MKD-Cooper: Cooperative 3D Object Detection for Autonomous Driving via Multi-Teacher Knowledge Distillation
文献类型：期刊论文
| 作者 | Li, Zhiyuan1,3 ; Liang, Huawei1,2,3,5; Wang, Hanqi3; Zhao, Mingzhuo4; Wang, Jian1,3; Zheng, Xiaokun1,3
|
| 刊名 | IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
 |
| 出版日期 | 2024 |
| 卷号 | 9 |
| 关键词 | Three-dimensional displays Object detection Feature extraction Solid modeling Adaptation models Point cloud compression Aggregates Cooperative perception 3D object detection autonomous driving knowledge distillation multiple teachers |
| ISSN号 | 2379-8858 |
| DOI | 10.1109/TIV.2023.3310580 |
| 通讯作者 | Liang, Huawei(hwliang@iim.ac.cn) |
| 英文摘要 | Accurately detecting objects in 3D point clouds is critical for achieving precise scene understanding in autonomous driving systems. Cooperative perception, through information exchange among neighboring vehicles, can significantly improve object detection performance even under occlusion. This article proposes a novel cooperative perception framework based on multi-teacher knowledge distillation for 3D object detection, namely MKD-Cooper. First, we design a Collaborative Attention Fusion (CAF) module that dynamically captures inter-vehicle interactions through channel and spatial attention. By incorporating the CAF module into the CAF network, we effectively aggregate shared deep learning-based features from neighboring vehicles, resulting in a fused feature map that contains rich contextual information. Second, we propose an adaptive multi-teacher knowledge distillation method that adaptively assigns weights to different teacher models based on their current performance, effectively transferring valuable knowledge from multiple excellent teacher models to the student model. Experimental results on the OPV2V and V2XSim 2.0 datasets demonstrate that our method achieves state-of-the-art performance in detection accuracy while exhibiting excellent comprehensive performance between detection accuracy and efficiency. Moreover, field experiments in real urban environments further validate the effectiveness of our approach. |
| WOS关键词 | MULTIOBJECT TRACKING |
| 资助项目 | National Key Research and Development Program of China[2020AAA0108103] |
| WOS研究方向 | Computer Science ; Engineering ; Transportation |
| 语种 | 英语 |
| WOS记录号 | WOS:001173317800127 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Key Research and Development Program of China |
| 源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/136209]  |
| 专题 | 中国科学院合肥物质科学研究院 |
| 通讯作者 | Liang, Huawei |
| 作者单位 | 1.Univ Sci & Technol China, Hefei 230026, Peoples R China 2.Chinese Acad Sci, Innovat Res Inst Robot & Intelligent Mfg, Hefei 230031, Peoples R China 3.Chinese Acad Sci, Hefei Inst Phys Sci, Hefei 230031, Peoples R China 4.Southeast Univ, Sch Cyber Sci & Engn, Nanjing 211189, Peoples R China 5.Anhui Engn Lab Intelligent Driving Technol & Appl, Hefei 230031, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Zhiyuan,Liang, Huawei,Wang, Hanqi,et al. MKD-Cooper: Cooperative 3D Object Detection for Autonomous Driving via Multi-Teacher Knowledge Distillation[J]. IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,2024,9. |
| APA | Li, Zhiyuan,Liang, Huawei,Wang, Hanqi,Zhao, Mingzhuo,Wang, Jian,&Zheng, Xiaokun.(2024).MKD-Cooper: Cooperative 3D Object Detection for Autonomous Driving via Multi-Teacher Knowledge Distillation.IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,9. |
| MLA | Li, Zhiyuan,et al."MKD-Cooper: Cooperative 3D Object Detection for Autonomous Driving via Multi-Teacher Knowledge Distillation".IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 9(2024). |
入库方式： OAI收割
来源：合肥物质科学研究院
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。