Knowledge Commons of Institute of Automation,CAS
3D Object Detection Using Scale Invariant and Feature Reweighting Networks | |
Zhao, Xin1; Liu, Zhe2; Hu, Ruolan2; Huang, Kaiqi1 | |
2019 | |
会议名称 | AAAI Conference on Artificial Intelligence |
会议日期 | 2019 |
会议地点 | USA |
摘要 | 3D object detection plays an important role in a large number of real-world applications. It requires us to estimate the localizations and the orientations of 3D objects in real scenes. In this paper, we present a new network architecture which focuses on utilizing the front view images and frustum point clouds to generate 3D detection results. On the one hand, a PointSIFT module is utilized to improve the performance of 3D segmentation. It can capture the information from different orientations in space and the robustness to different scale shapes. On the other hand, our network obtains the useful features and suppresses the features with less information by a SENet module. This module reweights channel features and estimates the 3D bounding boxes more effectively. Our method is evaluated on both KITTI dataset for outdoor scenes and SUN-RGBD dataset for indoor scenes. The experimental results illustrate that our method achieves better performance than the state-of-the-art methods especially when point clouds are highly sparse. |
收录类别 | EI |
七大方向——子方向分类 | 人工智能基础理论 |
国重实验室规划方向分类 | 环境多维感知 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51640 |
专题 | 复杂系统认知与决策实验室_智能系统与工程 |
通讯作者 | Liu, Zhe |
作者单位 | 1.Center for Research on Intelligent System and Engineering Institute of Automation, Chinese Academy of Sciences 2.Huazhong University of Science and Technology |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhao, Xin,Liu, Zhe,Hu, Ruolan,et al. 3D Object Detection Using Scale Invariant and Feature Reweighting Networks[C],2019. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
4963-Article Text-80(1935KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论