基于超声波传感器阵列的车辆周围目标物识别

辛喆; 邹若冰; 李升波; 俞佳莹; 戴一凡; 陈海亮

doi:10.16511/j.cnki.qhdxxb.2017.21.033

PDF(5288 KB)

清华大学学报（自然科学版） ›› 2017, Vol. 57 ›› Issue (12) : 1287-1295. DOI: 10.16511/j.cnki.qhdxxb.2017.21.033

汽车工程

基于超声波传感器阵列的车辆周围目标物识别

辛喆¹, 邹若冰¹, 李升波², 俞佳莹², 戴一凡², 陈海亮¹

作者信息 +

Target recognition around a vehicle based on an ultrasonic sensor array

XIN Zhe¹, ZOU Ruobing¹, LI Shengbo², YU Jiaying², DAI Yifan², CHEN Hailiang¹

Author information +

文章历史 +

摘要

为了对车辆环境信息进行探测与识别，提高道路交通安全，该文研究了利用超声波传感器阵列识别车辆环境目标类型的方法：以分类器为核心，搭载目标物区分算法，实现对目标物的实时探测与区分。首先根据车辆周围环境信息提取了具有一定形状特征的典型目标物，分别为平板、圆柱和角形3种类型，以支持向量机（support vector machine，SVM）为分类器建立分类模型，根据目标物形状不同构造与优选分类特征指标集；依托分类结果建立目标物的类型区分算法，得到每一时刻各类目标物的概率值。仿真结果表明：分类模型的分类准确率达到91.5%；同时该方法对各种类型的目标物进行区分时，均达到较好的识别效果。在实际道路试验中，采集了汽车、行人和自行车3类目标物，采用该方法达到了良好的识别效果，具有可行性。

Abstract

Road traffic safety can be improved by detection and recognition of vehicle environment information. This paper describes a method for recognizing the environment target type by an ultrasonic sensor array. A high performance classifier is used in an object type discrimination algorithm for real-time target detection and identification. Three general shapes are identified as planes, cylinders and triangles by a support vector machine (SVM) classification model. The target shape is then extended to more specific features. The classification algorithm also gives the probability of each object at that moment. Simulations show that the classification models are 91.5% accurate which demonstrates that the object type discrimination algorithm can recognize environmental objects near the vehicle. In road test, the experimental platform collected data on road objects, such as vehicles, pedestrians and cyclists with good recognition accuracy.

导出引用

辛喆, 邹若冰, 李升波, 俞佳莹, 戴一凡, 陈海亮. 基于超声波传感器阵列的车辆周围目标物识别[J]. 清华大学学报（自然科学版）. 2017, 57(12): 1287-1295 https://doi.org/10.16511/j.cnki.qhdxxb.2017.21.033

XIN Zhe, ZOU Ruobing, LI Shengbo, YU Jiaying, DAI Yifan, CHEN Hailiang. Target recognition around a vehicle based on an ultrasonic sensor array[J]. Journal of Tsinghua University(Science and Technology). 2017, 57(12): 1287-1295 https://doi.org/10.16511/j.cnki.qhdxxb.2017.21.033

中图分类号： U461.91

参考文献

[1] Jackisch J, Sethi D, Mitis F, et al. 76 European facts and the global status report on road safety 2015[J]. Scientific Reports, 2016, 22(2):29-29.[2] 杨晓光, 陈白磊, 彭国雄. 行人交通控制信号设置方法研究[J]. 中国公路学报, 2001, 14(1):73-76.YANG Xiaoguang, CHEN Bailei, PENG Guoxiong. Study of the way of setting pedestrian's traffic control signal[J]. China Journal of Highway and Transport, 2001, 14(1):73-76. (in Chinese)[3] Li X, Flohr F, Yang Y, et al. A new benchmark for vision-based cyclist detection[C]//2016 IEEE Intelligent Vehicles Symposlum. Piscataway. NJ, USA:IEEE Press, 2016:1028-1033.[4] 刘琼, 陈雯柏. 基于视觉选择性注意与IHOG-LBP特征组合的行人目标快速检测[J]. 计算机应用研究, 2016, 33(1):281-285.LIU Qiong, CHEN Wenbai. Fast pedestrian detection method based on combinatory features IHOG-LBP and visual selective attention computation[J]. Application Research of Computers, 2016, 33(1):281-285. (in Chinese)[5] YANG Kai, LIU Chao, ZHENG Jiangyu, et al. Bicyclist detection in large scale naturalistic driving video[C]//201417th IEEE International Conference on Intelligent Transportation Systems. Piscataway, NJ, USA:IEEE Press, 2014:1638-1643.[6] Liang C W, Juang C F. Moving object classification using a combination of static appearance features and spatial and temporal entropy values of optical flows[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(6):3453-3464.[7] Taghvaeeyan S, Rajamani R. Portable roadside sensors for vehicle counting, classification, and speed measurement[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(1):73-83.[8] Hoon L J, Jong-Suk C, Som J E, et al. Robust pedestrian detection by combining visible and thermal infrared cameras[J]. Sensors, 2015, 15(5):10580-10615.[9] Medina J, Chitturi M, Benekohal R. Effects of fog, snow, and rain on video detection systems at intersections[J]. Transportation Letters the International Journal of Transportation Research, 2010, 2(1):1-12.[10] Park W J, Kim B S, Seo D E, et al. Parking space detection using ultrasonic sensor in parking assistance system[C]//4th IEEE Intelligent Vehicles Symposium 2008. Piscataway, NJ, USA:IEEE Press, 2008:1039-1044.[11] Kohler P, Connette C, Verl A. Vehicle tracking using ultrasonic sensors & joined particle weighting[C]//2013 IEEE International Conference on Robotics and Automation. Piscataway, NJ, USA:IEEE Press, 2013:2900-2905.[12] Mirus F, Pfadt J, Connette C, et al. Detection of moving and stationary objects at high velocities using cost-efficient sensors, curve-fitting and neural networks[C]//2012 IEEE International Conference on Intelligent Robots and Systems. Piscataway, NJ, USA:IEEE Press, 2012:7-12.[13] 丁刚, 王海波, 王智灵, 等. 基于支持向量机的移动机器人环境识别[J]. 计算机仿真, 2010, 27(9):186-190.DING Gang, WANG Haibo, WANG Zhiling, et al. Environment identification based on support vector machine for mobile robot[J]. Simulation of Computer, 2010, 27(9):186-190. (in Chinese)[14] 李晓妮, 刘树林. 超声波液位自动测报系统的设计[J]. 九江学院学报(自然科学版), 2006, 21(3):29-31.LI Xiaoni, LIU Shulin. Design of ultrasonic liquid level automatic forecasting system[J]. Journal of Jiujiang University (Sciences and Technology), 2006, 21(3):29-31. (in Chinese)[15] 陈春林, 陈宗海, 卓睿. 基于多超声波传感器的自主移动机器人探测系统[J]. 测控技术, 2004, 23(6):11-13.CHEN Chunlin, CHEN Zonghai, ZHUO Rui. Detecting system of multi-ultrasonic sensor based autonomous mobile robot[J]. Measurement and Control Technology, 2004, 23(6):11-13. (in Chinese)[16] Canali C, Cicco G D, Morten B, et al. A temperature compensated ultrasonic sensor operating in air for distance and proximity measurements[J]. IEEE Transactions on Industrial Electronics, 1982, 29(4):336-341.[17] 管婉青, 郭明俊, 刘尧, 等. 基于LabVIEW声速测量系统研究声速与温湿度的关系[J].物理试验, 2013, 33(8):7-9.GUAN Wanqing, GUO Mingjun, LIU Yao, et al. Measuring temperature and humidity dependent sound speed using LabVIEW[J]. Physics Exper Imentation, 2013, 33(8):7-9. (in Chinese)[18] 段渭军, 黄晓利, 王福豹, 等. 无线传感器网络测距技术的研究[C]//第一届中国传感器网络学术会议(CWSN 2007)论文集. 哈尔滨, 中国:计算机科学编辑部, 2007:54-62.DUAN Weijun, HUANG Xiaoli, WANG Fubao, et al. Research on ranging technique for wireless sensor networks[C]//The First China Wireless Sensor Network Conference (CWSN 2007) Proceedings. Haerbin, China:Computer Science Press, 2007:54-62. (in Chinese)[19] Song K T, Chen C H, Huang C H C. Design and experimental study of an ultrasonic sensor system for lateral collision avoidance at low speeds[C]//2004 IEEE Intelligent Vehicles Symposium. Piscataway, NJ, USA:IEEE Press, 2004:647-652.[20] 刘国良, 孙增圻. 基于超声波传感器的未知狭窄环境导航算法[J]. 传感器技术, 2005, 24(2):70-72.LIU Guoliang, SUN Zengqi. Navigating algorithm in narrow unknown environment based on ultrasonic sensors[J]. Journal of Transducer Technology, 2005, 24(2):70-72. (in Chinese)[21] 俞佳莹.车辆侧向目标的超声波传感器阵列感知研究[D].北京:清华大学, 2016.YU Jiaying. Ultrasonic Sensor Array Based Object Tracking in Car's Side Zone[D]. Beijing:Tsinghua University, 2016. (in Chinese)[22] 张文蓉.稳定分布噪声下基于FLOS的波束形成技术的研究[D].大连:大连理工大学, 2005.ZHANG Wenrong. Research of Beamforming Technology Based on FLOS for Impulsive Stable Noise[D]. Dalian:Dalian University of Technology, 2005. (in Chinese)[23] Chang C C, Lin C J.LIBSVM:A library for support vector machine[Z/OL].[2016-10-15]. http://www.csie.ntu,edu.tw/~cjlin/libsvm.[24] Hsu C W, Lin C J. A comparison of methods for multi-class support vector machines[J]. IEEE Transactions on Neural Network, 2002, 13(2):415-425.