AFENet: Attention-guided Feature Enhancement Network and a benchmark for low-altitude UAV sewage outfall detection

Inspecting sewage outfall into rivers is significant to the precise management of the ecological environment because they are the last gate for pollutants to enter the river. Unmanned Aerial Vehicles (UAVs) have the characteristics of maneuverability and high-resolution images and have been used as an important means to inspect sewage outfalls. UAVs are widely used in daily sewage outfall inspections, but relying on manual interpretation lacking the corresponding low-altitude sewage outfall images dataset. Meanwhile, due to the sparse spatial distribution of sewage outfalls, the problems of less labeled sample data, complex background types, and weak objects are also prominent. In order to promote the inspection of sewage outfalls, this paper proposes a low-attitude sewage outfall object detection dataset, namely UAV-SOD, and an attention-guided feature enhancement network, namely AFENet. The UAV-SOD dataset features high resolution, complex backgrounds, and diverse objects while outfall objects are limited by multi-scale, single-colored, and weak feature responses, leading to low detection accuracy. To localize these objects effectively, AFENet first utilizes the global context block (GCB) can jointly explore valuable global and local information, and then the region of interest (RoI) attention module (RAM) is used to explore the relationships between RoI features and enhance the features. The experimental results demonstrate that the proposed method achieves better detection performance on the proposed UAV-SOD dataset than representative state-of-the-art two-stage object detection methods.