汽车工程 ›› 2021, Vol. 43 ›› Issue (4): 469-477.doi: 10.19562/j.chinasae.qcgc.2021.04.003

• • 上一篇    下一篇

基于体素网络的道路场景多类目标识别算法

龚章鹏,王国业(),于是   

  1. 中国农业大学工学院,北京 100083
  • 收稿日期:2020-05-21 修回日期:2020-07-25 出版日期:2021-04-25 发布日期:2021-04-23
  • 通讯作者: 王国业 E-mail:wgy1615@126.cm
  • 基金资助:
    国家自然科学基金(51775548)

The Algorithm of Multi⁃Category Object Recognition in Road Scene Based on Voxel Network

Zhangpeng Gong,Guoye Wang(),Shi Yu   

  1. College of Engineering,China Agriculture University,Beijing 100083
  • Received:2020-05-21 Revised:2020-07-25 Online:2021-04-25 Published:2021-04-23
  • Contact: Guoye Wang E-mail:wgy1615@126.cm

摘要:

基于激光雷达数据的三维物体识别是自动驾驶系统的关键组成部分,体素网络是较好的点云特征提取容器,但目前基于体素网络的目标识别研究大多指向单类目标。为满足无人驾驶领域的应用需求,多类目标识别亟待开展研究。本文中基于体素网络框架构建了多类目标识别网络,并测试其性能。采用计算所有类别先验候选边框重叠度的方法,为标签周围体素创建类别标签、置信度标签和目标包围边框回归值,解决了3项预测值之间可能不匹配的问题。测试结果表明,本文中提出的多目标识别算法类别预测综合召回率为88.6%;设定判定正确的重叠度阈值为0.5时,边框回归召回率为84.8%。相较于单类目标识别网络,本文中算法的单类目标预测正确率明显提高,验证了多类目标识别算法对目标特征学习有加强作用,对增强目标识别网络的鲁棒性有利。

关键词: 目标识别, 多类目标, 体素网络, 激光雷达, 鲁棒性

Abstract:

The 3D object recognition based on lidar data is a key part of autopilot system. Voxel network is a good container for extracting point cloud features, but most of the research at present on object recognition based on voxel network focuses on single?category object. In order to meet the application demand of unmanned vehicle, it is urgent to carry out research on multi?category object recognition. In this paper, a multi?category object recognition algorithm based on voxel network is established and its performance is validated. The category label, confidence label and bounding borders regression values of the voxels around the tag are created by calculating the maximal intersection over union(IoU) among prior candidate borders of all categories simultaneously, which resolves the possible mismatch among the three predicted values. The test results indicate that the average recall of category prediction of the proposed multi?category object recognition algorithm is 88.6% and taking the IoU threshold of 0.5 as the correct one, the border regression is 84.8%. Compared with the single?category object recognition network, each category performs an obviously improved accuracy using the proposed algorithm, which proves that the multi?category object recognition algorithm effectively enhances the ability of characteristics learning, and contributes to the improvement of the robustness of the object recognition network.

Key words: object recognition, multi?category, voxel network, lidar, robustness