Self-Attention Guidance and Multiscale Feature Fusion-Based UAV Image Object Detection

Object detection on unmanned aerial vehicle (UAV) images is a recent research hotspot. Existing object detection methods have achieved good results on general scenes, but there are inherent challenges with UAV images. The detection accuracy of UAV images is limited by complex backgrounds, significant scale differences, and densely arranged small objects. To solve these problems, we propose a UAV image object detection network based on self-attention guidance and multiscale feature fusion (SGMFNet). First, we design a global-local feature guidance (GLFG) module. This module can effectively combine local information and global information, which makes the model focus on the object area and reduces the impact of complex background. Second, an improved parallel sampling feature fusion (PSFF) module is designed to efficiently fuse multiscale features. Third, we design an inverse-residual feature enhancement (IFE) module, which is embedded in the front of the newly added detection head to enhance feature extraction on small objects. Finally, we conduct a large number of experiments on the VisDrone2019 dataset. The results show that the proposed SGMFNet outperforms other popular methods and has achieved good results in many scenarios.