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

Multi-target tracking algorithm based on tracklet confidence and appearance learning

A multi-target tracking and confidence level technology, applied in computing, image communication, color TV parts, etc., can solve problems such as target tracking, inaccurately detected or undetected objects, intermittent tracking fragments, etc.

Inactive Publication Date: 2018-06-19
JIAXING HIIKON SMART TECH CO LTD +1
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because the method is more difficult to deal with inaccurate or undetected objects due to occlusion, the online method often produces intermittent tracking segments and loses the target when the target is occluded.

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-target tracking algorithm based on tracklet confidence and appearance learning
  • Multi-target tracking algorithm based on tracklet confidence and appearance learning
  • Multi-target tracking algorithm based on tracklet confidence and appearance learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] A multi-target tracking algorithm based on tracking fragment confidence and appearance learning, the specific steps are as follows:

[0026] Step 1, modeling of the online multi-object tracking problem. If target i appears in frame t, record it as v i (t)=1, otherwise record v i (t)=0, when v i When (t)=1, the state of target i is expressed as in are position, size, and velocity, respectively.

[0027] define T i is the set of states from target i to frame t, namely In addition, the collection of tracking segments of all targets up to frame t is denoted as T 1：t . Similarly, the detection result of target i at frame t is The set of all detection results until the tth frame is Z 1：t. In this way, the problem of online multi-object tracking can be expressed as Based on the above equations, a definition of track segment confidence is proposed. A trace fragment with high confidence needs to have the following requirements: Length: Short trace fragments are...

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 a multi-target tracking algorithm based on tracklet confidence and appearance learning. The multi-target tracking algorithm includes: firstly, reading in an image and detectioninformation thereof, calculating the similarity of a detection result and obtained tracklets, performing local association computation on the tracklets and the detection result, then calculating thesimilarity among all the tracklets, and performing global association computation among the tracklets so that the robust and rapid online multi-target tracking algorithm is realized. According to themethod, the targets can be accurately and rapidly distinguished, an appearance model is updated by employing tracking results in an incremental manner, and the tracklets can be successfully associatedin the shielding condition.

Description

technical field [0001] The invention relates to the technical field of video processing and analysis, in particular to a multi-target tracking algorithm based on tracking segment confidence and appearance learning. Background technique [0002] Object tracking is an important content in video surveillance and video analysis, and has a wide range of applications in intelligent monitoring, human-computer interaction, robot navigation, and medical diagnosis. Target tracking mainly refers to determining the position of the moving target we are interested in in each image of the video, and corresponding the same target in different frames. [0003] The existing target tracking algorithms are mainly divided into two categories: batch methods and online methods. The batch processing method processes the detection results of all frames, and links the trajectories that are interrupted due to obstruction, that is, tracklets. For example, A. Andriyenko et al. published "Continuous Ene...

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): G06T7/20H04N5/14H04N7/18
CPCG06T7/20G06T2207/10016H04N5/144H04N5/145H04N7/18
Inventor 盛斌张越青肖佳平田立武周旭楚
Owner JIAXING HIIKON SMART TECH 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