改进YOLOv3-SPP水下目标检测研究

针对水下目标检测任务中图像模糊、背景复杂以及目标小而导致误检和漏检问题，提出一种改进YOLOv3-SPP的水下目标检测算法。利用UWGAN网络对水下原始图像进行恢复，采用Mixup方法增强数据，减少错误标签记忆；以YOLOv3-SPP网络结构为基础，增加网络预测尺度，提高小目标检测性能；引入CIoU边框回归损失，提高定位精度；利用K-Means++聚类算法，筛选最佳Anchor box。将改进YOLOv3-SPP算法在处理后的URPC数据集上进行实验，平均检测精度由79.58%提升到88.71%，速度为28.9 FPS。结果表明，改进算法综合检测能力优于其他算法。

Research on Underwater Target Detection by Improved YOLOv3-SPP

To solve the problem of faulty and omitted detection that results from blurred images, complex backgrounds and small targets in underwater target detection tasks, an improved YOLOv3-SPP underwater target detection algorithm is proposed. Firstly, the original underwater image is recovered by UWGAN network, and the Mixup method is employed to strengthen the data and diminish the mislabeled memory. Secondly, the YOLOv3-SPP network structure is used as the basis to increase the network prediction scale to raise the small target detection performance. Then the CIoU border regression loss is introduced to improve the localization accuracy. Finally, the K]-Means++ clustering algorithm is applied to filter the best Anchor box. The improved YOLOv3-SPP algorithm is experimented on the processed URPC dataset, and the average detection accuracy is improved from 79.58% to 88.71% with a speed of 28.9 FPS. The performance show that the improved algorithm has better comprehensive detection capability than other algorithms.