1.中国科学院计算技术研究所, 北京 100190
2.中国科学院大学, 北京 100049
3.北京邮电大学信息与通信工程学院, 北京 100876
4.北京邮电大学国际学院, 北京 100876
[ "徐频捷 男,1997年生于江西上饶.现为中科院计算技术研究所硕士研究生.E‑mail:xupinjie19g@ict.ac.cn" ]
[ "陈逸杰 男,1999年生于云南昆明.现为北京邮电大学信息与通信工程学院本科生.E‑mail:yj‑chen@bupt.edu.cn" ]
[ "李之南 男,1998年生于新疆乌鲁木齐.现为北京邮电大学本科生.主要研究方向为深度学习加速器,机器学习.E‑mail:a710859414@bupt.edu.cn" ]
[ "赵 地(通信作者) 男, 1978年生于湖南岳阳. 现为中科院计算技术研究所副研究员,主要研究方向为类脑计算和深度学习.E‑mail: zhaodi@ncic.ac.cn" ]
收稿:2020-12-01,
修回:2021-02-22,
纸质出版:2021-07-25
移动端阅览
徐频捷,陈逸杰,李之南等.基于事件驱动的车道线识别算法研究[J].电子学报,2021,49(07):1379-1385.
XU Pin-jie,CHEN Yi-jie,LI Zhi-nan,et al.Research on Event‑Driven Lane Recognition Algorithms[J].ACTA ELECTRONICA SINICA,2021,49(07):1379-1385.
徐频捷,陈逸杰,李之南等.基于事件驱动的车道线识别算法研究[J].电子学报,2021,49(07):1379-1385. DOI: 10.12263/DZXB.20201375.
XU Pin-jie,CHEN Yi-jie,LI Zhi-nan,et al.Research on Event‑Driven Lane Recognition Algorithms[J].ACTA ELECTRONICA SINICA,2021,49(07):1379-1385. DOI: 10.12263/DZXB.20201375.
动态视觉传感器(Dynamic Vision Sensor,DVS)相比于传统彩色相机有更高的时间分辨率、动态范围,且功耗更低、带宽更低,在自动驾驶领域有很好的应用前景,因此吸引了越来越多研究者的注意.然而由于事件驱动的数据是异步的且缺少一种统一的表示形式,在复杂的交通场景下,以车道检测为代表的基于事件驱动数据的交通场景分割任务难以应用传统的语义分割算法.针对以上问题,本文提出了一种三通道的事件数据编码方式,综合考虑事件数据的时空特征,将其作为卷积神经网络的输入;提出了一种基于编解码模型的事件数据车道检测算法,在基于事件驱动的车道线检测数据集DET上,本文方法的mIoU(mean Intersection over Union)达到了58.76%,比基准方法提高了4.4%.
Compared with the traditional color cameras
the dynamic vision sensor
a type of event‑based sensor
has higher time resolution
dynamic range
lower power consumption and lower bandwidth requirements. It has good application prospects in the field of automatic driving
which attracts more and more researchers’ attention. However
event‑driven data is asynchronous and lacks a unified representation. At the same time
in the complex traffic scenario
the traditional semantic segmentation model is difficult to be applied to the event‑driven data‑based traffic scene segmentation task
for instance
the lane detection task. In view of the above problems
our study proposes a three‑channel encoding method for event data
which is successfully used as the input of convolution neural network by considering the spatio‑temporal characteristics of event data comprehensively. This paper also proposes a lane segmentation algorithm based on encoding‑decoding model
which is superior to the traditional event‑based lane line segmentation. On the DET data set
with mIoU(mean Intersection over Union) as the evaluation index
this paper reaches 58.76%
which is 4.4% higher than the benchmark.
HILLEL A B , LERNER R , et al . Recent progress in road and lane detection: a survey [J]. Machine Vision and Applications , 2014 , 25 ( 3 ): 727 - 745 .
GALLEGO G , LUND J E A , et al . Event‑based, 6‑DOF camera tracking from photometric depth maps [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2018 , 40 ( 10 ): 2402 - 2412 .
CHEN N F Y . Pseudo‑labels for supervised learning on dynamic vision sensor data , applied to object detection under ego‑motion[A]. Proceedings 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops [C]. Salt Lake City : IEEE , 2018 . 757 - 766 .
BINAS J , NEIL D , et al . DDD17: End‑to‑end DAVIS Driving Dataset [EB/OL]. https://arxiv.org/abs/1711.01458 https://arxiv.org/abs/1711.01458 , 2017 .
CHENG W , LUO H , et al . DET: a high‑resolution DVS dataset for lane extraction [A]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops [C]. Long Beach : IEEE , 2019 . 1666 - 1675 .
ALONSO I , MURILLO A C . EV‑SegNet: semantic segmentation for event‑based cameras [A]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops [C]. Long Beach : IEEE , 2019 . 1624 - 1633 .
成春阳 , 黄渊博 , 等 . 基于主动红外滤光环视成像的车道线检测算法 [J]. 激光与光电子学进展 , 2018 , 55 ( 12 ): 288 - 296 .
CHENG Chun‑yang , HUANG Yuan‑bo , et al . Lane detection based on active infrared filter and around‑view imaging [J]. Laser & Optoelectronics Progress , 2018 , 55 ( 12 ): 288 - 296 . (in Chinese)
王正家 , 王若 , 等 . 夜间车道线检测的研究 [J]. 现代电子技术 , 2020 , 43 ( 24 ): 26 - 29 .
WANG Zheng‑jia , WANG Ruo , et al . Research on nighttime lane detection [J]. Modern Electronics Technique , 2020 , 43 ( 24 ): 26 - 29 . (in Chinese)
罗强 , 王国胤 , 等 . 复杂光照下的缩微道路车道线检测方法 [J]. 计算机科学 , 2014 , 41 ( 03 ): 46 - 49,70 .
LUO Qiang , WANG Guo‑yin , et al . Lane detection in micro‑traffic under complex illumination [J]. Computer Science , 2014 , 41 ( 03 ): 46 - 49,70 . (in Chinese)
NEVEN D , DE B B , et al . Towards end‑to‑end lane detection: an instance segmentation approach [A]. 2018 IEEE Intelligent Vehicles Symposium [C]. Changshu : IEEE , 2018 . 286 - 291 .
PAN X , SHI J , et al . Spatial as deep: spatial CNN for traffic scene understanding [A]. 32nd AAAI Conference on Artificial Intelligence [C]. New Orleans : AAAI , 2018 . 7276 - 7283 .
吴一全 , 刘莉 . 基于视觉的车道线检测方法研究进展 [J]. 仪器仪表学报 , 2019 , 40 ( 12 ): 92 - 109 .
WU Yi‑quan , LIU Li . Research and development of the vision‑based lane detection methods [J]. Chinese Journal of Scientific Instrument , 2019 , 40 ( 12 ): 92 - 109 . (in Chinese)
NGUYEN A , DO T T , et al . Real‑time 6‑DOF pose relocalization for event cameras with stacked spatial LSTM networks [A]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops [C]. Long Beach : IEEE , 2019 . 1638 - 1645 .
LONG J , SHELLHAMER E , et al . Fully convolutional networks for semantic segmentation [A]. 2015 IEEE Conference on Computer Vision and Pattern Recognition [C]. Boston : IEEE , 2015 . 3431 - 3440 .
CHOLLET F . Xception: deep learning with depthwise separable convolutions [A]. 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition [C]. Honolulu : IEEE , 2017 . 1251 - 1258 .
HOWARD A G , ZHU M , et al . Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision Applications [EB/OL]. https://arxiv.org/abs/1704.04861 https://arxiv.org/abs/1704.04861 , 2017 .
ESWARAN K P , TARJAN R E . Augmentation problems [J]. SIAM Journal on Computing , 1976 , 5 ( 4 ): 653 - 665 .
ABADI M , BARHAM P , et al . Tensorflow: a system for large‑scale machine learning [A]. Proceedings of OSDI’16: 12th USENIX Symposium on Operating Systems Design and Implementation [C]. Savannah : USENIX Association , 2016 . 265 - 283 .
LIU L , JIANG H , et al . On the Variance of the Adaptive Learning Rate and Beyond [EB/OL]. https://arxiv.org/abs/1908.03265 https://arxiv.org/abs/1908.03265 , 2019 .
CHEN L C , ZHU Y , et al . Encoder‑decoder with atrous separable convolution for semantic image segmentation [A]. Computer Vision‑ECCV 2018 , PT VII[C]. Munich : Springer , 2018 . 801 - 818 .
LIN G , MILAN A , et al . Refinenet: multi‑path refinement networks for high‑resolution semantic segmentation [A]. 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition [C]. Honolulu : IEEE , 2017 . 1925 - 1934 .
0
浏览量
19
下载量
4
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621