VM-MODNet: Vehicle Motion aware Moving Object Detection for Autonomous Driving
Moving object Detection (MOD) is a critical task in autonomous driving as moving agents around the ego-vehicle need to be accurately detected for safe trajectory planning. It also enables appearance agnostic detection of objects based on motion cues. There are geometric challenges like motion-parall...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2021-07 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Rashed, Hazem Ahmad El Sallab Yogamani, Senthil |
description | Moving object Detection (MOD) is a critical task in autonomous driving as moving agents around the ego-vehicle need to be accurately detected for safe trajectory planning. It also enables appearance agnostic detection of objects based on motion cues. There are geometric challenges like motion-parallax ambiguity which makes it a difficult problem. In this work, we aim to leverage the vehicle motion information and feed it into the model to have an adaptation mechanism based on ego-motion. The motivation is to enable the model to implicitly perform ego-motion compensation to improve performance. We convert the six degrees of freedom vehicle motion into a pixel-wise tensor which can be fed as input to the CNN model. The proposed model using Vehicle Motion Tensor (VMT) achieves an absolute improvement of 5.6% in mIoU over the baseline architecture. We also achieve state-of-the-art results on the public KITTI_MoSeg_Extended dataset even compared to methods which make use of LiDAR and additional input frames. Our model is also lightweight and runs at 85 fps on a TitanX GPU. Qualitative results are provided in https://youtu.be/ezbfjti-kTk. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2517116305</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2517116305</sourcerecordid><originalsourceid>FETCH-proquest_journals_25171163053</originalsourceid><addsrcrecordid>eNqNis0KgkAYAJcgSMp3WOgs7E-r0S2y6KJewqtsstaK7Vf7U6-fQg_QaRhmZihinNNku2FsgWLnekIISzMmBI9QWRdJUeWl8jtcq7tuB4UL8BoMlh9pJ3lrc8PVtVetx7nyI6bagcX74MHAA4LDudXTt0LzTg5OxT8u0fp0vBzOydPCKyjnmx6CNWNqmKAZpSkngv93fQE5rD1C</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2517116305</pqid></control><display><type>article</type><title>VM-MODNet: Vehicle Motion aware Moving Object Detection for Autonomous Driving</title><source>Free E- Journals</source><creator>Rashed, Hazem ; Ahmad El Sallab ; Yogamani, Senthil</creator><creatorcontrib>Rashed, Hazem ; Ahmad El Sallab ; Yogamani, Senthil</creatorcontrib><description>Moving object Detection (MOD) is a critical task in autonomous driving as moving agents around the ego-vehicle need to be accurately detected for safe trajectory planning. It also enables appearance agnostic detection of objects based on motion cues. There are geometric challenges like motion-parallax ambiguity which makes it a difficult problem. In this work, we aim to leverage the vehicle motion information and feed it into the model to have an adaptation mechanism based on ego-motion. The motivation is to enable the model to implicitly perform ego-motion compensation to improve performance. We convert the six degrees of freedom vehicle motion into a pixel-wise tensor which can be fed as input to the CNN model. The proposed model using Vehicle Motion Tensor (VMT) achieves an absolute improvement of 5.6% in mIoU over the baseline architecture. We also achieve state-of-the-art results on the public KITTI_MoSeg_Extended dataset even compared to methods which make use of LiDAR and additional input frames. Our model is also lightweight and runs at 85 fps on a TitanX GPU. Qualitative results are provided in https://youtu.be/ezbfjti-kTk.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Mathematical analysis ; Motion compensation ; Motion perception ; Moving object recognition ; Parallax ; Tensors ; Trajectory planning</subject><ispartof>arXiv.org, 2021-07</ispartof><rights>2021. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Rashed, Hazem</creatorcontrib><creatorcontrib>Ahmad El Sallab</creatorcontrib><creatorcontrib>Yogamani, Senthil</creatorcontrib><title>VM-MODNet: Vehicle Motion aware Moving Object Detection for Autonomous Driving</title><title>arXiv.org</title><description>Moving object Detection (MOD) is a critical task in autonomous driving as moving agents around the ego-vehicle need to be accurately detected for safe trajectory planning. It also enables appearance agnostic detection of objects based on motion cues. There are geometric challenges like motion-parallax ambiguity which makes it a difficult problem. In this work, we aim to leverage the vehicle motion information and feed it into the model to have an adaptation mechanism based on ego-motion. The motivation is to enable the model to implicitly perform ego-motion compensation to improve performance. We convert the six degrees of freedom vehicle motion into a pixel-wise tensor which can be fed as input to the CNN model. The proposed model using Vehicle Motion Tensor (VMT) achieves an absolute improvement of 5.6% in mIoU over the baseline architecture. We also achieve state-of-the-art results on the public KITTI_MoSeg_Extended dataset even compared to methods which make use of LiDAR and additional input frames. Our model is also lightweight and runs at 85 fps on a TitanX GPU. Qualitative results are provided in https://youtu.be/ezbfjti-kTk.</description><subject>Mathematical analysis</subject><subject>Motion compensation</subject><subject>Motion perception</subject><subject>Moving object recognition</subject><subject>Parallax</subject><subject>Tensors</subject><subject>Trajectory planning</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNis0KgkAYAJcgSMp3WOgs7E-r0S2y6KJewqtsstaK7Vf7U6-fQg_QaRhmZihinNNku2FsgWLnekIISzMmBI9QWRdJUeWl8jtcq7tuB4UL8BoMlh9pJ3lrc8PVtVetx7nyI6bagcX74MHAA4LDudXTt0LzTg5OxT8u0fp0vBzOydPCKyjnmx6CNWNqmKAZpSkngv93fQE5rD1C</recordid><startdate>20210711</startdate><enddate>20210711</enddate><creator>Rashed, Hazem</creator><creator>Ahmad El Sallab</creator><creator>Yogamani, Senthil</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20210711</creationdate><title>VM-MODNet: Vehicle Motion aware Moving Object Detection for Autonomous Driving</title><author>Rashed, Hazem ; Ahmad El Sallab ; Yogamani, Senthil</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_25171163053</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Mathematical analysis</topic><topic>Motion compensation</topic><topic>Motion perception</topic><topic>Moving object recognition</topic><topic>Parallax</topic><topic>Tensors</topic><topic>Trajectory planning</topic><toplevel>online_resources</toplevel><creatorcontrib>Rashed, Hazem</creatorcontrib><creatorcontrib>Ahmad El Sallab</creatorcontrib><creatorcontrib>Yogamani, Senthil</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Rashed, Hazem</au><au>Ahmad El Sallab</au><au>Yogamani, Senthil</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>VM-MODNet: Vehicle Motion aware Moving Object Detection for Autonomous Driving</atitle><jtitle>arXiv.org</jtitle><date>2021-07-11</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>Moving object Detection (MOD) is a critical task in autonomous driving as moving agents around the ego-vehicle need to be accurately detected for safe trajectory planning. It also enables appearance agnostic detection of objects based on motion cues. There are geometric challenges like motion-parallax ambiguity which makes it a difficult problem. In this work, we aim to leverage the vehicle motion information and feed it into the model to have an adaptation mechanism based on ego-motion. The motivation is to enable the model to implicitly perform ego-motion compensation to improve performance. We convert the six degrees of freedom vehicle motion into a pixel-wise tensor which can be fed as input to the CNN model. The proposed model using Vehicle Motion Tensor (VMT) achieves an absolute improvement of 5.6% in mIoU over the baseline architecture. We also achieve state-of-the-art results on the public KITTI_MoSeg_Extended dataset even compared to methods which make use of LiDAR and additional input frames. Our model is also lightweight and runs at 85 fps on a TitanX GPU. Qualitative results are provided in https://youtu.be/ezbfjti-kTk.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2021-07 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2517116305 |
source | Free E- Journals |
subjects | Mathematical analysis Motion compensation Motion perception Moving object recognition Parallax Tensors Trajectory planning |
title | VM-MODNet: Vehicle Motion aware Moving Object Detection for Autonomous Driving |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T18%3A53%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=VM-MODNet:%20Vehicle%20Motion%20aware%20Moving%20Object%20Detection%20for%20Autonomous%20Driving&rft.jtitle=arXiv.org&rft.au=Rashed,%20Hazem&rft.date=2021-07-11&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2517116305%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2517116305&rft_id=info:pmid/&rfr_iscdi=true |