Please wait a minute...
 首页  期刊介绍 期刊订阅 联系我们 横山亮次奖 百年刊庆
 
最新录用  |  预出版  |  当期目录  |  过刊浏览  |  阅读排行  |  下载排行  |  引用排行  |  横山亮次奖  |  百年刊庆
清华大学学报(自然科学版)  2018, Vol. 58 Issue (4): 438-444    DOI: 10.16511/j.cnki.qhdxxb.2018.21.010
  汽车工程 本期目录 | 过刊浏览 | 高级检索 |
基于深度学习的自动驾驶技术综述
张新钰1, 高洪波2, 赵建辉3, 周沫2
1. 清华大学 信息技术中心, 北京 100084;
2. 清华大学 汽车安全与节能国家重点实验室, 北京 100084;
3. 清华大学 计算机科学与技术系, 北京 100084
Overview of deep learning intelligent driving methods
ZHANG Xinyu1, GAO Hongbo2, ZHAO Jianhui3, ZHOU Mo2
1. Information Technology Center, Tsinghua University, Beijing 100084, China;
2. State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing 100084, China;
3. Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
全文: PDF(2102 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 该文在行人检测技术方面介绍了基于卷积神经网络(CNN)模型的目标识别、检测技术与改进的区域卷积神经网络(R-CNN)、任务辅助卷积神经网络(TA-CNN)模型技术。在立体匹配技术方面简述了基于孪生网络的立体匹配的深度学习模型技术。在多传感器融合技术方面回顾了基于深度学习网络的视觉传感器、雷达传感器与摄像机传感器的多源数据融合技术。在汽车控制技术方面分析了基于卷积神经网络实现无人驾驶车辆端到端的横向与纵向控制技术。深度学习技术在自动驾驶领域的感知层、决策层与控制层的广泛运用,不断地提高感知、检测、决策与控制的准确率,并取得一定的成功,分析表明深度学习技术将加速自动驾驶技术的发展速度,为自动驾驶成为现实带来巨大的可能性。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
张新钰
高洪波
赵建辉
周沫
关键词 计算机视觉深度学习无人驾驶车辆传感器    
Abstract:This paper introduces target recognition and detection methods based on the convolutional neural network (CNN) model, the improved regions with convolutional neural network (R-CNN) and the task-assistant convolutional neural network (TA-CNN) model for pedestrian detection. This paper also describes stereo matching based on a deep learning model for stereo matching using the Siamese network. Multi-source data fusion is also introduced based on a vision sensor, a radar sensor and a camera using a deep learning network. The CNN is used for end-to-end horizontal and vertical control of autonomous vehicles. Deep learning is widely used in the perception level, decision-making level and control level in automatic driving systems to continuously improve the perception, detection, decision-making and control accuracy. Analyses show that deep learning will improve of autonomous driving systems.
Key wordscomputer vision    deep learning    autonomous vehicle    sensor
收稿日期: 2017-12-30      出版日期: 2018-04-15
ZTFLH:  TP399  
基金资助:国家重点研究和发展计划(2016YFB0100903);北京市科学技术委员会重大专项(d171100005017002,d171100005117002);中国博士后基金(2017M620765)
通讯作者: 高洪波,助理研究员,E-mail:ghb48@tsinghu.edu.cn     E-mail: ghb48@tsinghu.edu.cn
作者简介: 张新钰(1974-),男,副研究员。
引用本文:   
张新钰, 高洪波, 赵建辉, 周沫. 基于深度学习的自动驾驶技术综述[J]. 清华大学学报(自然科学版), 2018, 58(4): 438-444.
ZHANG Xinyu, GAO Hongbo, ZHAO Jianhui, ZHOU Mo. Overview of deep learning intelligent driving methods. Journal of Tsinghua University(Science and Technology), 2018, 58(4): 438-444.
链接本文:  
http://jst.tsinghuajournals.com/CN/10.16511/j.cnki.qhdxxb.2018.21.010  或          http://jst.tsinghuajournals.com/CN/Y2018/V58/I4/438
  图1 谷歌无人驾驶车辆架构
  表1 行人检测方法
  表1 行人检测方法
  图3 双目系统获取深度信息原理图 <sup>[22]</sup>
  图4 孪生深度网络原理图
  图5 雷达的密度深度图及对应的 HHA特征图
  图6 3种无人驾驶控制方案
[1] DÖRR D, GRABENGIESSER D, GAUTERIN F. Online driving style recognition using fuzzy logic[C]//Proceedings of the 17th International Conference on Intelligent Transportation Systems (ITSC). Qingdao, China:IEEE, 2014:1021-1026.
[2] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, CA, USA:IEEE, 2005, 1:886-893.
[3] WU B, NEVATIA R. Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors[C]//Proceedings of the 10th IEEE International Conference on Computer Vision. Beijing, China:IEEE, 2005, 1:90-97.
[4] GAVRILA D M. A Bayesian, exemplar-based approach to hierarchical shape matching[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(8):1408-1421.
[5] MU Y D, YAN S C, LIU Y, et al. Discriminative local binary patterns for human detection in personal album[C]//Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, Alaska, USA:IEEE, 2008:1-8.
[6] WANG X Y, HAN T X, YAN S C. An HOG-LBP human detector with partial occlusion handling[C]//Proceedings of the 12th International Conference on Computer Vision. Kyoto, Japan:IEEE, 2009:32-39.
[7] TUZEL O, PORIKLI F, MEER P. Pedestrian detection via classification on Riemannian manifolds[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(10):1713-1727.
[8] WATANABE T, ITO S, YOKOI K. Co-occurrence histograms of oriented gradients for human detection[J]. IPSJ Transactions on Computer Vision and Applications, 2010, 2:39-47.
[9] DOLLAR P, TU Z W, PERONA P, et al. Integral channel features[C]//Proceedings of the British Machine Vision Conference. London, UK:BMVC, 2009:1-11.
[10] GAO W, AI H Z, LAO S H. Adaptive Contour Features in oriented granular space for human detection and segmentation[C]//Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL, USA:IEEE, 2009:1786-1793.
[11] LIU Y Z, SHAN S G, ZHANG W C, et al. Granularity-tunable gradients partition (GGP) descriptors for human detection[C]//Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL, USA:IEEE, 2009:1255-1262.
[12] WU J X, GEYER C, REHG J M. Real-time human detection using contour cues[C]//Proceedings of the 2011 IEEE International Conference on Robotics and Automation. Shanghai, China:IEEE, 2011:860-867.
[13] WALK S, MAJER N, SCHINDLER K, et al. New features and insights for pedestrian detection[C]//Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco, CA, USA:IEEE, 2010:1030-1037.
[14] PLÖCHL M, EDELMANN J. Driver models in automobile dynamics application[J]. Vehicle System Dynamics, 2007, 45(7-8):699-741.
[15] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA:IEEE, 2014:580-587.
[16] WALLACE B, GOUBRAN R, KNOEFEL F, et al. Measuring variation in driving habits between drivers[C]//Proceedings of the 2014 IEEE International Symposium on Medical Measurements and Applications. Lisboa, Portugal:IEEE, 2014:1-6.
[17] GIRSHICK R. Fast R-CNN[C]//Proceedings of the 2015 IEEE International conference on Computer Vision. Santiago, Chile:IEEE, 2015:1440-1448.
[18] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN:Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.
[19] TIAN Y L, LUO P, WANG X G, et al. Pedestrian detection aided by deep learning semantic tasks[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA:IEEE, 2015:5079-5087.
[20] LUO L H. Adaptive cruise control design with consideration of humans' driving psychology[C]//Proceedings of the 11th World Congress on Intelligent Control and Automation. Shenyang, China:IEEE, 2014:2973-2978.
[21] PACHECO J E, LÓPEZ E. Monitoring driving habits through an automotive CAN network[C]//Proceedings of the 23rd International Conference on Electronics, Communications and Computing. Cholula, Mexico:IEEE, 2013:138-143.
[22] MVHLMANN K, MAIER D, HESSER J, et al. Calculating dense disparity maps from color stereo images, an efficient implementation[J]. International Journal of Computer Vision, 2002, 47(1-3):79-88.
[23] CHOPRA S, HADSELL R, LECUN Y. Learning a similarity metric discriminatively, with application to face verification[C]//Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, CA, USA:IEEE, 2005, 1:539-546.
[24] LUO W J, SCHWING A G, URTASUN R. Efficient deep learning for stereo matching[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA:IEEE, 2016:5695-5703.
[25] BUTAKOV V, IOANNOU P. Driving autopilot with personalization feature for improved safety and comfort[C]//Proceedings of the 18th International Conference on Intelligent Transportation Systems. Las Palmas, Spain:IEEE, 2015:387-393.
[26] ALJAAFREH A, ALSHABATAT N, NAJIM AL-DIN M S. Driving style recognition using fuzzy logic[C]//Proceedings of the 2012 IEEE International Conferenceon Vehicular Electronics and Safety. Istanbul, Turkey:IEEE, 2012:460-463.
[27] JOHNSON D A, TRIVEDI M M. Driving style recognition using a smartphone as a sensor platform[C]//Proceedings of the 14th International IEEE Conference on Intelligent Transportation Systems. Washington, DC, USA:IEEE, 2011:1609-1615.
[28] SCHLOSSER J, CHOW C K, KIRA Z. Fusing LIDAR and images for pedestrian detection using convolutional neural networks[C]//Proceedings of the2016 IEEE International Conference on Robotics and Automation. Stockholm, Sweden:IEEE, 2016:2198-2205.
[29] VAN LY M, MARTIN S, TRIVEDI M M. Driver classification and driving style recognition using inertial sensors[C]//Proceedings of the 2013 IEEE Intelligent Vehicles Symposium (IV). Gold Coast, QLD, Australia:IEEE, 2013:1040-1045.
[30] POMERLEAU D A. ALVINN:An autonomous land vehicle in a neural network[C]//Advances in Neural Information Processing Systems. San Francisco, CA, USA:ACM, 1989:305-313.
[31] BOJARSKI M, DEL TESTA D, DWORAKOWSKI D, et al. End to end learning for self-driving cars[J/OL]. (2016-04-25). http://arxiv.org/pdf/1604.07316.pdf.
[32] CHEN C Y, SEFF A, KORNHAUSER A, et al. DeepDriving:Learning affordance for direct perception in autonomous driving[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Santiago, Chile:IEEE, 2015:2722-2730.
[1] 王志国, 章毓晋. 监控视频异常检测:综述[J]. 清华大学学报(自然科学版), 2020, 60(6): 518-529.
[2] 蒋文斌, 王宏斌, 刘湃, 陈雨浩. 基于AVX2指令集的深度学习混合运算策略[J]. 清华大学学报(自然科学版), 2020, 60(5): 408-414.
[3] 余传明, 原赛, 胡莎莎, 安璐. 基于深度学习的多语言跨领域主题对齐模型[J]. 清华大学学报(自然科学版), 2020, 60(5): 430-439.
[4] 庞齐齐, 张丽霞, 何一超, 宫正, 冯占宗, 陈亚龙, 危银涛, 杜永昌. 磁流变半主动悬架控制算法验证平台[J]. 清华大学学报(自然科学版), 2019, 59(7): 567-574.
[5] 孙博文, 朱志明, 郭吉昌, 张天一. 基于组合激光结构光的视觉传感器检测算法及图像处理流程优化[J]. 清华大学学报(自然科学版), 2019, 59(6): 445-452.
[6] 张继文, 宋立滨, 许君杰, 石循磊, 刘莉. 仿人足球机器人的非预定义足球检测算法[J]. 清华大学学报(自然科学版), 2019, 59(4): 298-305.
[7] 张思聪, 谢晓尧, 徐洋. 基于dCNN的入侵检测方法[J]. 清华大学学报(自然科学版), 2019, 59(1): 44-52.
[8] 芦效峰, 蒋方朔, 周箫, 崔宝江, 伊胜伟, 沙晶. 基于API序列特征和统计特征组合的恶意样本检测框架[J]. 清华大学学报(自然科学版), 2018, 58(5): 500-508.
[9] 于金鹏, 周燕, 莫逆, 刘兴男, 赵雷. 基于FPGA的数字化电涡流位移传感器设计[J]. 清华大学学报(自然科学版), 2018, 58(3): 330-336.
[10] 邹权臣, 张涛, 吴润浦, 马金鑫, 李美聪, 陈晨, 侯长玉. 从自动化到智能化:软件漏洞挖掘技术进展[J]. 清华大学学报(自然科学版), 2018, 58(12): 1079-1094.
[11] 季建朝, 张宇, 王明新. 声传感器阵列风洞测量结果优化[J]. 清华大学学报(自然科学版), 2018, 58(1): 94-100.
[12] 苘大鹏, 王臣业, 杨武, 王巍, 玄世昌, 靳小鹏. 低能耗的无线传感器网络隐私数据融合方法[J]. 清华大学学报(自然科学版), 2017, 57(2): 213-219.
[13] 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.
[14] 强茂山, 张东成, 江汉臣. 基于加速度传感器的建筑工人施工行为识别方法[J]. 清华大学学报(自然科学版), 2017, 57(12): 1338-1344.
[15] 刘一民, 文俊杰, 王岚君. 基于空-时近邻与似然比检验的传感器网络异常点检测[J]. 清华大学学报(自然科学版), 2017, 57(11): 1196-1201.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 《清华大学学报(自然科学版)》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn