Real-Time Detection of River Surface Floating Object Based on Improved RefineDet

Abstract

Object detection is widely used in robot navigation, intelligent security and industrial detection, but it is rarely used in water conservancy industry. In the aspect of river and lake health management, it is important to clean out the floating objects in time, which prevents water pollution caused by the accumulation of the floating objects. The early methods of water surface object detection, such as background subtraction and frame difference, are greatly affected by the change of object shape and background, resulting in poor robustness. Therefore, we propose a real-time detection method of surface floating objects based on improved RefineDet model, which includes three modules: the anchor refinement module, the transfer connection block and the object detection module. We improve anchor refinement module by adding convolution layers to obtain higher-level semantic, and fuse high-level features with low-level features to improve detection accuracy. Moreover, we adjust the parameters setting of anchors according to the scale and aspect ratio distribution to match the multi-scale object better. Aiming at the foreground-background class imbalance caused by dense anchors sampling, we introduce focal loss function to solve it and make our model more efficient by adjusting the parameters of the function. We verify the performance of the proposed method on different floating object datasets we constructed. The detection accuracies on these different datasets are 83.8%, 88.0%, and 82.3% respectively, and the detection speed is 28 FPS. This shows that the improved RefineDet realizes high-precision and real-time detection.

Keywords

• Object detection
• RefineDet
• focal loss
• feature fusion