[1]杨会成,朱文博,童英.基于车内外视觉信息的行人碰撞预警方法[J].智能系统学报,2019,14(04):752-760.[doi:10.11992/tis.201801016]
 YANG Huicheng,ZHU Wenbo,TONG Ying.Pedestrian collision warning system based on looking-in and looking-out visual information analysis[J].CAAI Transactions on Intelligent Systems,2019,14(04):752-760.[doi:10.11992/tis.201801016]
点击复制

基于车内外视觉信息的行人碰撞预警方法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第14卷
期数:
2019年04期
页码:
752-760
栏目:
出版日期:
2019-07-02

文章信息/Info

Title:
Pedestrian collision warning system based on looking-in and looking-out visual information analysis
作者:
杨会成 朱文博 童英
安徽工程大学 电气工程学院, 安徽 芜湖 241000
Author(s):
YANG Huicheng ZHU Wenbo TONG Ying
College of Electrical Engineering, Anhui Polytechnic University, Wuhu 241000, China
关键词:
碰撞预警内外信息行人定位驾驶员状态单目视觉通道特征多任务级联卷积网络模糊推理系统
Keywords:
collision warninginternal and external informationpedestrian positioningdriver statesmonocular visionchannel featuresmulti-task cascaded convolutional networkfuzzy inference system
分类号:
TP181
DOI:
10.11992/tis.201801016
摘要:
行人碰撞预警系统通常依据行人检测与碰撞时间判断的方式为驾驶员提供预警信息。为了提供更加可靠的危险判断依据,本文提出一种同时分析道路状况与驾驶员头部姿态的行人碰撞预警方法,用两个单目相机分别获取车辆内外环境图像。通道特征检测器用于定位行人,根据单目视觉距离测量方法估计出行人与自车间的纵向与横向距离。多任务级联卷积网络用于定位驾驶员面部特征点,通过求解多点透视问题获取头部方向角以反映驾驶员注意状态。结合行人位置信息与驾驶员状态信息,本文构建模糊推理系统判断碰撞风险等级。在实际路况下的实验结果表明,根据模糊系统输出的风险等级可以为预防碰撞提供有效的指导。
Abstract:
Pedestrian collision warning systems usually provide early warning for drivers based on the technologies of pedestrian detection and collision time measurement. To provide a more reliable basis for risk assessment, a pedestrian collision warning method that involves analyzing the road condition and driver’s head pose simultaneously is proposed in this paper. Two monocular cameras are used to capture vehicle exterior and interior images, and a channel features detector is applied to locate pedestrians. The vertical and horizontal distances between pedestrians and ego-vehicle are estimated based on monocular vision distance measurement. The multi-task cascaded convolutional network is utilized for facial landmark detection. By solving a perspective-n-point (PnP) problem, the estimated head angles can reflect driver’s attention states. By combining both pedestrian location information and driver’s attention information, we implemented a fuzzy inference system to assess collision risk level. An experiment in real-world driving conditions demonstrated that the risk levels obtained from the fuzzy system are reliable and can provide guidance for collision avoidance.

参考文献/References:

[1] VIOLA P, JONES M. Rapid object detection using a boosted cascade of simple features[C]//Proceedings of 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Kauai, USA, 2001:I-511-I-518.
[2] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA, 2005:886-893.
[3] FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D, et al. Object detection with discriminatively trained part-based models[J]. IEEE Transactions on pattern analysis and machine intelligence, 2010, 32(9):1627-1645.
[4] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA, 2014:580-587.
[5] GIRSHICK R. Fast R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, USA, 2015:1440-1448.
[6] STANTON N A, SALMON P M. Human error taxonomies applied to driving:a generic driver error taxonomy and its implications for intelligent transport systems[J]. Safety science, 2009, 47(2):227-237.
[7] TAWARI A, MARTIN S, TRIVEDI M M. Continuous head movement estimator for driver assistance:issues, algorithms, and on-road evaluations[J]. IEEE transactions on intelligent transportation systems, 2014, 15(2):818-830.
[8] COOTES T F, EDWARDS G J, TAYLOR C J. Active appearance models[J]. IEEE transactions on pattern analysis and machine intelligence, 2001, 23(6):681-685.
[9] REN Shaoqing, CAO Xudong, WEI Yichen, et al. Face alignment at 3000 fps via regressing local binary features[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA, 2014:1685-1692.
[10] SUN Yi, WANG Xiaogang, TANG Xiaoou. Deep convolutional network cascade for facial point detection[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA, 2013:3476-3483.
[11] ZHANG Kaipeng, ZHANG Zhanpeng, LI Zhifeng, et al. Joint face detection and alignment using multitask cascaded convolutional networks[J]. IEEE Signal processing letters, 2016, 23(10):1499-1503.
[12] DOLLÁR P, APPEL R, BELONGIE S, et al. Fast feature pyramids for object detection[J]. IEEE transactions on pattern analysis and machine intelligence, 2014, 36(8):1532-1545.
[13] BOURDEV L, BRANDT J. Robust object detection via soft cascade[C]//Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA, 2005:236-243.
[14] 王牛, 李祖枢, 武德臣, 等. 机器人单目视觉定位模型及其参数辨识[J]. 华中科技大学学报(自然科学版), 2008, 36(S1):57-60 WANG Niu, LI Zushu, WU Dechen, et al. Robot monocular vision position determination model and its parametric identification[J]. Journal of Huazhong University of Science and Technology (Nature Science Edition), 2008, 36(S1):57-60
[15] LEPETIT V, MORENO-NOGUER F, FUA P. EPnP:an accurate O(n) solution to the PnP problem[J]. International journal of computer vision, 2009, 81(2):155-166.
[16] TAWARI A, SIVARAMAN S, TRIVEDI M M, et al. Looking-in and looking-out vision for Urban Intelligent Assistance:estimation of driver attentive state and dynamic surround for safe merging and braking[C]//Proceedings of 2014 IEEE Intelligent Vehicles Symposium. Dearborn, USA, 2014:115-120.
[17] TATEIWA K, YAMADA K. Estimating driver awareness of pedestrians in crosswalk in the path of right or left turns at an intersection from vehicle behavior[C]//Proceedings of 2015 IEEE Intelligent Vehicles Symposium. Seoul, South Korea, 2015:952-957.
[18] ROTH M, FLOHR F, GAVRILA D M. Driver and pedestrian awareness-based collision risk analysis[C]//Proceedings of 2016 IEEE Intelligent Vehicles Symposium. Gothenburg, Sweden, 2016:454-459.

备注/Memo

备注/Memo:
收稿日期:2018-01-08。
基金项目:安徽省高校自然科学研究重点项目(KJ2018A0122).
作者简介:杨会成,男,1970年生,教授,主要研究方向为图像信息处理、疲劳驾驶检测。主持和参与安徽省自然科学基金项目、安徽省高校自然科学基金项目6项。发表学术论文15篇;朱文博,男,1992年生,硕士研究生,主要研究方向为图像处理与模式识别;童英,女,1993年生,硕士研究生,主要研究方向为图像处理与模式识别。
通讯作者:朱文博.E-mail:vembozhu@163.com
更新日期/Last Update: 2019-08-25