A Late Collaborative Perception Framework for 3D Multi-Object and Multi-Source Association and Fusion
Uloženo v:
| Název: | A Late Collaborative Perception Framework for 3D Multi-Object and Multi-Source Association and Fusion |
|---|---|
| Autoři: | Fadili, Maryem, Ghaoui, Mohamed Anis, Lecrosnier, Louis, Pechberti, Steve, Khemmar, Redouane |
| Přispěvatelé: | FADILI, MARYEM |
| Zdroj: | 2025 9th International Conference on Robotics and Automation Sciences (ICRAS). :259-266 |
| Publication Status: | Preprint |
| Informace o vydavateli: | IEEE, 2025. |
| Rok vydání: | 2025 |
| Témata: | Signal Processing (eess.SP), FOS: Computer and information sciences, Sensor fusion, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, [INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO], Image and Video Processing (eess.IV), Image and Video Processing, Robotics, Collaborative perception, 3D object detection, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], Signal Processing, Autonomous driving, FOS: Electrical engineering, electronic engineering, information engineering, Robotics (cs.RO) |
| Popis: | In autonomous driving, recent research has increasingly focused on collaborative perception based on deep learning to overcome the limitations of individual perception systems. Although these methods achieve high accuracy, they rely on high communication bandwidth and require unrestricted access to each agent's object detection model architecture and parameters. These constraints pose challenges real-world autonomous driving scenarios, where communication limitations and the need to safeguard proprietary models hinder practical implementation. To address this issue, we introduce a novel late collaborative framework for 3D multi-source and multi-object fusion, which operates solely on shared 3D bounding box attributes-category, size, position, and orientation-without necessitating direct access to detection models. Our framework establishes a new state-of-the-art in late fusion, achieving up to five times lower position error compared to existing methods. Additionally, it reduces scale error by a factor of 7.5 and orientation error by half, all while maintaining perfect 100% precision and recall when fusing detections from heterogeneous perception systems. These results highlight the effectiveness of our approach in addressing real-world collaborative perception challenges, setting a new benchmark for efficient and scalable multi-agent fusion. |
| Druh dokumentu: | Article Conference object |
| Popis souboru: | application/pdf |
| DOI: | 10.1109/icras65818.2025.11108781 |
| DOI: | 10.48550/arxiv.2507.02430 |
| Přístupová URL adresa: | http://arxiv.org/abs/2507.02430 |
| Rights: | STM Policy #29 arXiv Non-Exclusive Distribution |
| Přístupové číslo: | edsair.doi.dedup.....93458b01fc7e59c1464cbdd7cacddcc9 |
| Databáze: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | In autonomous driving, recent research has increasingly focused on collaborative perception based on deep learning to overcome the limitations of individual perception systems. Although these methods achieve high accuracy, they rely on high communication bandwidth and require unrestricted access to each agent's object detection model architecture and parameters. These constraints pose challenges real-world autonomous driving scenarios, where communication limitations and the need to safeguard proprietary models hinder practical implementation. To address this issue, we introduce a novel late collaborative framework for 3D multi-source and multi-object fusion, which operates solely on shared 3D bounding box attributes-category, size, position, and orientation-without necessitating direct access to detection models. Our framework establishes a new state-of-the-art in late fusion, achieving up to five times lower position error compared to existing methods. Additionally, it reduces scale error by a factor of 7.5 and orientation error by half, all while maintaining perfect 100% precision and recall when fusing detections from heterogeneous perception systems. These results highlight the effectiveness of our approach in addressing real-world collaborative perception challenges, setting a new benchmark for efficient and scalable multi-agent fusion. |
|---|---|
| DOI: | 10.1109/icras65818.2025.11108781 |