Joint Detection, Re-Identification, and Lstm in Multi-Object Tracking

Wen-Jiin Tsai, Zih Jie Huang, Chen En Chung

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

4 Scopus citations

Abstract

Using Convolutional Neural Networks (CNN) in object tracking typically utilizes spatial features, while ignores the temporal correlation of frames in the whole film, causing that it is easy to lose the target when it is occluded by other objects. To cope with the problem, a robust system combining CNN and long short-term memory (LSTM) is proposed for multi-object tracking. The system consists of three modules: object detection, data association, and LSTM tracking. With the proposed approach, the tracking accuracy can be greatly improved especially when the tracking targets suffer from occlusion. Experimental results showed that the proposed system exhibits outstanding tracking accuracy and stability.

Original languageEnglish
Title of host publication2020 IEEE International Conference on Multimedia and Expo, ICME 2020
PublisherIEEE Computer Society
ISBN (Electronic)9781728113319
DOIs
StatePublished - Jul 2020
Event2020 IEEE International Conference on Multimedia and Expo, ICME 2020 - London, United Kingdom
Duration: 6 Jul 202010 Jul 2020

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
Volume2020-July
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Conference

Conference2020 IEEE International Conference on Multimedia and Expo, ICME 2020
Country/TerritoryUnited Kingdom
CityLondon
Period6/07/2010/07/20

Keywords

  • Convolutional neural network
  • Long short-term memory (LSTM)
  • Multiple object tracking (MOT)

Fingerprint

Dive into the research topics of 'Joint Detection, Re-Identification, and Lstm in Multi-Object Tracking'. Together they form a unique fingerprint.

Cite this