A New Multi-Channel Deep Convolutional Neural Network for Semantic Segmentation of Remote Sensing Image

Abstract

The semantic segmentation of remote sensing (RS) image is a hot research field. With the development of deep learning, the semantic segmentation based on a full convolution neural network greatly improves the segmentation accuracy. The amount of information on the RS image is very large, but the sample size is extremely uneven. Therefore, even the common network can segment RS images to a certain extent, but the segmentation accuracy can still be greatly improved. The common neural network deepens the network to improve the classification accuracy, but it has a lot of loss to the target spatial features and scale features, and the existing common feature fusion methods can only solve some problems. A segmentation network is built to solve the above problems very well. The network employs the InceptionV-4 network as the backbone and improves it. We modify the network structure and introduce the changed Atrous Spatial Pyramid Pooling module to extract the multi-scale features of the target from different training stages. Without losing the depth of the network, using Inception blocks to strengthen the width of the network can obtain more abstract features. At the same time, the backbone network is used for semantic fusion of the context, it can retain more spatial features, then an effective decoder network is designed. Finally, evaluate our model on the ISPRS 2D Semantic Labeling Contest Potsdam and Inria Aerial Image Labeling Dataset. The results show that the network has very superior performance, reaching 89.62% IOU score and 94.49% F1 score on the Potsdam dataset, and the IOU score on the Inria dataset has been greatly improved.

Research Contribution and Comprehensive Review towards the Semantic Segmentation of Aerial Images Using Deep Learning Techniques

“…In 2020, Liu et al [50] have proposed a semantic segmentation model for high-resolution remote-sensing images using a multichannel segmentation network termed DAPN that has completely extracted the multiscale features of the images and retained the spatial features of the object. In 2020, Mou et al [51] have considered two efficient networks called channel and spatial relation module for learning and reasoning about the global correlations among the feature maps or positions.…”

“…A general scheme for constructing a deep network to process a rich dataset is complex. e improved DNN models are modified inceptionV-4 network [50], NDRB [52], ResNet101-v2 [39], ALRNet [70], HMANET [56], ResNet [65], inceptionV-4 network [81], MAVNet [41], and SDNF [61], which are aimed to enhance the superior accuracy on segmentation.…”

Image Semantic Recognition and Segmentation Algorithm of Colorimetric Sensor Array Based on Deep Convolutional Neural Network

“…e image semantic recognition process mostly uses machine learning (ML) and a deep learning approach to find out the actual segment of an image. ML techniques are widely used for the detection and recognition process to improve the accuracy rate in the detection process [11].…”

Non-Local Feature Search Network for Building and Road Segmentation of Remote Sensing Image

“…Liu et al [16] proposed a new multi-channel deep convolutional neural network. This network had solved the problem that the spatial and scale features of segmenting objects were lost in some remote sensing images, but it was easy to make mistakes in the case of shadow occlusion.…”

“…In summary, these convolutional neural semantic segmentation networks [12][13][14][15][16][17][18][19] had made significant contributions to the field of semantic segmentation in computer vision. Compared with the feature engineering segmentation method [2][3][4], it had strong anti-noise performance and could realized end-to-end mass automatic segmentation.…”