@inproceedings{e6f28c48137848239bc5d1be65b31235,
title = "A Multi-Level Semantic Fusion VoteNet for 3D Object Detection on Point Clouds",
abstract = "In this paper, a Multi-Level Semantic Fusion VoteNet (MLSFVNet) is proposed to detect objects in 3D scenes. The method works on 3D point clouds captured by RGB-D camera, which can provide abundant and precise distance information of environments. The proposed method consists of three modules: the multi-level semantics fusion network, voting operation and proposal generator. To overcome the lack of semantic information, the multi-level semantics fusion network is proposed to capture the multi-level features. To predict the object centers, the voting operation is used to map the features into a feature space of the same scale and regress the object centers. The proposal generator is used to generate proposals and then predict the bounding boxes. MLSFVNet is evaluated on the popular indoor datasets SUN RGB-D and ScanNetV2. The experimental results demonstrate that the MLSFVNet proposed in this paper is an effective way to promote detection accuracy: 58.1% mAP on SUN RGB-D and 59.8% mAP on ScanNetV2.",
keywords = "3D object detection, computer vision, deep learning, multi-level semantics, point clouds",
author = "Yihui Xie and Yaping Dai and Zhongjian Dai and Zhiyang Jia",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE; 2021 China Automation Congress, CAC 2021 ; Conference date: 22-10-2021 Through 24-10-2021",
year = "2021",
doi = "10.1109/CAC53003.2021.9728594",
language = "English",
series = "Proceeding - 2021 China Automation Congress, CAC 2021",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "4514--4519",
booktitle = "Proceeding - 2021 China Automation Congress, CAC 2021",
address = "United States",
}