LiDAR点云中融合点注意力机制的三维目标检测  

3D Object Detection with Fusion Point Attention Mechanism in LiDAR Point Cloud

作　　者：刘威莉 朱德利[1,2] 骆华昊 李益 LIU Weili;ZHU Deli;LUO Huahao;LI Yi(School of Computer and Information Science,Chongqing Normal University,Chongqing 401331,China;Chongqing Digital Agricultural Service Engineering Technology Research Center,Chongqing 401331,China;Information Center of Chongqing Academy of Animal Husbandry,Chongqing 401331,China)

机构地区：[1]重庆师范大学计算机与信息科学学院,重庆401331 [2]重庆市数字农业服务工程技术研究中心,重庆401331 [3]重庆市畜牧科学院信息中心,重庆401331

出　　处：《光子学报》2023年第9期213-223,共11页Acta Photonica Sinica

基　　金：重庆市教育委员会科学技术研究项目(No.KJQN201800536);重庆市高校创新研究群体项目(No.CXQT20015)。

摘　　要：针对Pillar编码点云的三维目标检测算法中存在一定细粒度信息的丢失以及对点云特征提取能力不足等问题,基于PointPillars提出一种融合逐点空间注意力机制和跨阶段局部网络的三维目标检测算法。首先在支柱特征网络层中融入逐点空间注意力机制,增强网络对局部几何信息的提取并保留深层次信息,使得到的关键特征更适合检测任务;其次将对点云伪图像进行高维特征提取的降采样模块中的普通卷积替换为跨阶段局部网络,进一步提升网络的学习能力;最后算法在高速公路的应用场景下,以KITTI数据集中car类作为检测目标,与基准网络相比,在简单、中等和困难三种情况下的3D检测精度分别提高了2.23%、2.25%和2.30%。实验结果表明,所提算法在检测性能上有明显提升,同时检测速度达到实时检测水平,对自动驾驶技术的优化和完善具有一定的积极意义。With the rapid development of computer vision,object detection has made remarkable achievements in 2D vision tasks,but it still can not solve the problems such as light changes and lack of depth that occur in actual scenes.The 3D data acquired by LiDAR makes up for some defects existing in the 2D vision field,so 3D object detection is widely studied as an important field in 3D scene perception.3D object detection in the field of autonomous driving is an important part of intelligent transportation,and the 3D object detection algorithm based on LiDAR point cloud provides an important perception means for it.Perception is a key component of autonomous driving,ensuring the intelligence and safety of driving.3D object detection refers to the detection of physical objects from sensor data,predicting and estimating the category,bounding box,and spatial position of the target.However,due to the unstructured and non-fixed size characteristics of point clouds,they can not be directly processed by 3D object detectors and must be encoded into a more compact structure through some form of expression.There are currently two main types of expressions:point-based and voxel-based methods.Voxel-based methods have higher detection efficiency,but their detection accuracy is lower than that of methods based on raw point clouds.Therefore,how to improve the detection accuracy of voxel-based methods while ensuring detection efficiency has become a research hotspot in recent years.In view of the problems of loss of fine-grained information and insufficient ability to extract point cloud features in the 3D object detection algorithm for Pillar-encoded point clouds,this paper proposes a 3D object detection algorithm based on PointPillars that integrates point-wise spatial attention mechanism and CSPNet.Firstly,the point-wise spatial attention mechanism is integrated into the pillar feature network layer,which can enhance the network′s ability to extract local geometric information and retain deep-level information,making the obtained ke

关 键 词：三维目标检测 点云 注意力机制 PointPillars 跨阶段局部网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]