Anti-shielding tracking method of small target in large-scale scene

A technology for small targets and large scenes, applied in image data processing, instrumentation, computing, etc., can solve problems such as less target information, inconspicuous target features, and tracking target loss, so as to improve reliability, solve tracking loss, and solve judgment. effect of the problem

Inactive Publication Date: 2016-04-06
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF2 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that the existing technology obtains less target information in the tracking process of small targets in large scenes, the target features are not obvious, and when occluders appear, the tracking target is lost

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
  • Anti-shielding tracking method of small target in large-scale scene
  • Anti-shielding tracking method of small target in large-scale scene
  • Anti-shielding tracking method of small target in large-scale scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The specific implementation manner of the present invention is described in conjunction with the accompanying drawings. A small target anti-occlusion tracking method in a large scene of the present invention includes the following steps:

[0019] Step 1. Use the target detection method to detect the previous t 0 The position of the target in the frame image, the detection result is used to initialize the target trajectory prediction method, including:

[0020] First, the target detection method needs to predefine a two-dimensional Gaussian function

[0021] Secondly, establish the model required by the target trajectory prediction method, including: state variables at time t X t = x y v x ...

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 anti-shielding tracking method of a small target in a large-scale scene relating to a target tracking method. According to the invention, the problem in the prior art that the target information of the small target in the large-scale scene obtained in the tracking process is relatively little and the tracking target is liable to be lost is solved. The method comprises following steps: detecting the positions in which a target is located in the front t0 frames of images by the cross-correlation filtering target detection method; judging whether the target is shielded starting from the t0+1 frame of image, if the target is shielded, predicting and tracing the position of the target by the Kalman filtering trajectory prediction method; if the target is not shielded, determining the accurate position of the target through the tracking method combining the cross-correlation filtering target detection method and the Kalman filtering trajectory prediction method. According to the invention, the cross-correlation filtering target detection method and the Kalman filtering trajectory prediction method are creatively combined so as to solve the problem that the small target is liable to be lost when being shielded.

Description

technical field [0001] The invention relates to a target tracking method, in particular to a small target anti-occlusion tracking method in a large scene, and belongs to the technical field of intelligent information processing and target tracking. Background technique [0002] Video-based moving target tracking is one of the widely concerned contents in computer vision, image processing, artificial intelligence and other fields, and has extremely important application value in intelligent monitoring, intelligent transportation and other fields. Video-based moving target tracking refers to the use of intelligent tracking algorithms to track the targets appearing in the video. The target tracking technology replaces manpower with artificial intelligence technology, which reduces the burden on staff and improves work efficiency. [0003] The application scenarios of video-based object tracking are not fixed, so there are some difficult problems in the field of object tracking...

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 Applications(China)
IPC IPC(8): G06T7/20
Inventor 孙文健任鹏
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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