激光与光电子学进展, 2020, 57 (20): 201508, 网络出版: 2020-10-13
基于改进Frustum PointNet的3D目标检测 下载: 908次
3D Object Detection Based on Improved Frustum PointNet
机器视觉 激光雷达 点云数据 3D目标检测 宽阈值掩模处理 machine vision lidar point cloud data 3D object detection wide-threshold mask processing
摘要
提出对图像和激光雷达点云数据进行3D目标检测的改进F-PointNet(Frustum PointNet)。首先利用图像的2D目标检测模型提取目标2D区域,并将其映射到点云数据中,得到该目标的点云候选区域,然后预测候选区域的3D目标掩模,最后利用掩模对3D目标进行检测。当预测掩模时,提出的宽阈值掩模处理可以用来减少原始网络的信息损失;增加注意力机制可以获取需要被关注的点和通道层;使用Focal Loss可以解决目标与背景不平衡的问题。通过多次对比实验,证明宽阈值掩模处理可以提高3D目标检测的准确率,同时注意力机制和Focal Loss可以提高预测的准确率。
Abstract
An improved F-PointNet (Frustum PointNet) for 3D target detection on image and lidar point cloud data is proposed. First, the 2D target detection model of the image is used to extract 2D region of the target, and it is mapped to the point cloud data to obtain the candidate region of the target. Then, the 3D target mask of the candidate region is predicted. Finally, the 3D target is detected by using mask. When the mask is predicted, the proposed wide-threshold mask processing is used to reduce the information loss of the original network, the attention mechanism is added to obtain the points and channel layers that require attention, the Focal Loss can solve the imbalance between the target and the background problem. Through multiple comparison experiments, it is proved that wide-threshold mask processing can improve the accuracy of 3D target detection, and the attention mechanism and Focal Loss can improve the accuracy of prediction.
刘训华, 孙韶媛, 顾立鹏, 李想. 基于改进Frustum PointNet的3D目标检测[J]. 激光与光电子学进展, 2020, 57(20): 201508. Xunhua Liu, Shaoyuan Sun, Lipeng Gu, Xiang Li. 3D Object Detection Based on Improved Frustum PointNet[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201508.