A LiDAR-Camera Fusion Network for Small Object Detection in Open-pit Mining Areas

As intelligent and autonomous driving technologies advance, the secure and productive functioning of mining trucks during autonomous operations is critically dependent on precise object detection within open-pit mining environments. Due to the sparse nature of point cloud data for small objects such as stones, cones, and equipment parts, they are susceptible to generating false negatives and false positives. Although camera images are rich in semantic content, the absence of precise depth cues renders them vulnerable to interference from background noise. Currently, the technology of fusing LiDAR point cloud and camera image data for 3D object detection is gaining popularity in this field. In this paper, we introduce a query feature generation strategy based on multi-scale image features in the cross-attention-based feature fusion module to generate high-quality fusion features for small objects. Additionally, within the traditional non-maximum suppression strategy, we introduce size factors and shape factors to alleviate the sensitivity of small objects to bounding box offsets. Notably, our network model has achieved an mAP of 88.0 and an NDS of 77.9 on the mining dataset, significantly enhancing the precision of detecting small objects over previous approaches.