A Method of Tracking Moving Object Using Multiple Cameras

A moving target and camera technology, applied in the field of target tracking, can solve problems such as the degradation of moving target tracking quality and the limited viewing angle of a single camera, so as to solve the problem of poor tracking effect and improve tracking quality.

Inactive Publication Date: 2017-09-01
NANJING UNIV OF SCI & TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention proposes a method for tracking a moving target by using multiple cameras, which solves the problem that the tracking quality is degraded due to the occlusion of the moving target due to the limited monitoring angle of a single camera

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 Method of Tracking Moving Object Using Multiple Cameras
  • A Method of Tracking Moving Object Using Multiple Cameras
  • A Method of Tracking Moving Object Using Multiple Cameras

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] Such as figure 1 Shown, a kind of method that adopts multiple cameras to carry out moving object tracking of the present invention, comprises the following steps:

[0016] Step 1: Use at least three cameras to monitor the moving target A from multiple angles. The common plane area in each camera image is the main plane. The common plane area can be the same ground, plane background and other areas in each camera image. Select four or more points in the main plane of each camera image, use the normalized cross-correlation algorithm to accurately match each point pair in the main plane of the two cameras to obtain matching point pairs, and calculate according to the matching point pairs Homography relationship between principal planes in each camera image.

[0017] The normalized cross-correlation algorithm (NCC) described in this step can be found in Document 1 (Sun Bujiao, Zhou Donghua. Fast matching algorithm based on NCC [J]. Sensors and Microsystems. 2007.26(9).). ...

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 proposes a method for tracking a moving object by using multiple cameras. Based on the general single-camera target tracking method, the present invention uses multi-cameras and multiple viewing angles to simultaneously track moving targets in the same area, and utilizes multiple viewing angles to distinguish and locate targets that are blocked by a single viewing angle. First determine the common plane area in each camera image as the main plane of each camera image, and calculate the homography matrix between the main planes, and then use the main plane of the camera image with the largest target occlusion weight as the main plane for mapping, and the rest of the camera images A homography is performed on the mapped principal plane. Using the homography relation, the tracking information of the object with the largest occlusion weight is obtained through the object tracking information in the remaining camera images. The invention overcomes the problem of target tracking failure in the case of occlusion, and improves the accuracy of target tracking.

Description

technical field [0001] The invention belongs to the technical field of target tracking, and in particular relates to a method for tracking a moving target by using multiple cameras. Background technique [0002] Commonly used moving target tracking methods include the mean-shift algorithm, Kalman filter, and particle filter, among which particle filters are often used to track moving targets of various complexity. Generally speaking, the tracking of independent moving targets in a single camera surveillance video has achieved good results, but when there are too many moving targets or the targets are frequently occluded, the tracking effect of these commonly used target tracking methods will be affected. . At this point, multiple cameras can be considered for auxiliary tracking. Contents of the invention [0003] The invention proposes a method for tracking a moving target by using multiple cameras, which solves the problem that the tracking quality is reduced due to the...

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): G06T7/292
Inventor 顾国华刘琳李娇龚文彪孔筱芳徐富元
Owner NANJING UNIV OF SCI & TECH
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