Hourglass-ShapeNetwork Based Semantic Segmentation for High Resolution Aerial Imagery

Abstract

Abstract:A new convolution neural network (CNN) architecture for semantic segmentation of high resolution aerial imagery is proposed in this paper. The proposed architecture follows an hourglass-shaped network (HSN) design being structured into encoding and decoding stages. By taking advantage of recent advances in CNN designs, we use the composed inception module to replace common convolutional layers, providing the network with multi-scale receptive areas with rich context. Additionally, in order to reduce spatial ambiguities in the up-sampling stage, skip connections with residual units are also employed to feed forward encoding-stage information directly to the decoder. Moreover, overlap inference is employed to alleviate boundary effects occurring when high resolution images are inferred from small-sized patches. Finally, we also propose a post-processing method based on weighted belief propagation to visually enhance the classification results. Extensive experiments based on the Vaihingen and Potsdam datasets demonstrate that the proposed architectures outperform three reference state-of-the-art network designs both numerically and visually.

Multiple and Single Green Area Measurements and Classification Using Phantom Images in Comparison With Derived Experimental Law

“…There are many reasons to measure and classify arbitrarily shaped pieces of land including trade, agriculture, division among partners, security or reclamation (Liu et al, 2017;Lopes et al, 2017;Santos et al, 2016;Svatonova and Kolejka, 2017). Measuring regular spaces is often a simple process because the land takes a regular or semi-regular shape.…”

“…For these reasons, the use of low-altitude aerial images (Liu et al, 2017;Svatonova and Kolejka, 2017) to classify and calculate green spaces will be discussed in this paper. Here, two things will be done.…”

ERN: Edge Loss Reinforced Semantic Segmentation Network for Remote Sensing Images

“…Examples of remote sensing images that are challenging for semantic segmentation. (a) similar appearance between a building and its surroundings, in which the impervious surface was incorrectly recognized as a building by HSNet [24], SegNet [19], and FCN [17]. white: impervious surface; blue: buildings; cyan: low vegetation; green: trees.…”

“…Typical semantic segmentation approaches mainly focus on mitigating semantic ambiguity via providing rich information [19,24]. However, redundant and noisy semantic information from high-resolution feature maps may clutter the final pixel-wise predictions [25].…”

“…For remote sensing images, Volpi et al [23] proposed a full patch labeling (FPL) network to up-sample the rough spatial maps with successive deconvolution layers. Liu et al [24] proposed an hourglass-shaped network (HSNet) and replaced some convolution layers with inception and residual blocks to further enhance the ability of context information extraction.…”