to be tracked between the current area and the next area. According to the application, through the cooperative coordination of the fixed camera and the patrol robot, seamless continuous tracking of the cross-region of the mobile booth is realized, and the resource utilization efficiency is improved.

Inventors

  • LENG PENGYU
  • Chen Yaowo
  • DAI XIANG

Assignees

  • 深圳云天励飞技术股份有限公司

Dates

Publication Date
20260512
Application Date
20260410

Claims (10)

  1. 1. A method of tracking a mobile booth, the method comprising the steps of: when a fixed camera in a current area detects a flowing stall to be tracked, determining event persistence and moving direction of the flowing stall to be tracked; determining a next area to which the mobile booth to be tracked is to go according to the event persistence and the moving direction; If the untraceable distance between the next area and the current area is larger than a preset distance, searching for a patrol robot in a preset area, wherein the preset distance is dynamically set according to the occurrence probability of the event between the current area and the next area; And when the event discovery probability of the patrol robot is smaller than the preset event discovery probability, the patrol robot is scheduled to execute a tracking task aiming at the event to be tracked between the current area and the next area.
  2. 2. The method of tracking a flowing booth as claimed in claim 1, wherein the determining event persistence of the flowing booth to be tracked includes: acquiring the residence time of the mobile booth to be tracked in a current area, the time interval from the last movement and the crowd gathering density around the booth; Calculating the event persistence based on the dwell time, the time interval, and the crowd gathering density.
  3. 3. The method of tracking a mobile booth as claimed in claim 1, wherein the determining a next area to which the mobile booth is to be tracked based on the event persistence and the direction of movement includes: Predicting the time of the flowing stall to be tracked to the next area according to the event persistence; and determining the direction of the flowing stall to be tracked to the next area according to the moving direction.
  4. 4. The method for tracking a flowing booth as claimed in claim 1, wherein the predetermined distance is dynamically set according to a probability of occurrence of an event between the current area and the next area, comprising: Acquiring the occurrence frequency of a historical flowing stall on a path between the current area and the next area, and determining the occurrence probability of an event between the current area and the next area according to the occurrence frequency of the historical flowing stall; according to the mapping relation between the preset event occurrence probability and the preset distance value, converting the event occurrence probability into the corresponding preset distance value, wherein the higher the event occurrence probability is, the smaller the corresponding preset distance is.
  5. 5. The method of tracking a mobile booth as claimed in claim 4, wherein if the non-trackable distance between the next area and the current area is greater than a predetermined distance, locating a patrol robot in the predetermined area includes: acquiring a first coverage boundary of the current area fixed camera and a second coverage boundary of the next area fixed camera; calculating a path distance between the first coverage boundary and the second coverage boundary to obtain the untraceable distance; Comparing the untracked distance with the preset distance; When the untracked distance is larger than the preset distance, searching a planned area with a preset searching radius as a preset area by taking a connecting path of the current area and the next area as a central line; Searching for patrol robots in the preset area.
  6. 6. The method for tracking a flowing booth as claimed in any one of claims 1 to 5, wherein the locating a patrol robot within a predetermined area includes: Acquiring the current positions, the current task states and the residual electric quantity of all patrol robots in the preset area; And screening at least one robot according to the current position, the current task state and the residual electric quantity.
  7. 7. The method of tracking a flowing booth of any of claims 1 to 5 wherein when the event discovery probability of a patrol robot is less than a preset event discovery probability, the method further comprises, prior to scheduling the patrol robot to perform a tracking task for the event to be tracked between the current area and the next area: acquiring the type of a task currently executed by the patrol robot; Searching historical event discovery data of the task type in a target period in an area where the patrol robot is located based on the task type; and determining event discovery probability of the patrol robot based on the historical event discovery data.
  8. 8. A tracking device for a mobile booth, the tracking device comprising: The event detection module is used for determining the event persistence and the moving direction of the flowing stall to be tracked when the fixed camera in the current area detects the flowing stall to be tracked; The first processing module is used for determining the next area to which the flowing stall to be tracked goes according to the event persistence and the moving direction; The second processing module is used for searching the patrol robot in the preset area if the untraceable distance between the next area and the current area is larger than a preset distance, wherein the preset distance is dynamically set according to the occurrence probability of the event between the current area and the next area; and the scheduling tracking module is used for scheduling the patrol robot to execute the tracking task aiming at the event to be tracked between the current area and the next area when the event discovery probability of the patrol robot is smaller than the preset event discovery probability.
  9. 9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the method of tracking a flowing booth as claimed in any one of claims 1 to 7 when the computer program is executed.
  10. 10. A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps in the method of tracking a flowing booth as claimed in any one of claims 1 to 7.

Description

Tracking method and device for mobile booth, electronic equipment and storage medium Technical Field The application belongs to the technical field of artificial intelligence, and particularly relates to a tracking method and device for a mobile booth, electronic equipment and a storage medium. Background Along with the acceleration of the urban process, the mobile stall such as mobile dining car, street vendor, temporary commodity selling point and the like has the characteristics of strong mobility, random distribution, difficult continuous monitoring and the like, so that the management of the mobile stall becomes one of the difficulties in urban management. A traditional fixed camera monitoring mode has a blind area, and is difficult to realize the cross-region continuous tracking of a mobile booth. The patrol robot has the characteristic of being movable, but because the patrol robot performs patrol tasks according to a preset route, more resources are needed if only one mobile stall is continuously tracked. Therefore, a new way of tracking a mobile booth is needed to improve the continuity and efficiency of the mobile booth tracking. Disclosure of Invention The embodiment of the application provides a tracking method of a mobile booth, which can solve the problems that a blind area exists in the existing fixed camera monitoring mode, the cross-region continuous tracking of the mobile booth is difficult to realize, and more resources are required to be input for the cross-region continuous tracking of the mobile booth by adopting a patrol robot. By the cooperative coordination of the fixed cameras and the patrol robots, the dynamic adjustment tracking strategy is combined with the behavior characteristics of the mobile booth and the occurrence probability of events among areas, so that seamless continuous tracking of the mobile booth across areas is realized, the scheduling mechanism of the patrol robots is optimized, and the resource utilization efficiency is improved. In a first aspect, embodiments of the present application provide a method of tracking a mobile booth, the method comprising the steps of: When a fixed camera in the current area detects a flowing stall to be tracked, determining event persistence and moving direction of the flowing stall to be tracked; determining a next area to which the mobile booth to be tracked is to go according to the event persistence and the moving direction; If the untraceable distance between the next area and the current area is larger than the preset distance, searching for the patrol robot in the preset area, wherein the preset distance is dynamically set according to the occurrence probability of the event between the current area and the next area; and when the event discovery probability of the patrol robot is smaller than the preset event discovery probability, the patrol robot is scheduled to execute the tracking task aiming at the event to be tracked between the current area and the next area. Optionally, the determining the event persistence of the flowing booth to be tracked includes: acquiring the residence time of the mobile booth to be tracked in a current area, the time interval from the last movement and the crowd gathering density around the booth; Calculating the event persistence according to the residence time, the time interval and the crowd gathering density. Optionally, the determining, according to the event persistence and the moving direction, a next area to which the flowing booth to be tracked is to be located includes: Predicting the time of the flowing stall to be tracked to the next area according to the event persistence; and determining the direction of the flowing stall to be tracked to the next area according to the moving direction. Optionally, the dynamically setting the preset distance according to the occurrence probability of the event between the current area and the next area includes: Acquiring the occurrence frequency of a historical flowing stall on a path between a current area and a next area, and determining the occurrence probability of an event between the current area and the next area according to the occurrence frequency of the historical flowing stall; and converting the event occurrence probability into a corresponding preset distance value according to a mapping relation between the preset event occurrence probability and the distance value, wherein the event occurrence probability and the preset distance value are in a negative correlation relation, so that the preset distance corresponding to the inter-area path with the higher event occurrence probability is smaller. Optionally, if the untraceable distance between the next area and the current area is greater than the preset distance, searching for the patrol robot in the preset area includes: acquiring a first coverage boundary of a current area fixed camera and a second coverage boundary of a next area fixed camera; Calculating a space linear distan