Unlock instant, AI-driven research and patent intelligence for your innovation.

Object matching and tracking system based on multiple camera information fusion and method thereof

A multi-camera and target technology, applied in closed-circuit television systems, image analysis, image data processing, etc., can solve problems such as lack of robustness, achieve the effect of reducing algorithm complexity, reducing irrelevant information interference, and improving accuracy

Inactive Publication Date: 2014-09-24
SUN YAT SEN UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to factors such as occlusion, illumination, angle change, and deformation, such methods lack the necessary robustness.

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
  • Object matching and tracking system based on multiple camera information fusion and method thereof
  • Object matching and tracking system based on multiple camera information fusion and method thereof
  • Object matching and tracking system based on multiple camera information fusion and method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0040] In this embodiment, a moving target matching and tracking system based on multi-camera information fusion includes a single-camera target detection module, a single-camera target tracking module, a single-camera target key feature extraction module, a multi-camera target matching module, and online update of the target model Module

[0041] Such as figure 1 As shown, the single-camera target detection module extracts the moving target in the video collected by the camera and outputs it to the target tracking module; the single-camera target tracking module extracts the parameters of the moving target to realize the tracking of the target in the single camera.

[0042] Such as figure 2 As shown, the single-camera target key point feature extraction module detects visually significant key points on the target, extracts the color and local direction histogram features at the key points, and outputs them to the multi-camera target matching module.

[0043] Such as image 3 As sh...

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 an object matching and tracking system based on multiple camera information fusion and a method thereof. The system comprises a single camera object detection module, a single camera object tracking module, a single camera object key point feature extraction module, a multiple camera object matching module and an object model online updating module. The method is characterized by: establishing a model corresponding to an object in the system; based on two features of a local color and a direction histogram respectively, calculating a similarity of the object and the model; finally, carrying out decision level fusion and taking a fusion result as a basis of the object matching. The matched object feature is used to update the model and realize adaptive tracking of the object. By using the system and the method of the invention, robustness of the multiple camera object matching to a shield, environment, illumination, an angle and the like can be improved. The system and the method of the invention are helpful to realize the robust cooperation tracking of the multiple camera video monitoring system to the object.

Description

Technical field [0001] The present invention relates to the technical field of multi-camera information fusion in video surveillance, and particularly relates to a system and method capable of intelligently detecting and tracking multiple moving targets when monitoring the same scene from different angles. Background technique [0002] Video tracking is an important field to be studied in computer vision. The so-called video tracking refers to the use of a certain method to detect, feature extraction, recognition and tracking of the target of interest in the video sequence, so as to obtain the target's motion parameters and motion trajectory, so that the subsequent behavior of the moving target on this basis Perform analysis and understanding. In actual video surveillance, the occurrence of incidents that require staff intervention and processing is very small, which requires surveillance staff to concentrate for a long time at work. However, it is difficult to achieve this in r...

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): G06T7/20H04N7/18
Inventor 郑慧诚李俊
Owner SUN YAT SEN UNIV