siaNMS: Non-Maximum Suppression with Siamese Networks for Multi-Camera 3D Object Detection
This addresses a specific challenge in multi-camera 3D object detection for autonomous vehicles, representing an incremental improvement.
The paper tackles the problem of duplicate object detections from multiple cameras in autonomous vehicles by integrating a siamese network into a 3D object detector to suppress duplicates and enhance box regression, resulting in outperformance over traditional NMS approaches on the nuScenes dataset.
The rapid development of embedded hardware in autonomous vehicles broadens their computational capabilities, thus bringing the possibility to mount more complete sensor setups able to handle driving scenarios of higher complexity. As a result, new challenges such as multiple detections of the same object have to be addressed. In this work, a siamese network is integrated into the pipeline of a well-known 3D object detector approach to suppress duplicate proposals coming from different cameras via re-identification. Additionally, associations are exploited to enhance the 3D box regression of the object by aggregating their corresponding LiDAR frustums. The experimental evaluation on the nuScenes dataset shows that the proposed method outperforms traditional NMS approaches.