3D object detection using improved PointRCNN
3D object detection using improved PointRCNN
复制标题
使用改进的 PointRCNN 进行 3D 对象检测
DOI：
10.1016/j.cogr.2022.12.001
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Serikawa Seiichi
中科院分区：
文献类型：
--
作者：
Fukitani Kazuki;Shin Ishiyama;Lu Huimin;Yang Shuo;Kamiya Tohru;Nakatoh Yoshihisa;Serikawa Seiichi
近年来，二维目标检测(2D Object Detect)在建筑物外部诊断、犯罪预防与监控、医学领域等领域得到了广泛的应用。然而，对于室内机器人导航、机器人抓取、自主行驶等，采用常规的目标检测，距离(深度)信息是不够的。因此，为了提高3D目标检测的准确率，本文提出了一种改进的点RCNN方法，它是一种基于RPN的分割方法，在自动驾驶识别任务中常用的Kitti数据集上的3D检测基准测试中表现良好。提出的改进是在生成3D盒候选的第一阶段对网络进行改进，以解决频繁的误报问题。具体地说，我们在第一阶段的PointNet++网络中增加了一个挤压和激励(SE)块来执行特征提取，并将激活函数从RELU改为MISH。实验是在针对自动驾驶的研究中常用的Kitti数据集上进行的，并使用AP进行了准确的比较。在所有三个难度水平上，该方法都比传统方法高出几个百分点。
Recently, two-dimensional object detection (2D object detection) has been introduced in numerous applications such as building exterior diagnosis, crime prevention and surveillance, and medical fields. However, the distance (depth) information is not enough for indoor robot navigation, robot grasping, autonomous running, and so on, with conventional object detection. Therefore, in order to improve the accuracy of 3D object detection, this paper proposes an improvement of Point RCNN, which is a segmentation-based method using RPNs and has performed well in 3D detection benchmarks on the KITTI dataset commonly used in recognition tasks for automatic driving. The proposed improvement is to improve the network in the first stage of generating 3D box candidates in order to solve the problem of frequent false positives. Specifically, we added a Squeeze and Excitation (SE) Block to the network of pointnet++ that performs feature extraction in the first stage and changed the activation function from ReLU to Mish. Experiments were conducted on the KITTI dataset, which is commonly used in research aimed at automated driving, and an accurate comparison was conducted using AP. The proposed method outperforms the conventional method by several percent on all three difficulty levels.