A survey on 3D object detection in real time for autonomous driving
This survey reviews advances in 3D object detection approaches for autonomous driving. A brief introduction to 2D object detection is first discussed and drawbacks of the existing methodologies are identified for highly dynamic environments. Subsequently, this paper reviews the state-of-the-art 3D o...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2024-03-01
|
Series: | Frontiers in Robotics and AI |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/frobt.2024.1212070/full |
_version_ | 1797272647472513024 |
---|---|
author | Marcelo Contreras Aayush Jain Neel P. Bhatt Arunava Banerjee Ehsan Hashemi |
author_facet | Marcelo Contreras Aayush Jain Neel P. Bhatt Arunava Banerjee Ehsan Hashemi |
author_sort | Marcelo Contreras |
collection | DOAJ |
description | This survey reviews advances in 3D object detection approaches for autonomous driving. A brief introduction to 2D object detection is first discussed and drawbacks of the existing methodologies are identified for highly dynamic environments. Subsequently, this paper reviews the state-of-the-art 3D object detection techniques that utilizes monocular and stereo vision for reliable detection in urban settings. Based on depth inference basis, learning schemes, and internal representation, this work presents a method taxonomy of three classes: model-based and geometrically constrained approaches, end-to-end learning methodologies, and hybrid methods. There is highlighted segment for current trend of multi-view detectors as end-to-end methods due to their boosted robustness. Detectors from the last two kinds were specially selected to exploit the autonomous driving context in terms of geometry, scene content and instances distribution. To prove the effectiveness of each method, 3D object detection datasets for autonomous vehicles are described with their unique features, e. g., varying weather conditions, multi-modality, multi camera perspective and their respective metrics associated to different difficulty categories. In addition, we included multi-modal visual datasets, i. e., V2X that may tackle the problems of single-view occlusion. Finally, the current research trends in object detection are summarized, followed by a discussion on possible scope for future research in this domain. |
first_indexed | 2024-03-07T14:32:22Z |
format | Article |
id | doaj.art-ccb9ac105b494cd18827fe88f1509fdf |
institution | Directory Open Access Journal |
issn | 2296-9144 |
language | English |
last_indexed | 2024-03-07T14:32:22Z |
publishDate | 2024-03-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Robotics and AI |
spelling | doaj.art-ccb9ac105b494cd18827fe88f1509fdf2024-03-06T04:22:47ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442024-03-011110.3389/frobt.2024.12120701212070A survey on 3D object detection in real time for autonomous drivingMarcelo Contreras0Aayush Jain1Neel P. Bhatt2Arunava Banerjee3Ehsan Hashemi4University of Alberta, Edmonton, AB, CanadaIndian Institute of Technology Kharagpur, Kharagpur, West Bengal, IndiaUniversity of Alberta, Edmonton, AB, CanadaUniversity of Alberta, Edmonton, AB, CanadaUniversity of Alberta, Edmonton, AB, CanadaThis survey reviews advances in 3D object detection approaches for autonomous driving. A brief introduction to 2D object detection is first discussed and drawbacks of the existing methodologies are identified for highly dynamic environments. Subsequently, this paper reviews the state-of-the-art 3D object detection techniques that utilizes monocular and stereo vision for reliable detection in urban settings. Based on depth inference basis, learning schemes, and internal representation, this work presents a method taxonomy of three classes: model-based and geometrically constrained approaches, end-to-end learning methodologies, and hybrid methods. There is highlighted segment for current trend of multi-view detectors as end-to-end methods due to their boosted robustness. Detectors from the last two kinds were specially selected to exploit the autonomous driving context in terms of geometry, scene content and instances distribution. To prove the effectiveness of each method, 3D object detection datasets for autonomous vehicles are described with their unique features, e. g., varying weather conditions, multi-modality, multi camera perspective and their respective metrics associated to different difficulty categories. In addition, we included multi-modal visual datasets, i. e., V2X that may tackle the problems of single-view occlusion. Finally, the current research trends in object detection are summarized, followed by a discussion on possible scope for future research in this domain.https://www.frontiersin.org/articles/10.3389/frobt.2024.1212070/full3D object detectionautonomous navigationvisual navigationrobot perceptionautomated driving systems (ADS)visual-aided decision |
spellingShingle | Marcelo Contreras Aayush Jain Neel P. Bhatt Arunava Banerjee Ehsan Hashemi A survey on 3D object detection in real time for autonomous driving Frontiers in Robotics and AI 3D object detection autonomous navigation visual navigation robot perception automated driving systems (ADS) visual-aided decision |
title | A survey on 3D object detection in real time for autonomous driving |
title_full | A survey on 3D object detection in real time for autonomous driving |
title_fullStr | A survey on 3D object detection in real time for autonomous driving |
title_full_unstemmed | A survey on 3D object detection in real time for autonomous driving |
title_short | A survey on 3D object detection in real time for autonomous driving |
title_sort | survey on 3d object detection in real time for autonomous driving |
topic | 3D object detection autonomous navigation visual navigation robot perception automated driving systems (ADS) visual-aided decision |
url | https://www.frontiersin.org/articles/10.3389/frobt.2024.1212070/full |
work_keys_str_mv | AT marcelocontreras asurveyon3dobjectdetectioninrealtimeforautonomousdriving AT aayushjain asurveyon3dobjectdetectioninrealtimeforautonomousdriving AT neelpbhatt asurveyon3dobjectdetectioninrealtimeforautonomousdriving AT arunavabanerjee asurveyon3dobjectdetectioninrealtimeforautonomousdriving AT ehsanhashemi asurveyon3dobjectdetectioninrealtimeforautonomousdriving AT marcelocontreras surveyon3dobjectdetectioninrealtimeforautonomousdriving AT aayushjain surveyon3dobjectdetectioninrealtimeforautonomousdriving AT neelpbhatt surveyon3dobjectdetectioninrealtimeforautonomousdriving AT arunavabanerjee surveyon3dobjectdetectioninrealtimeforautonomousdriving AT ehsanhashemi surveyon3dobjectdetectioninrealtimeforautonomousdriving |