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

A correlation filter tracking method based on saliency detection and image segmentation

A technology of correlation filtering and image segmentation, applied in image analysis, image enhancement, image data processing, etc., can solve problems such as tracking failure, reduction of background feature expression, weak target feature expression, etc., to achieve contrast enhancement, stable and reliable tracking , to solve the effect of easy failure

Active Publication Date: 2018-12-14
ROPEOK TECHNOLOGY GROUP CO LTD
View PDF17 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of the complex background in the actual scene, the feature expression of the target in the rectangular frame is weaker than the background feature, resulting in the phenomenon of tracking failure, the present invention combines the saliency detection and image segmentation method, by distinguishing the foreground and background in the rectangular frame, Preserve foreground information, destroy background information, reduce background feature expression, and then solve the problem of tracking failure in complex backgrounds

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 correlation filter tracking method based on saliency detection and image segmentation
  • A correlation filter tracking method based on saliency detection and image segmentation
  • A correlation filter tracking method based on saliency detection and image segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] Embodiment 1: (pedestrian)

[0025] Step 1: Get the video stream from the camera;

[0026] Step 2: Carry out target detection, select the pedestrian detection method, and obtain the target rectangular frame containing pedestrians to be tracked, such as figure 2 As shown; besides the target to be tracked, the rectangular box also contains rich and complex background information. During the process of correlation filter initialization and feature extraction, the expression of these background information features will be stronger than the expression of pedestrian information features. Such as image 3 As shown, the background is mistakenly regarded as the target, and the real target is regarded as the background, resulting in tracking failure;

[0027] Step 3: For the tracking failure caused by the complex background, firstly, the saliency detection technology is introduced into the initialization process of the correlation filter tracking technology, and the saliency ...

Embodiment 2

[0033] Embodiment 2: (vehicle)

[0034] Step 1: Get the video stream from the camera;

[0035] Step 2: Carry out target detection, select the vehicle detection method, and obtain the target rectangular frame containing the vehicle to be tracked; in addition to the target to be tracked, the rectangular frame also contains rich and complex background information, which is related to In the process of filter initialization and feature extraction, the expression of its features will be stronger than the expression of pedestrian information features, resulting in the background being mistakenly regarded as the target and the real target as the background, resulting in tracking failure;

[0036] Step 3: For the tracking failure caused by the complex background, firstly, the saliency detection technology is introduced into the initialization process of the correlation filter tracking technology, and the saliency detection technology can be used to distinguish the foreground and backg...

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

A correlation filter tracking method based on saliency detection and image segmentation is disclosed. An improved correlation filter method combining saliency detection and image segmentation is proposed, which can improve the tracking accuracy by destroying the background in an image, highlighting the target features, and weakening the background features. The method comprises the steps of acquiring a video stream; detecting a target; distinguishing the foreground and background in the image by saliency detection; performing image contrast enhancement and image segmentation; carrying out andoperation on the obtained segmentation map and the original image to obtain a rectangular frame containing only the target information. Through saliency detection, the contrast degree is improved and,through the image segmentation, the background information in the original rectangular frame is destroyed and the target information is preserved, which makes the expression of the target informationfeature stronger than the background information, and solves the problem of correlation filter tracking failure in complex background.

Description

technical field [0001] The invention relates to the field of video surveillance. Especially related to image processing and analysis technology, a filter tracking method based on saliency detection and image segmentation is proposed. Background technique [0002] With the development of cities, more and more attention has been paid to urban security issues, and video surveillance is the cornerstone of security. In recent years, video processing has become more and more intelligent, and the application of video tracking technology has become more and more extensive. Whether it is a large square, a school park, or an unattended substation, etc., it is necessary to monitor the key focus targets in the video. track. Traditional target tracking requires manual observation, the tracking efficiency is low, and it cannot take into account multiple videos at the same time. Through the introduction of target tracking technology, the monitoring efficiency can be greatly improved, an...

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): G06K9/00G06K9/46G06K9/34
CPCG06T7/136G06T7/194G06T2207/10016G06V40/10G06V20/41G06V20/584G06V10/267G06V10/40G06V2201/08
Inventor 刘晓程苏松志蔡国榕苏松剑李仁杰张翔陈延艺陈延行
Owner ROPEOK TECHNOLOGY GROUP CO LTD
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