Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

UNSUPERVISED AUTO-ENCODING MULTIPLE-OBJECT TRACKER FOR CONSTRAINT-CONSISTENT COMBINATORIAL PROBLEM

Abstract: 

Multiple-object tracking (MOT) and classification are core technologies for processing moving point clouds in radar or lidar applications. For accurate object classification, the one-to-one association relationship between the model of each objects' motion (trackers) and the observation sequences including auxiliary features (e.g., radar cross section) is important. In this work, we propose an unsupervised neural MOT model for accurate semi-automatic association labeling and we tackle the challenging one-to-one constrained combinatorial association problem by applying relaxation techniques. Experimental results demonstrate that our neural MOT model generates a more constraint-consistent association solution than conventional row-wise softmax methods.

up
0 users have voted:

Paper Details

Authors:
Yuta Kawachi, Teppei Suzuki
Submitted On:
4 June 2020 - 7:59am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Yuta Kawachi
Paper Code:
SPTM-P10.12
Document Year:
2020
Cite

Document Files

ICASSP2020_A0_vert_ykawachi_submit_20200415_3.pdf

(17)

Subscribe

[1] Yuta Kawachi, Teppei Suzuki, "UNSUPERVISED AUTO-ENCODING MULTIPLE-OBJECT TRACKER FOR CONSTRAINT-CONSISTENT COMBINATORIAL PROBLEM", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5452. Accessed: Jul. 09, 2020.
@article{5452-20,
url = {http://sigport.org/5452},
author = {Yuta Kawachi; Teppei Suzuki },
publisher = {IEEE SigPort},
title = {UNSUPERVISED AUTO-ENCODING MULTIPLE-OBJECT TRACKER FOR CONSTRAINT-CONSISTENT COMBINATORIAL PROBLEM},
year = {2020} }
TY - EJOUR
T1 - UNSUPERVISED AUTO-ENCODING MULTIPLE-OBJECT TRACKER FOR CONSTRAINT-CONSISTENT COMBINATORIAL PROBLEM
AU - Yuta Kawachi; Teppei Suzuki
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5452
ER -
Yuta Kawachi, Teppei Suzuki. (2020). UNSUPERVISED AUTO-ENCODING MULTIPLE-OBJECT TRACKER FOR CONSTRAINT-CONSISTENT COMBINATORIAL PROBLEM. IEEE SigPort. http://sigport.org/5452
Yuta Kawachi, Teppei Suzuki, 2020. UNSUPERVISED AUTO-ENCODING MULTIPLE-OBJECT TRACKER FOR CONSTRAINT-CONSISTENT COMBINATORIAL PROBLEM. Available at: http://sigport.org/5452.
Yuta Kawachi, Teppei Suzuki. (2020). "UNSUPERVISED AUTO-ENCODING MULTIPLE-OBJECT TRACKER FOR CONSTRAINT-CONSISTENT COMBINATORIAL PROBLEM." Web.
1. Yuta Kawachi, Teppei Suzuki. UNSUPERVISED AUTO-ENCODING MULTIPLE-OBJECT TRACKER FOR CONSTRAINT-CONSISTENT COMBINATORIAL PROBLEM [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5452