ImFusion: Boosting Two-Stage 3D Object Detection via Image Candidates
文献类型：期刊论文
| 作者 | Tao, Manli2,3 ; Zhao, Chaoyang1,3; Wang, Jinqiao1,2,3; Tang, Ming2,3
|
| 刊名 | IEEE SIGNAL PROCESSING LETTERS
 |
| 出版日期 | 2024 |
| 卷号 | 31页码:241-245 |
| 关键词 | Three-dimensional displays Proposals Object detection Feature extraction Point cloud compression Aggregates Sun 3D object detection image candidates pseudo 3D proposal target missing |
| ISSN号 | 1070-9908 |
| DOI | 10.1109/LSP.2023.3336569 |
| 通讯作者 | Zhao, Chaoyang(chaoyang.zhao@nlpr.ia.ac.cn) |
| 英文摘要 | Multi-modal fusion methods combine the advantages of both point clouds and RGB images to boost the performance of 3D object detection. Despite the significant progress, we find that existing two-stage multi-modal fusion methods suffer from the 3D proposal missing in the first stage and projected-style feature fusion mechanism. To solve these problems, we propose a two-stage multi-modal feature fusion network, which improves the recall rate of hard targets in the first stage of network with pseudo 3D proposals generated from image candidates. Then, considering the complementary information between similar image foreground features across multiple objects, we design a multi-modal cross-target fusion module to pay more attention to the foreground objects. It enables a 3D proposal can aggregate the semantic features of multiple image candidates belonging to the same category. Finally, these enhanced fused proposals are processed in the second stage to further boost the performance of 3D detector. Experimental results on SUN RGB-D and KITTI datasets show the effectiveness of our proposed method. |
| WOS关键词 | NETWORK |
| 资助项目 | National Key Ramp;D Program of China |
| WOS研究方向 | Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001140435000004 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Key Ramp;D Program of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/55488]  |
| 专题 | 紫东太初大模型研究中心 |
| 通讯作者 | Zhao, Chaoyang |
| 作者单位 | 1.ObjectEye Inc, Beijing 100000, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Tao, Manli,Zhao, Chaoyang,Wang, Jinqiao,et al. ImFusion: Boosting Two-Stage 3D Object Detection via Image Candidates[J]. IEEE SIGNAL PROCESSING LETTERS,2024,31:241-245. |
| APA | Tao, Manli,Zhao, Chaoyang,Wang, Jinqiao,&Tang, Ming.(2024).ImFusion: Boosting Two-Stage 3D Object Detection via Image Candidates.IEEE SIGNAL PROCESSING LETTERS,31,241-245. |
| MLA | Tao, Manli,et al."ImFusion: Boosting Two-Stage 3D Object Detection via Image Candidates".IEEE SIGNAL PROCESSING LETTERS 31(2024):241-245. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。