Enhanced Automotive Object Detection via RGB-D Fusion in a DiffusionDet Framework
This work addresses the problem of reliable object detection for autonomous driving, but it is incremental as it builds on existing DiffusionDet methods with data fusion.
The paper tackles automotive object detection by proposing a DiffusionDet-based framework that fuses RGB and depth data, achieving a 2.3 AP gain on the KITTI dataset, particularly improving detection of small objects.
Vision-based autonomous driving requires reliable and efficient object detection. This work proposes a DiffusionDet-based framework that exploits data fusion from the monocular camera and depth sensor to provide the RGB and depth (RGB-D) data. Within this framework, ground truth bounding boxes are randomly reshaped as part of the training phase, allowing the model to learn the reverse diffusion process of noise addition. The system methodically enhances a randomly generated set of boxes at the inference stage, guiding them toward accurate final detections. By integrating the textural and color features from RGB images with the spatial depth information from the LiDAR sensors, the proposed framework employs a feature fusion that substantially enhances object detection of automotive targets. The $2.3$ AP gain in detecting automotive targets is achieved through comprehensive experiments using the KITTI dataset. Specifically, the improved performance of the proposed approach in detecting small objects is demonstrated.