Improved U-Net-Based Novel Segmentation Algorithm for Underwater Mineral Image

Autonomous underwater vehicle (AUV) has many intelligent optical system, which can collect signal information to make the system decision. One of them is vision and it capture images analyze. The performance particle image segmentation plays an important role in monitoring mineral resources. In order improve performance, some novel algorithm architectures are proposed. this paper, improved proposed based on modified U-Net. pyramid upsampling module residual bring into U-Net model, called JPU-Net, JPMU-Net ResU-Net. These models combined power block encoder part decoder respectively. tested Electron Microscopy (EM) dataset dataset. experimental results show that JPU-Net superior EM dataset, a better result than existing convolutional neural network