Skip to main navigation Skip to search Skip to main content

Graph-Based Tracklet Stitching with Feature Information for Ground Target Tracking

  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Based on the approximation that tracklet kinematic association likelihoods satisfy the Markov or path-independence assumption, several polynomial-time bipartite matching algorithms were proposed to stitch track segments for their effectiveness. However, with target density increasing, their stitching performance would degrade inevitably. Despite the help of feature information, it is remarkable that the aforementioned approximation is no longer valid since the feature information is usually sporadic. In order to solve this problem, track graph is utilized and the feature information is passed through the graph to calculate the tracklet feature association likelihood under path-dependence assumption. It makes bipartite matching algorithms valid again. Finally, simulation results demonstrate that the proposed algorithm outperforms previous algorithms based on path-independence assumption in the dense target situation.

Original languageEnglish
Title of host publicationGeo-Spatial Knowledge and Intelligence - 5th International Conference, GSKI 2017, Revised Selected Papers
EditorsFuling Bian, Hanning Yuan, Jing Geng, Chuanlu Liu, Tisinee Surapunt
PublisherSpringer Verlag
Pages550-557
Number of pages8
ISBN (Print)9789811308925
DOIs
StatePublished - 2018
Event5th International Conference on Geo-Spatial Knowledge and Intelligence, GSKI 2017 - Chiang Mai, Thailand
Duration: 8 Dec 201710 Dec 2017

Publication series

NameCommunications in Computer and Information Science
Volume848
ISSN (Print)1865-0929

Conference

Conference5th International Conference on Geo-Spatial Knowledge and Intelligence, GSKI 2017
Country/TerritoryThailand
CityChiang Mai
Period8/12/1710/12/17

Keywords

  • Bipartite matching
  • Feature information
  • Graph-based model
  • Tracklet stitching

Fingerprint

Dive into the research topics of 'Graph-Based Tracklet Stitching with Feature Information for Ground Target Tracking'. Together they form a unique fingerprint.

Cite this