基于改进Yolo v8s-seg的船舶旋转角度检测方法

Boat rotation angle detection method based on improved Yolo v8s-seg

水上收费站的智能控制船闸开关系统为了能够自动识别船闸内外船舶的动向,需要精准检测航道内船舶的旋转角度.传统的目标检测算法存在着精度有限、实时性差等问题.针对以上问题,在Yolo v8s-seg模型的基础上通过添加CA注意力机制,提出了检测船舶旋转角度的模型Yolo v8s-seg-boat.模型采用实例分割算法提取船舶的轮廓点,并据此判断船舶重心,最终计算出船舶的旋转角度.实验结果表明:该模型在水上收费站拍摄的船舶数据集上分割评价指标mAP相比于Yolo v8s-seg提升了1.8%,分割精确率达到了97.6%,获取的船舶旋转角度与实际角度误差小于Yolo v8s-seg模型.

Intelligent control lock switching system for water toll station needs to be able to accurately detect the rotation angle of boats in the channel in order to be able to automatically recognize the movement of boats inside and outside the lock.Traditional target detection algorithms have problems such as limited accuracy and poor real-time performance.To address the above problems,a model Yolo v8s-seg-boat is proposed to detect the rotation angle of a boat by adding CA(Coordinate Attention)mechanism on the basis of Yolo v8s-seg model.The model adopts the instance segmentation algorithm to extract the boat’s contour points,and judge the boat's center of gravity accordingly,and finally calculate the rotation angle of the boat.The experimental results show that the model improves the segmentation evaluation index mAP by 1.8%compared with Yolo v8s-seg on the boat dataset captured at the water toll station,and the segmentation precision rate reaches 97.6%,and the error between the acquired boat rotation angle and the actual angle is smaller than that of the Yolo v8s-seg model.