YOLOX-DRONE: AN IMPROVED OBJECT DETECTION METHOD FOR UAV IMAGES

Yuqing Zhang, Huanxin Zou, Shitian He, Xu Cao, Liyuan Pan

Abstract: Unmanned aerial vehicles (UAV) are widely used for their small size and flexibility. However, the large number of small objects and the significant difference in object size in UAV images bring great challenges to the detection task. There fore, we propose an object detection method for UAV im ages with four improvements on the strong baseline model YOLOX-S, which is robust to detect small objects and multi scale objects. Firstly, we introduce a high-resolution fea ture map to retain rich detailed information about small ob jects. Secondly, we propose new up-sampling and down sampling modules to reduce the feature information loss dur ing the sampling process. Thirdly, we present the triple-scale feature fusion module (TSFFM) to fuse more abundant multi scale features in the neck’s bottom-up feature fusion process. Finally, the parrell dilated convolution attention module (PD CAM) is proposed to learn the multi-receptive field features. Experiment results on the VisDrone-VID2019 dataset vali date the effectiveness and superiority of the proposed method.