基于多台飞行时间相机的建图与结构语义的三维库位检测
|
摘要
提出一种基于多台飞行时间(ToF)相机的建图与结构语义的三维库位检测方法.利用多台ToF相机进行联合观测,采用视觉里程计对局部停车场场景进行建图,并通过对停车场墙面、顶面、地面和障碍物结构语义信息的聚类和分割,实现对三维停车库位的实时检测.结果表明:该方法在有效探测范围内库位检出率为94.83%,库位宽度识别精度为14.4 cm,高度识别精度为12.4 cm.
A detection method for three-dimensional parking slot was proposed by using multiple time-of-flight(ToF) cameras. The local scene of a parking lot was jointly captured and mapped by using multiple ToF observations in real time, and structural semantics such as walls, ceilings, floors and obstacles were segmented in the scene for the detection of parking slots. The detection rate of 94.83% was achieved in the experiment. The precision of detected width and height of parking slots are 14.4 cm and 12.4 cm respectively.
A detection method for three-dimensional parking slot was proposed by using multiple time-of-flight(ToF) cameras. The local scene of a parking lot was jointly captured and mapped by using multiple ToF observations in real time, and structural semantics such as walls, ceilings, floors and obstacles were segmented in the scene for the detection of parking slots. The detection rate of 94.83% was achieved in the experiment. The precision of detected width and height of parking slots are 14.4 cm and 12.4 cm respectively.
引文
[1] HUANG Y,ZHAO J,HE X,et al.Vision-based semantic mapping and localization for autonomous indoor parking[C]//IEEE Intelligent Vehicles Symposium.[S.l.]:IEEE,2018:636-641.
[2] SONG Y,LIAO C.Analysis and review of state-of-the-art automatic parking assist system[C]//IEEE International Conference on Vehicular Electronics and Safety.[S.l.]:IEEE,2016:1-6.
[3] MOON J,BAE I,KIM S.Real-time near-optimal path and maneuver planning in automatic parking using a simultaneous dynamic optimization approach[C]//IEEE Intelligent Vehicles Symposium.[S.l.]:IEEE,2017:193-196.
[4] 何伟.基于超声波传感器的自动泊车车位补偿检测法[J].中国仪器仪表,2016(2):47.HE Wei.Automatic parking location compensation detection method based on ultrasonic sensor[J].China Instrumentation,2016(2):47.
[5] PARK W J,KIM B S,SEO D E,et al.Parking space detection using ultrasonic sensor in parking assistance system[C]//IEEE Intelligent Vehicles Symposium.[S.l.]:IEEE,2008:1039-1044.
[6] KIM S H,KIM J S,KIM W Y.A method of detecting parking slot in hough space and pose estimation using rear view image for autonomous parking system[C]//IEEE International Conference on Network Infrastructure and Digital Content.[S.l.]:IEEE,2017:452-454.
[7] 王旭东,王春香,杨明,等.一种基于环视相机的自动泊车方法[J].上海交通大学学报,2013,47(7):1077.WANG Xudong,WANG Chunxiang,YANG Ming,et al.An automatic parking method based on the circular camera[J].Journal of Shanghai Jiaotong University,2013,47(7):1077.
[8] JUNG H G,CHO Y H,YOON P J,et al.Scanning laser radar-based target position designation for parking aid system[J].IEEE Transactions on Intelligent Transportation Systems,2008,9(3):406.
[9] ABAD F,BENDAHAN R,WYBO S,et al.Parking space detection[C]//Proceedings of the 14th World Congress on Intelligent Transport System.Beijing:ITS,2007:1-8.
[10] 缪弘,张文强.基于深度卷积神经网络的视觉SLAM去模糊系统[J].中兴通讯技术,2018,24(5):62.MIU Hong,ZHANG Wenqiang.Deep convolutional neural network for visual SLAM deblurring[J].ZTE Technology Journal,2018,24(5):62.
[11] 陆平,邓硕,李伟华.基于深度学习的多目标跟踪算法研究[J].中兴通讯技术,2017,23(4):14.LU Ping,DENG Shuo,LI Weihua.Multiple object tracking algorithm based on deep learning[J].ZTE Technology Journal,2017,23(4):14.
[12] VU H T,HUANG C C.A multi-task convolutional neural network with spatial transform for parking space detection[C]//2017 IEEE International Conference on Image Processing.[S.l.]:IEEE,2017:1762-1766.
[13] AMATO G,CARRARA F,FALCHI F,et al.Deep learning for decentralized parking lot occupancy detection[J].Expert Systems with Applications,2017,72(1):327.
[14] SHANG E,AN X,LI J,et al.A novel setup method of 3D LIDAR for negative obstacle detection in field environment[C]//IEEE International Conference on Intelligent Transportation Systems.[S.l.]:IEEE,2014:1436-1441.
[15] ZENG A,SONG S,NIEBNER M,et al.3Dmatch:learning local geometric descriptors from RGB-D reconstructions[C]//IEEE Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE,2017:199-208.
[16] ENDRES F,HESS J,ENGELHARD N,et al.An evaluation of the RGB-D SLAM system[C]//IEEE International Conference on Robotics and Automation.[S.l.]:IEEE,2012:1691-1696.
[17] LOWE G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91.
[18] FISCHLER M A,BOLLES R C.Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J].Communications of the ACM,1981,24(6):381.
[19] 北京建筑大学.JGJ100-2015 车库建筑设计规范[S].北京:中国建筑工业出版社,2015.Beijing University of Civil Engineering and Architecture.JGJ100-2015 Code for design of parking garage building[S].Beijing:China Architecture and Building Press,2015.
[20] YANG L,ZHANG L,DONG H,et al.Evaluating and improving the depth accuracy of Kinect for windows V2[J].IEEE Sensors Journal,2015,15(8):4275.
[2] SONG Y,LIAO C.Analysis and review of state-of-the-art automatic parking assist system[C]//IEEE International Conference on Vehicular Electronics and Safety.[S.l.]:IEEE,2016:1-6.
[3] MOON J,BAE I,KIM S.Real-time near-optimal path and maneuver planning in automatic parking using a simultaneous dynamic optimization approach[C]//IEEE Intelligent Vehicles Symposium.[S.l.]:IEEE,2017:193-196.
[4] 何伟.基于超声波传感器的自动泊车车位补偿检测法[J].中国仪器仪表,2016(2):47.HE Wei.Automatic parking location compensation detection method based on ultrasonic sensor[J].China Instrumentation,2016(2):47.
[5] PARK W J,KIM B S,SEO D E,et al.Parking space detection using ultrasonic sensor in parking assistance system[C]//IEEE Intelligent Vehicles Symposium.[S.l.]:IEEE,2008:1039-1044.
[6] KIM S H,KIM J S,KIM W Y.A method of detecting parking slot in hough space and pose estimation using rear view image for autonomous parking system[C]//IEEE International Conference on Network Infrastructure and Digital Content.[S.l.]:IEEE,2017:452-454.
[7] 王旭东,王春香,杨明,等.一种基于环视相机的自动泊车方法[J].上海交通大学学报,2013,47(7):1077.WANG Xudong,WANG Chunxiang,YANG Ming,et al.An automatic parking method based on the circular camera[J].Journal of Shanghai Jiaotong University,2013,47(7):1077.
[8] JUNG H G,CHO Y H,YOON P J,et al.Scanning laser radar-based target position designation for parking aid system[J].IEEE Transactions on Intelligent Transportation Systems,2008,9(3):406.
[9] ABAD F,BENDAHAN R,WYBO S,et al.Parking space detection[C]//Proceedings of the 14th World Congress on Intelligent Transport System.Beijing:ITS,2007:1-8.
[10] 缪弘,张文强.基于深度卷积神经网络的视觉SLAM去模糊系统[J].中兴通讯技术,2018,24(5):62.MIU Hong,ZHANG Wenqiang.Deep convolutional neural network for visual SLAM deblurring[J].ZTE Technology Journal,2018,24(5):62.
[11] 陆平,邓硕,李伟华.基于深度学习的多目标跟踪算法研究[J].中兴通讯技术,2017,23(4):14.LU Ping,DENG Shuo,LI Weihua.Multiple object tracking algorithm based on deep learning[J].ZTE Technology Journal,2017,23(4):14.
[12] VU H T,HUANG C C.A multi-task convolutional neural network with spatial transform for parking space detection[C]//2017 IEEE International Conference on Image Processing.[S.l.]:IEEE,2017:1762-1766.
[13] AMATO G,CARRARA F,FALCHI F,et al.Deep learning for decentralized parking lot occupancy detection[J].Expert Systems with Applications,2017,72(1):327.
[14] SHANG E,AN X,LI J,et al.A novel setup method of 3D LIDAR for negative obstacle detection in field environment[C]//IEEE International Conference on Intelligent Transportation Systems.[S.l.]:IEEE,2014:1436-1441.
[15] ZENG A,SONG S,NIEBNER M,et al.3Dmatch:learning local geometric descriptors from RGB-D reconstructions[C]//IEEE Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE,2017:199-208.
[16] ENDRES F,HESS J,ENGELHARD N,et al.An evaluation of the RGB-D SLAM system[C]//IEEE International Conference on Robotics and Automation.[S.l.]:IEEE,2012:1691-1696.
[17] LOWE G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91.
[18] FISCHLER M A,BOLLES R C.Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography[J].Communications of the ACM,1981,24(6):381.
[19] 北京建筑大学.JGJ100-2015 车库建筑设计规范[S].北京:中国建筑工业出版社,2015.Beijing University of Civil Engineering and Architecture.JGJ100-2015 Code for design of parking garage building[S].Beijing:China Architecture and Building Press,2015.
[20] YANG L,ZHANG L,DONG H,et al.Evaluating and improving the depth accuracy of Kinect for windows V2[J].IEEE Sensors Journal,2015,15(8):4275.