Deep Neural Network Based Vehicle and Pedestrian Detection for Autonomous Driving: A Survey

doi:10.1109/TITS.2020.2993926

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 平行智能技术与系统团队

	Deep Neural Network Based Vehicle and Pedestrian Detection for Autonomous Driving: A Survey
	Chen, Long 1; Lin, Shaobo 1; Lu, Xiankai 2; Cao, Dongpu 3; Wu, Hangbin 4; Guo, Chi 5; Liu, Chun 4; Wang, Fei-Yue6
发表期刊	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
ISSN	1524-9050
	2021-06-01
卷号	22 期号:6 页码:3234-3246
通讯作者	Cao, Dongpu(dongpu@uwaterloo.ca)
摘要	Vehicle and pedestrian detection is one of the critical tasks in autonomous driving. Since heterogeneous techniques have been proposed, the selection of a detection system with an appropriate balance among detection accuracy, speed and memory consumption for a specific task has become very challenging. To deal with this issue and to provide guidance for model selection, this paper analyzes several mainstream object detection architectures, including Faster R-CNN, R-FCN, and SSD, along with several typical feature extractors, such as ResNet50, ResNet101, MobileNet_V1, MobileNet_V2, Inception_V2 and Inception_ResNet_V2. By conducting extensive experiments using the KITTI benchmark, which is a commonly used street dataset, we demonstrate that Faster R-CNN ResNet50 obtains the best average precision (AP) (58%) for vehicle and pedestrian detection, with a speed of 8.6 FPS. Faster R-CNN Inception_V2 performs best for detecting cars and detecting pedestrians respectively (74.5% and 47.3%). ResNet101 consumes the highest memory (9907 MB) and has the largest number of parameters (64.42 millions), and Inception_ResNet_V2 is the slowest model (3.05 FPS). SSD MobileNet_V2 is the fastest model (70 FPS), and SSD MobileNet_V1 is the lightest model in terms of memory usage (875 MB), both of which are suitable for applications on mobile and embedded devices.
关键词	Deep neural networks autonomous driving vehicle detection pedestrian detection survey
DOI	10.1109/TITS.2020.2993926
关键词[WOS]	OBJECT DETECTION ; REPRESENTATION ; LOCALIZATION ; RECOGNITION ; REGION ; SCALE
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2018YFB1305002]
项目资助者	National Key Research and Development Program of China
WOS研究方向	Engineering ; Transportation
WOS类目	Engineering, Civil ; Engineering, Electrical & Electronic ; Transportation Science & Technology
WOS记录号	WOS:000658360600002
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：87[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/45356
专题	多模态人工智能系统全国重点实验室_平行智能技术与系统团队
通讯作者	Cao, Dongpu
作者单位	1.Sun Yat Sen Univ, Sch Data & Comp Sci, Guangzhou 510275, Peoples R China 2.Incept Inst Artificial Intelligence, Abu Dhabi, U Arab Emirates 3.Univ Waterloo, Waterloo Cognit Autonomous Driving CogDr Lab, Waterloo, ON N2L 3G1, Canada 4.Tongji Univ, Coll Surveying & Geoinformat, Shanghai 200092, Peoples R China 5.Wuhan Univ, Natl Satellite Positioning Syst Engn Technol Res, Wuhan 430072, Peoples R China 6.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Chen, Long,Lin, Shaobo,Lu, Xiankai,et al. Deep Neural Network Based Vehicle and Pedestrian Detection for Autonomous Driving: A Survey[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2021,22(6):3234-3246.
APA	Chen, Long.,Lin, Shaobo.,Lu, Xiankai.,Cao, Dongpu.,Wu, Hangbin.,...&Wang, Fei-Yue.(2021).Deep Neural Network Based Vehicle and Pedestrian Detection for Autonomous Driving: A Survey.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,22(6),3234-3246.
MLA	Chen, Long,et al."Deep Neural Network Based Vehicle and Pedestrian Detection for Autonomous Driving: A Survey".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 22.6(2021):3234-3246.