Tracklet Siamese Network with Constrained Clustering for Multiple Object Tracking

Jinlong Peng, Fan Qiu, John See, Qi Guo, Shaoshuai Huang, Ling-Yu Duan, Weiyao Lin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Multiple object tracking (MOT) is an important yet challenging task in video understanding and analysis. Basically, MOT aims to associate detected objects into trajectories based on their temporal relationships. The occlusion among moving objects poses a major challenge towards robust modeling of these relationships. In this paper, we propose a novel Tracklet Siamese Network (TSN) for learning similarities between track-lets characterized by appearance information, achieving superior performance on two MOTChallenge benchmark datasets. Our framework constructs short tracklets from highly-related object detections by excluding inaccurate object detections. We also adopt a constrained clustering technique to piece tracklets together into long trajectories, thus recovering many missing detections caused by original detector or the detection removing in the previous step. Comparisons against state-of-the-art methods were reported while ablation studies further substantiate the viability of components in our approach.

Original languageEnglish
Title of host publication2018 IEEE Visual Communications and Image Processing (VCIP)
PublisherIEEE
ISBN (Electronic)9781538644584
DOIs
Publication statusPublished - 25 Apr 2019
Event33rd IEEE International Conference on Visual Communications and Image Processing 2018 - Taichung, Taiwan, Province of China
Duration: 9 Dec 201812 Dec 2018

Conference

Conference33rd IEEE International Conference on Visual Communications and Image Processing 2018
Abbreviated titleVCIP 2018
CountryTaiwan, Province of China
CityTaichung
Period9/12/1812/12/18

Keywords

  • Constrained clustering
  • Local temporal pooling
  • Multiple object tracking
  • Tracklet
  • Tracklet siamese network

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Fingerprint Dive into the research topics of 'Tracklet Siamese Network with Constrained Clustering for Multiple Object Tracking'. Together they form a unique fingerprint.

Cite this