River Debris Detection Image Dataset

The pollution problem in rivers around the world is becoming increasingly severe. Traditional manual monitoring methods are inefficient, and there is an urgent need for automated and intelligent solutions. Existing debris detection methods usually rely on manual observation, which is time-consuming and prone to errors. This dataset aims to improve detection accuracy and efficiency through machine learning. The dataset is collected by drones capturing high-altitude images of major polluted river sections under different weather conditions. It ensures data quality through strict multi-round annotation and multi-expert review. The annotation team is from the field of environmental science, consisting of approximately 20 people. Preprocessing includes steps such as image denoising and enhancement, with data stored in JPG format by classification.