快速识别和精准定位周围目标是自动驾驶车辆安全、自主行驶的前提和基础.针对基于体素的点云三维目标检测方法识别与定位不准的问题,提出一种基于改进SECOND算法的点云三维目标检测算法.首先,在二维卷积骨干网络中引入自适应的空间特征融合模块融合不同尺度的空间特征,提高模型的特征表达能力.其次,充分利用边界框参数之间的关联性,采用three-dimensional distance-intersection over union(3D DIoU)损失作为边界框的定位回归损失函数,使得回归任务更加高效.最后,同时考虑候选框的分类置信度和定位精度,通过一个新的候选框质量评价标准,获得更平滑的回归结果.在KITTI测试集的实验结果表明,所提算法的 3D检测精度优于许多以往的算法,与基准算法SECOND相比,在简单难度下的car类和cyclist类分别提高2.86百分点和3.84百分点,中等难度下分别提高2.99百分点和3.89百分点,困难难度下分别提高7.06百分点和4.27个百分点.
Point Cloud 3D Object Detection Based on Improved SECOND Algorithm
Rapid identification and precise positioning of surrounding targets are prerequisites and represent the foundation for safe autonomous vehicle driving.A point cloud 3D object detection algorithm based on an improved SECOND algorithm is proposed to address the challenges of inaccurate recognition and positioning in voxel-based point cloud 3D object detection methods.First,an adaptive spatial feature fusion module is introduced into a 2D convolutional backbone network to fuse spatial features of different scales,so as to improve the model's feature expression capability.Second,by fully utilizing the correlation between bounding box parameters,the three-dimensional distance-intersection over union(3D DIoU)is adopted as the bounding box localization regression loss function,thus improving regression task efficiency.Finally,considering both the classification confidence and positioning accuracy of candidate boxes,a new candidate box quality evaluation standard is utilized to obtain smoother regression results.Experimental results on the KITTI test set demonstrate that the 3D detection accuracy of the proposed algorithm is superior to many previous algorithms.Compared with the SECOND benchmark algorithm,the car and cyclist classes improves by 2.86 and 3.84 percentage points,respectively,under simple difficulty;2.99 and 3.89 percentage points,respectively,under medium difficulty;and 7.06 and 4.27 percentage points,respectively,under difficult difficulty.
autonomous drivingthree-dimensional object detectionfeature fusionloss function
NETL
NSTL
万方数据
