基于ARD-PSPNet网络下的水下鱼类图像分割算法研究

Research on segmentation algorithm of underwater fish image based on ARD-PSPNet network

水下鱼类图像因受到光线散射和吸收、水体杂质等因素影响,导致水下鱼类图像质量较低,本文通过改进自动彩色均衡(automatic color equalization,ACE)算法进行水下鱼类图像增强,有效改善图像质量,并为后续的水下图像分割打下良好的基础。针对水下鱼类图像分割效果差、实时性低等问题,本文提出ARD-PSPNet网络模型,使用ResNet101网络模型作为特征提取网络,利用分割性能良好的PSPNet(pyramid scene parsing network)网络模型作为基础图像分割模型,通过引入深度可分离卷积来降低计算量,通过R-MCN网络结构,充分利用浅层网络特征层丰富的位置信息和完整性,改进损失函数使得分割位置更加准确,在Fish4knowledge数据集上进行实验,结果表明:新模型与原模型相比,在平均交并比(mean intersection over union,MIOU)上提高了2.8个百分点,在平均像素准确率(mean pixel accuracy,MPA)上提高了约2个百分点。

Underwater fish images are affected by ligt scattering and absorption,water impurities and other factors,resulting in low underwater fish image quality.This article uses improved automatic color equalization(ACE)algorithm to enhance underwater fish images to effectively improve image quality,and lay a good foundation for the subsequent underwater image segmentation.Aiming at the problems of poor segmentation effect and low real-time performance of underwater fish images,this paper proposes the ARD-PSPNet network model,using the ResNet101 network model as the feature extraction network,and using the pyramid scene parsing network(PSPNet)network model with good segmentation performance as the basic image The segmentation model reduces the amount of calculation by introducing deep separable convolutions.Through the R-MCN network structure,it makes full use of the rich location information and completeness of the shallow network feature layer,and improves the loss function to make the segmentation position more accurate.In experiments and completed on the Fish4 knowledge data set.Experimental results show that the new model has an increase of 2.8%in mean intersection over union(MIOU)and about 2%in mean pixel accuracy(MPA)compared with the original model.