A Real-time Pedestrian Detection System based on Structure and Appearance Classification

被引:10
作者
Bansal, Mayank [1 ]
Jung, Sang-Hack [1 ]
Matei, Bogdan [1 ]
Eledath, Jayan [1 ]
Sawhney, Harpreet [1 ]
机构
[1] Sarnoff Corp, Vis Technol, Princeton, NJ 08540 USA
来源
2010 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) | 2010年
关键词
D O I
10.1109/ROBOT.2010.5509841
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We present a real-time pedestrian detection system based on structure and appearance classification. We discuss several novel ideas that contribute to having low-false alarms and high detection rates, while at the same time achieving computational efficiency: (i) At the front end of our system we employ stereo to detect pedestrians in 3D range maps using template matching with a representative 3D shape model, and to classify other background objects in the scene such as buildings, trees and poles. The structure classification efficiently labels substantial amount of non-relevant image regions and guides the further computationally expensive process to focus on relatively small image parts; (ii) We improve the appearance-based classifiers based on HoG descriptors by performing template matching with 2D human shape contour fragments that results in improved localization and accuracy; (iii) We build a suite of classifiers tuned to specific distance ranges for optimized system performance. Our method is evaluated on publicly available datasets and is shown to match or exceed the performance of leading pedestrian detectors in terms of accuracy as well as achieving real-time computation (10 Hz), which makes it adequate for in-vehicle navigation platform.
引用
收藏
页码:903 / 909
页数:7
相关论文
共 50 条
[21]   Real-time pedestrian detection based on improved YOLO model [J].
Zhao, Congcong ;
Chen, Bin .
2019 11TH INTERNATIONAL CONFERENCE ON INTELLIGENT HUMAN-MACHINE SYSTEMS AND CYBERNETICS (IHMSC 2019), VOL 2, 2019, :25-28
[22]   Design of Real-time Detection System for Fruits Appearance Quality [J].
He, Fang ;
Zhang, Yunwei ;
Jiang, Tao .
2011 3RD WORLD CONGRESS IN APPLIED COMPUTING, COMPUTER SCIENCE, AND COMPUTER ENGINEERING (ACC 2011), VOL 3, 2011, 3 :587-+
[23]   A Real-Time Pedestrian Animation System [J].
Schulz, Christian ;
Schultz, Michael ;
Fricke, Hartmut .
PEDESTRIAN AND EVACUATION DYNAMICS 2008, 2010, :811-817
[24]   Design and Evaluation of a Real-time Pedestrian Detection System for Autonomous Vehicles [J].
Pranav, K. B. ;
Manikandan, J. .
2020 ZOOMING INNOVATION IN CONSUMER TECHNOLOGIES CONFERENCE (ZINC), 2020, :155-159
[25]   Real-time pedestrian detection system with novel thermal features at night [J].
Lin, Chun-Fu ;
Lin, Sheng-Fuu ;
Hwang, Chi-Hung ;
Chen, Yu-Chieh .
2014 IEEE INTERNATIONAL INSTRUMENTATION AND MEASUREMENT TECHNOLOGY CONFERENCE (I2MTC) PROCEEDINGS, 2014, :1329-1333
[26]   Real-time Pedestrian Detection for Autonomous Driving [J].
Yang, Zhiheng ;
Li, Jun ;
Li, Huiyun .
2018 INTERNATIONAL CONFERENCE ON INTELLIGENT AUTONOMOUS SYSTEMS (ICOIAS), 2018, :9-13
[27]   Real-time Pedestrian Traffic Light Detection [J].
Ash, Roni ;
Ofri, Dolev ;
Brokman, Jonathan ;
Friedman, Idan ;
Moshe, Yair .
2018 IEEE INTERNATIONAL CONFERENCE ON THE SCIENCE OF ELECTRICAL ENGINEERING IN ISRAEL (ICSEE), 2018,
[28]   Real-time pedestrian detection using eigenflow [J].
Goel, Dhiraj ;
Chen, Tsuhan .
2007 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-7, 2007, :1357-1360
[29]   Dataset Optimization for Real-Time Pedestrian Detection [J].
Trichet, Remi ;
Bremond, Francois .
IEEE ACCESS, 2018, 6 :7719-7727
[30]   Improved Real-time Pedestrian Detection Method [J].
Zhao, Zhiming ;
Lei, Xiaoyong .
PROCEEDINGS OF 2019 IEEE 7TH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND NETWORK TECHNOLOGY (ICCSNT 2019), 2019, :298-302