MINIAOD: Lightweight Aerial Image Object Detection
Huiying Wang, Chunping Wang, Qiang Fu, Binqiang Si, Dongdong Zhang, Renke Kou, Ying Yu, Changfeng Feng
Abstract
Identifying challenging samples in real-time aerial images captured by the unmanned aerial vehicles (UAVs) is currently a difficult task. Lightweight network designs often utilize lightweight modules or employ methods such as network pruning, quantization, and distillation for real-time detection on embedded devices. However, these approaches are inadequate for complex background aerial images. In this article, we propose a real-time object detection algorithm specifically designed for complex aerial images, named MINIAOD. First, we use Ghost convolution to build a lightweight backbone network, which improves the detection speed without compromising the feature extraction capability. In addition, we utilize the GSConv module to construct a feature enhancement network and develop the C3 module with integrated GSConv convolution and ECA attention mechanism (GSC3ECA) module to improve the network’s learning capability for challenging targets, while also decreasing computational complexity. To boost the network’s focus on small and medium-sized targets and mitigate interference from complex backgrounds, we incorporate the ECA attention mechanism in the small and medium-sized target detection branch to elevate the focus on difficult-to-detect samples. Finally, we design the rotation detection head to characterize the target directionality of aerial images. We perform extensive experiments on multiple publicly available datasets and the proposed method demonstrates a favorable balance between accuracy and speed when compared to the current leading models.