An efficient model for small object detection in the maritime environment

Environmental perception is crucial for autonomous ships realizing autonomous navigation, in particular, the high-precision and low-latency detection of small objects on the sea surface is a key and challenging issue. To address this problem, this paper presents a model that improves the detection accuracy and delivers excellent real-time performance for autonomous ship navigation. The backbone of the proposed model enhances the modelling capabilities by expanding deformable convolution and introducing the self-designed attention mechanism. Additionally, an enhanced feature fusion structure is designed by the pixel shuffle based on super-resolution reconstruction to keep the integrity of feature information for small objects. This paper also presents an optimized model quantization strategy that alleviates the problem of low model efficiency caused by the limited resources onboard the ship. Compared to the earlier model, the present one has increased the mean average precision on the Rizhao Zhuimeng-3# maritime optical dataset by 4.5 % and by 21 % for small object detection. Furthermore, the real-time detection for high-resolution images can now reach a speed of 67 frames/s. Moreover, the present model outperforms existing methods concerning accuracy when the frames/s are similar. The results indicate that the proposed model can be potentially applied to autonomous ships.