CCH-YOLOX: Improved YOLOX for Challenging Vehicle Detection from UAV Images

In this paper, we focus on vehicle detection algorithms from UAV images in intelligent transportation applications. We propose an improved YOLOX model called CCHYOLOX for the problems of dense distribution and drastic scale changes of vehicle targets from the UAV viewpoint. Firstly, we construct a novel plug-and-play module, called Correlation Extraction and Feature Fusion (CEFF), to process the multi-layer adaptive fusion of pyramidal features. It enables the adaptive fusion of features in adjacent layers by adding spatial-awareness and extracting global channels correlation of adjacent layers features to mitigate the effect of target size diversity. Then, we design a special cascade strategy, including a feature alignment module named DConv, for single-stage and anchor-free detectors by considering the feature offset problem to produce more accurate detection bounding boxes. The cascade strategy allows the model to improve performance with little increase in computational cost. Finally, a high-resolution branch is designed for the small-target detection task, which greatly improves the detection accuracy of the model. Experiments on the challenging Visdrone-vehicle and Drone Vehicle datasets show that the proposed method effectively tackle the detection accuracy decrease caused by the above problems. CCH-YOLOX achieves 43.2% mAP and 57.3% mAP on the above two datasets, respectively, which is about 3%-4% higher than the strong baseline model (YOLOX) and exceeds many current popular models. The code is available at https://github.com/lz06787/CCH-YOLOX