A segmentation and data association annotation system for laser-based multi-target tracking evaluation

Chien Chen Weng*, Chieh-Chih Wang, Jennifer Healey

*Corresponding author for this work

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

2 Scopus citations

Abstract

2D laser scanners are now widely used to accomplish robot perception tasks such as SLAM and multi-target tracking (MTT). While a number of SLAM benchmarking datasets are available, only a few works have discussed the issues of collecting multi-target tracking benchmarking datasets. In this work, a segmentation and data association annotation system is proposed for evaluating multi-target tracking using 2D laser scanners. The proposed annotation system uses the existing MTT algorithm to generate initial annotation results and uses camera images as the strong hints to assist annotators to recognize moving objects in laser scans. The annotators can draw the object's shape and future trajectory to automate segmentation and data association and reduce the annotation task loading. The user study results show that the performance of the proposed annotation system is superior in the V-measure vs. annotation speed tests and the false positive and false negative rates.

Original languageEnglish
Title of host publicationAIM 2012 - 2012 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, Conference Digest
Pages80-86
Number of pages7
DOIs
StatePublished - 5 Oct 2012
Event2012 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2012 - Kaohsiung, Taiwan
Duration: 11 Jul 201214 Jul 2012

Publication series

NameIEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM

Conference

Conference2012 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2012
CountryTaiwan
CityKaohsiung
Period11/07/1214/07/12

Fingerprint Dive into the research topics of 'A segmentation and data association annotation system for laser-based multi-target tracking evaluation'. Together they form a unique fingerprint.

  • Cite this

    Weng, C. C., Wang, C-C., & Healey, J. (2012). A segmentation and data association annotation system for laser-based multi-target tracking evaluation. In AIM 2012 - 2012 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, Conference Digest (pp. 80-86). [6265984] (IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM). https://doi.org/10.1109/AIM.2012.6265984