Fusion of Dual-Scale Convolution Neural Network for Urban Building Footprints

Abstract

Building footprint has a significant role in urban design and management but, extracting the building feature is still challenging due to significant variations in scale and shape. Convolution neural networks (CNN) have shown effective results in extracting the high-level and discriminative urban features from high-resolution remote sensing imagery. The traditional CNN architecture has been modified two-scale input based architecture, known as Dual-scale CNN (Du-CNN). However, the repetitive usage of pooling operation leads to a fuzzy boundary of the extracted features. This paper has proposed the MRF-based fusion strategy to take full use of the blurred boundary and define the conditional relationship between classification maps. In the Preliminary stage, we have designed a Du-CNN framework to extract the building feature at different scales. Du-CNN contains a multiple-size asymmetric filter to provide the variation in the receptive field and the depth-wise convolution in the skip connection block for efficient computation. Finally, the classification maps of both CNN sub-architectures are fused using a Modified Markov random field (MMRF). The proposed MMRF technique inherits the properties of Classical MRF with the extension of overlap potential for associating additional terms between the inter-decision layer. The model was tested on Inria Aerial image labeling dataset and Mnih dataset. Experimental result has shown the superior performance of the proposed strategy for extracting the complex building architecture.

Keywords

• Remote sensing
• Feature extraction
• Overlap potential
• Markov Random Field (MRF)
• Depth-wise convolution