A Target Tracking Method in Camera Distribution Map

A distribution map and target tracking technology, applied in the field of target tracking in the camera distribution map, can solve problems such as complexity and heavy workload, and achieve the effect of reducing arduous work and increasing application value.

Active Publication Date: 2019-05-31
徐州汉泽信息科技有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this application can also achieve the purpose of intelligent monitoring to a certain extent, in view of the fact that the effective clips of the target appearing in the video only account for a small proportion of the monitoring staff's screen-browsing workload, and if it is necessary to rely on manual The camera monitoring node draws a path on the map and analyzes the corresponding motion information. The workload is huge and very complicated. Therefore, a technology for tracking suspicious targets in the camera distribution map is needed, and computer vision is used to automatically extract the location of suspicious targets. Video clips and motion information for targeted analysis by monitoring personnel

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Target Tracking Method in Camera Distribution Map
  • A Target Tracking Method in Camera Distribution Map
  • A Target Tracking Method in Camera Distribution Map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] combine figure 1 In this embodiment, a target tracking system in a camera distribution map includes two parts: a monitoring operation client and a video computing server.

[0048] The monitoring operation client includes a suspect target image operation module, a camera distribution map operation module and a tracking result display module. The camera nodes in the monitoring area have already been marked on the map through the GIS API interface, and have the function of calling the monitoring video information on the corresponding camera node.

[0049] The suspect target image operation module mainly realizes that when the suspect target is not found in the monitoring area, directly import the suspect target image; or when the suspect target is found in the monitoring area, select the video frame containing the suspect target, and interact with the mouse The function of delineating and delineating the suspected target and the area where it is located.

[0050] The cam...

Embodiment 2

[0070] The object tracking system and tracking method in a camera distribution map of this embodiment are basically the same as in Embodiment 1, the difference is that in this embodiment, the clothing color of the suspect's bottom clothing is fused as the clothing color feature template of the suspect, For example, the main color of the bottom of the suspect target is blue, and only the area containing blue is segmented by the back projection method, and the boundary of the bottom of the suspect target is segmented, such as figure 2 As shown in (b), when the region growing method is used, the seed point is the centroid of the lower half of the image of the imported suspected target, and the core value of the principal component of the color histogram in the boundary area is calculated as the feature template.

Embodiment 3

[0072] The target tracking system and tracking method in a camera distribution map of this embodiment are basically the same as in Embodiment 1, the difference is that in this embodiment, the color fusion of the upper and lower clothing of the suspect target is selected as the clothing of the suspect target. Color feature templates, such as figure 2 As shown in (c), that is, in this embodiment, the image containing only the upper body and the lower garment area processed by the region growing method is subjected to array weighted fusion, and the fusion formula is as follows:

[0073] g(x)=(1-α)f 0 (x)+αf 1 (x)

[0074] In this embodiment, the value of α is 0.5, and f 0 (x) and f 1 (x) respectively represent the image arrays of the upper body and the lower body after processing by the region growing method.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a target tracking method in a camera distribution map, which includes a monitoring operation client and a video calculation server. The monitoring operation client inputs an image of a suspected target, and sets the range to be searched through the camera distribution map; the video calculation server The sampled video and images are processed, including the color feature extraction of the suspected target image, target detection and tracking in the video scene, recording target movement information, and then sending the corresponding calculated results to the monitoring operation client; the monitoring operation client is marked On the map of the camera node, the path track of the suspected target on the map is obtained according to the camera node that has appeared, and the speed and status of the target are collected at the same time for security monitoring personnel to analyze. The invention greatly reduces the arduous work of staring at the screen and searching, allows staff to focus on effective video clips, and has greater application value in the field of scientific and technological strengthening of the police.

Description

technical field [0001] The invention belongs to the technical field of video monitoring, and more specifically relates to a method for tracking a target in a camera distribution map. Background technique [0002] With the improvement of the requirements for smart cities, people's demand for video surveillance is unprecedentedly high, and the cameras deployed in various places are becoming more and more dense. There are at least 10 million surveillance cameras used in urban surveillance and alarm systems in our country. Although the addition of cameras has brought benefits to large-scale prevention and the ability to obtain massive amounts of video data for real-time alarms and post-event inquiries, how to use massive amounts of video data manually has become a huge challenge. The Sandia National Laboratory in the United States conducted a special study, and the results showed that if a person stares intently at a large number of video images, after only 22 minutes, the huma...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
CPCG06V20/42G06V20/46
Inventor 纪滨许婷申元霞粱昌龙
Owner 徐州汉泽信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap