An Image Segmentation Model Based on Cascaded Multilevel Features.

In deep convolutional networks for segmentation, resolution is significantly reduced by multiple pooling and convolution operations, which makes the prediction accuracy of pixel class reduced. Based on the deep convolutional coding-decoding network, an end-to-end image segmentation model by cascading multi-level features in encoder and decoder is proposed in this paper. Firstly, the last layer convolution feature of the first two convolution stages and all convolution layer features of the last three convolution stages in the encoder are selected, and the features of the latter three stages are added pixel by pixel through skip connection. Secondly, all the convolution layer features of the last three convolution stages in the decoder are selected to fuse pixel by pixel. Finally, the above multi-level features are cascaded in the way of channel splicing, and then sent to the new convolution layer to learn and make category prediction. In this paper, the experiments are carried out on the CUB_200_2011 and ISPRS Vaihingen datasets, and compared with the research results in the literature. The results show that the proposed model does better than the comparative methods, and has achieved good segmentation effect on common images and remote sensing images.