Object detection in a maritime environment : performance evaluation of background subtraction methods

This paper provides a benchmark of the performance of 23 classical and state-of-the-art background subtraction (BS) algorithms on visible range and near infrared range videos in the Singapore Maritime dataset. Importantly, our study indicates the limitations of the conventional performance evaluatio...

Full description

Saved in:
Bibliographic Details
Main Authors: Prasath, Chandrashekar Krishna, Rajan, Deepu, Rachmawati, Lily, Rajabally, Eshan, Quek, Chai, Prasad, Dilip Kumar
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2019
Subjects:
Online Access:https://hdl.handle.net/10356/84193
http://hdl.handle.net/10220/50180
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-84193
record_format dspace
spelling sg-ntu-dr.10356-841932020-03-07T11:50:48Z Object detection in a maritime environment : performance evaluation of background subtraction methods Prasath, Chandrashekar Krishna Rajan, Deepu Rachmawati, Lily Rajabally, Eshan Quek, Chai Prasad, Dilip Kumar School of Computer Science and Engineering Rolls-Royce@ NTU Corporate Lab Engineering::Computer science and engineering Autonomous Automobiles Maritime Vehicles This paper provides a benchmark of the performance of 23 classical and state-of-the-art background subtraction (BS) algorithms on visible range and near infrared range videos in the Singapore Maritime dataset. Importantly, our study indicates the limitations of the conventional performance evaluation criteria for maritime vision and proposes new performance evaluation criteria that is better suited to this problem. This paper provides insight into the specific challenges of BS in maritime vision. We identify four open challenges that plague BS methods in maritime scenario. These include spurious dynamics of water, wakes, ghost effect, and multiple detections. Poor recall and extremely poor precision of all the 23 methods, which have been otherwise successful for other challenging BS situations, allude to the need for new BS methods custom designed for maritime vision. NRF (Natl Research Foundation, S’pore) Accepted version 2019-10-16T07:49:14Z 2019-12-06T15:40:15Z 2019-10-16T07:49:14Z 2019-12-06T15:40:15Z 2018 Journal Article Prasad, D. K., Prasath, C. K., Rajan, D., Rachmawati, L., Rajabally, E., & Quek, C. (2019). Object detection in a maritime environment : performance evaluation of background subtraction methods. IEEE Transactions on Intelligent Transportation Systems, 20(5), 1787-1802. doi:10.1109/TITS.2018.2836399 1524-9050 https://hdl.handle.net/10356/84193 http://hdl.handle.net/10220/50180 10.1109/TITS.2018.2836399 en IEEE Transactions on Intelligent Transportation Systems © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TITS.2018.2836399. 15 p. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Autonomous Automobiles
Maritime Vehicles
spellingShingle Engineering::Computer science and engineering
Autonomous Automobiles
Maritime Vehicles
Prasath, Chandrashekar Krishna
Rajan, Deepu
Rachmawati, Lily
Rajabally, Eshan
Quek, Chai
Prasad, Dilip Kumar
Object detection in a maritime environment : performance evaluation of background subtraction methods
description This paper provides a benchmark of the performance of 23 classical and state-of-the-art background subtraction (BS) algorithms on visible range and near infrared range videos in the Singapore Maritime dataset. Importantly, our study indicates the limitations of the conventional performance evaluation criteria for maritime vision and proposes new performance evaluation criteria that is better suited to this problem. This paper provides insight into the specific challenges of BS in maritime vision. We identify four open challenges that plague BS methods in maritime scenario. These include spurious dynamics of water, wakes, ghost effect, and multiple detections. Poor recall and extremely poor precision of all the 23 methods, which have been otherwise successful for other challenging BS situations, allude to the need for new BS methods custom designed for maritime vision.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Prasath, Chandrashekar Krishna
Rajan, Deepu
Rachmawati, Lily
Rajabally, Eshan
Quek, Chai
Prasad, Dilip Kumar
format Article
author Prasath, Chandrashekar Krishna
Rajan, Deepu
Rachmawati, Lily
Rajabally, Eshan
Quek, Chai
Prasad, Dilip Kumar
author_sort Prasath, Chandrashekar Krishna
title Object detection in a maritime environment : performance evaluation of background subtraction methods
title_short Object detection in a maritime environment : performance evaluation of background subtraction methods
title_full Object detection in a maritime environment : performance evaluation of background subtraction methods
title_fullStr Object detection in a maritime environment : performance evaluation of background subtraction methods
title_full_unstemmed Object detection in a maritime environment : performance evaluation of background subtraction methods
title_sort object detection in a maritime environment : performance evaluation of background subtraction methods
publishDate 2019
url https://hdl.handle.net/10356/84193
http://hdl.handle.net/10220/50180
_version_ 1681036809778233344