Efficient and Accurate Giraffe-Det for UAV Image Based Object Detection

Object detection based on unmanned aerial vehicle (UAV) images has become an important area of research within remote sensing community. However, detecting objects on UAV image datasets, such as Visdrone [1] and UAVDT [2], encounters greater challenges compared with detecting objects on ordinary image datasets like COCO. It can be attributed to the fact that UAV image datasets frequently include a significant quantity of small objects, which are more difficult to detect due to the limited information available. In this study, we introduce a new object detection method for UAV images, termed as HRGiraffe-Det, which builds upon the small-object-friendly detection model(i.e., Giraffe-Det). To preserve more spatial information of small targets, we utilize upsampled image instead of the original image as input. Additionally, we construct a Multi-Proxy Head (MPHead) to deal with objects those have diverse appearance variations. Experimental results on UAV image dataset demonstrate the effectiveness of the proposed method for object detection.