摘要
随着激光雷达、RGB摄像头等传感器在无人驾驶领域的广泛应用,2D目标检测已不能满足无人驾驶车辆感知环境的需要。在对现有3D目标检测算法文献研究的基础上,介绍了基于RGBD、激光点云与传感器融合的3D目标检测算法,并对上述三类算法的改进方法进行了系统阐述。介绍了常用评判检测算法的测试数据集,展望了3D目标检测算法的研究前景。
With the widespread application of sensors, such as laser radar and RGB cameras in the unmanned field,the 2 D target detection can no longer meet the needs of unmanned vehicles.Based on the researches of existing literatures for 3 D target detection algorithm,a 3 D target detection algorithm based on RGB-D,laser point cloud and sensor fusion is introduced,and the improvement methods for the above three types of algorithms are systematically expounded.The test data set of commonly used evaluation algorithm is presented,and the research prospect of the 3 D target detection algorithm is prospected.
作者
季一木
陈治宇
田鹏浩
吴飞
刘尚东
孙静
焦志鹏
王娜
毕强
JI Yimu;CHEN Zhiyu;TIAN Penghao;WU Fei;LIU Shangdong;SUN Jing;JIAO Zhipeng;WANG Na;BI Qiang(School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;Institue of High Performance Computing and Bigdata,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;Nanjing Center of HPC China,Nanjing 210023,China;Jiangsu HPC and Intelligent Processing Engineer Research Center,Nanjing University of Posts and Telecommunications,Nanjing 210023,China)
出处
《南京邮电大学学报（自然科学版）》
北大核心
2019年第4期72-79,共8页
Journal of Nanjing University of Posts and Telecommunications：Natural Science Edition
基金
国家重点研发计划专项(2017YFB1401302,2017YFB0202200)
国家自然科学基金(61572260,61872196)
江苏省自然科学基金优秀青年基金(BK20170100)
江苏省重点研发计划(BE2017166)资助项目
关键词
目标检测
激光点云
传感器融合
target detection
laser point cloud
sensor fusion
