Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-camera linkage multi-target tracking method and system for smart community

A target tracking, multi-camera technology, applied in image enhancement, image analysis, image data processing and other directions, can solve the problems of tracking trajectory identification changes, lack of multi-camera multi-target tracking methods, tracking targets being occluded, etc., to reduce occlusion, etc. The effect of changing probability

Pending Publication Date: 2019-12-27
QINGDAO WINDAKA TECH
View PDF6 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in target tracking, the tracking track logo changes frequently due to the tracking target being blocked, the camera shakes, etc.
And most of the current target tracking methods are single-camera multi-target tracking, lacking multi-camera linkage multi-target tracking methods

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
  • Multi-camera linkage multi-target tracking method and system for smart community
  • Multi-camera linkage multi-target tracking method and system for smart community

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] see figure 1 , in an embodiment of the present invention, a multi-camera linkage multi-target tracking method for a smart community includes the following steps:

[0045] Step (1): Obtain the current monitoring camera image;

[0046] In the specific implementation, the real-time video frame of the surveillance camera is pulled through RTSP.

[0047] Step (2): Input the image into the human body detection model;

[0048] In the specific implementation, the human body detection model is trained using a convolutional neural network; a large number of pedestrian pictures collected by itself under surveillance cameras and human body pictures on the Internet are used as data sets, and Mask rcnn is used for training. First, the default parameters are used for training. According to the results during training, the initial weights, training speed, and number of iterations are adjusted until the network achieves the desired recognition effect.

[0049] Step (3): When the huma...

Embodiment 2

[0064] see figure 2 In combination with the smart community-oriented multi-camera linkage multi-target tracking method of Embodiment 1, a smart community-oriented multi-camera linkage multi-target tracking system is provided, including a human body and face feature extraction module 10, a calculation matching module 20, and a target tracking system. Trajectory processing module 30 and data processing module 40. The following is a detailed description of the multi-camera linkage multi-target tracking system for smart communities:

[0065] The human body and human face feature extraction module 10 is used to extract the human body and human face features in the video frame captured by the camera, and obtain the human body detection frame.

[0066] In specific implementation, the human body and face feature extraction module 10 is equipped with a human body detection model and a face recognition model. Both the human body detection model and the face recognition model are trai...

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 relates to the field of community security and protection, in particular to a multi-camera linkage multi-target tracking method and system for a smart community. Human body features andhuman face features are extracted by using a convolutional neural network and are combined with Kalman filtering estimation. The distance is calculated by using the Mahalanobis distance, the similarity of the features is measured by using the cosine distance, then weighted calculation is performed on the two measurements, and the final result is judged by the face recognition result in an auxiliary manner. The method can adapt to a scene with a complex community environment, has multi-camera linkage target tracking, reduces the probability that the target tracking trajectory identifier is changed due to shielding and the like to a certain extent, and has important significance for community management, public security criminal investigation and the like.

Description

technical field [0001] The invention relates to the field of community security, in particular to a multi-camera linkage multi-target tracking method and system for smart communities. Background technique [0002] In smart communities, face recognition technology is an important means of community security deployment and control. It can not only help community managers discover illegal elements in time and grasp the trajectory of strangers, but also assist relevant government departments to search for suspects in a targeted manner. [0003] However, in the surveillance video, due to factors such as camera shooting angle, low resolution, and facial occlusion, it is difficult to obtain high-quality face pictures that meet the standards, and face recognition cannot be completed. When face recognition fails, object tracking becomes a more important community safety technology than face recognition. [0004] The traditional target tracking methods mostly use Kalman filter to pre...

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
IPC IPC(8): G06T7/292G06T7/277G06K9/00G06K9/62
CPCG06T7/292G06T7/277G06T2207/10016G06T2207/20024G06T2207/30201G06T2207/30232G06T2207/20081G06T2207/20084G06V40/172G06V10/751G06F18/241
Inventor 管洪清管延成肖常升王伟张元杰
Owner QINGDAO WINDAKA TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com