Joint object detection and re-identification for 3D obstacle multi-camera systems
This work addresses the need for sophisticated information processing in autonomous driving by enhancing object detection and re-identification across cameras, though it appears incremental as it builds on existing detection networks.
The paper tackled the problem of joint object detection and re-identification for 3D obstacle multi-camera systems in autonomous driving by modifying an object detection network with an additional re-identification branch, resulting in a more than 5% improvement in the car category in overlapping areas compared to traditional NMS techniques.
In recent years, the field of autonomous driving has witnessed remarkable advancements, driven by the integration of a multitude of sensors, including cameras and LiDAR systems, in different prototypes. However, with the proliferation of sensor data comes the pressing need for more sophisticated information processing techniques. This research paper introduces a novel modification to an object detection network that uses camera and lidar information, incorporating an additional branch designed for the task of re-identifying objects across adjacent cameras within the same vehicle while elevating the quality of the baseline 3D object detection outcomes. The proposed methodology employs a two-step detection pipeline: initially, an object detection network is employed, followed by a 3D box estimator that operates on the filtered point cloud generated from the network's detections. Extensive experimental evaluations encompassing both 2D and 3D domains validate the effectiveness of the proposed approach and the results underscore the superiority of this method over traditional Non-Maximum Suppression (NMS) techniques, with an improvement of more than 5\% in the car category in the overlapping areas.