HOTA: A higher order metric for evaluating multi-object tracking

Multi-object tracking (MOT) has been notoriously difficult to evaluate. Previous metrics overemphasize the importance of either detection or association. To address this, we present a novel MOT evaluation metric, higher order tracking accuracy (HOTA), which explicitly balances the effect of performi...

Full description

Bibliographic Details
Main Authors: Luiten, J, Os̆ep, A, Dendorfer, P, Torr, P, Geiger, A, Leal-Taixé, L, Leibe, B
Format: Journal article
Language:English
Published: Springer Nature 2020
_version_ 1797077432442814464
author Luiten, J
Os̆ep, A
Dendorfer, P
Torr, P
Geiger, A
Leal-Taixé, L
Leibe, B
author_facet Luiten, J
Os̆ep, A
Dendorfer, P
Torr, P
Geiger, A
Leal-Taixé, L
Leibe, B
author_sort Luiten, J
collection OXFORD
description Multi-object tracking (MOT) has been notoriously difficult to evaluate. Previous metrics overemphasize the importance of either detection or association. To address this, we present a novel MOT evaluation metric, higher order tracking accuracy (HOTA), which explicitly balances the effect of performing accurate detection, association and localization into a single unified metric for comparing trackers. HOTA decomposes into a family of sub-metrics which are able to evaluate each of five basic error types separately, which enables clear analysis of tracking performance. We evaluate the effectiveness of HOTA on the MOTChallenge benchmark, and show that it is able to capture important aspects of MOT performance not previously taken into account by established metrics. Furthermore, we show HOTA scores better align with human visual evaluation of tracking performance.
first_indexed 2024-03-07T00:17:54Z
format Journal article
id oxford-uuid:7b7d0c01-8039-4a47-8683-98863fef1dc1
institution University of Oxford
language English
last_indexed 2024-03-07T00:17:54Z
publishDate 2020
publisher Springer Nature
record_format dspace
spelling oxford-uuid:7b7d0c01-8039-4a47-8683-98863fef1dc12022-03-26T20:51:00ZHOTA: A higher order metric for evaluating multi-object tracking Journal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:7b7d0c01-8039-4a47-8683-98863fef1dc1EnglishSymplectic ElementsSpringer Nature2020Luiten, JOs̆ep, ADendorfer, PTorr, PGeiger, ALeal-Taixé, LLeibe, BMulti-object tracking (MOT) has been notoriously difficult to evaluate. Previous metrics overemphasize the importance of either detection or association. To address this, we present a novel MOT evaluation metric, higher order tracking accuracy (HOTA), which explicitly balances the effect of performing accurate detection, association and localization into a single unified metric for comparing trackers. HOTA decomposes into a family of sub-metrics which are able to evaluate each of five basic error types separately, which enables clear analysis of tracking performance. We evaluate the effectiveness of HOTA on the MOTChallenge benchmark, and show that it is able to capture important aspects of MOT performance not previously taken into account by established metrics. Furthermore, we show HOTA scores better align with human visual evaluation of tracking performance.
spellingShingle Luiten, J
Os̆ep, A
Dendorfer, P
Torr, P
Geiger, A
Leal-Taixé, L
Leibe, B
HOTA: A higher order metric for evaluating multi-object tracking
title HOTA: A higher order metric for evaluating multi-object tracking
title_full HOTA: A higher order metric for evaluating multi-object tracking
title_fullStr HOTA: A higher order metric for evaluating multi-object tracking
title_full_unstemmed HOTA: A higher order metric for evaluating multi-object tracking
title_short HOTA: A higher order metric for evaluating multi-object tracking
title_sort hota a higher order metric for evaluating multi object tracking
work_keys_str_mv AT luitenj hotaahigherordermetricforevaluatingmultiobjecttracking
AT osepa hotaahigherordermetricforevaluatingmultiobjecttracking
AT dendorferp hotaahigherordermetricforevaluatingmultiobjecttracking
AT torrp hotaahigherordermetricforevaluatingmultiobjecttracking
AT geigera hotaahigherordermetricforevaluatingmultiobjecttracking
AT lealtaixel hotaahigherordermetricforevaluatingmultiobjecttracking
AT leibeb hotaahigherordermetricforevaluatingmultiobjecttracking