Building Extraction from UAV Images Jointly Using 6D-SLIC and Multiscale Siamese Convolutional Networks

Abstract

Automatic building extraction using a single data type, either 2D remotely-sensed images or light detection and ranging 3D point clouds, remains insufficient to accurately delineate building outlines for automatic mapping, despite active research in this area and the significant progress which has been achieved in the past decade. This paper presents an effective approach to extracting buildings from Unmanned Aerial Vehicle (UAV) images through the incorporation of superpixel segmentation and semantic recognition. A framework for building extraction is constructed by jointly using an improved Simple Linear Iterative Clustering (SLIC) algorithm and Multiscale Siamese Convolutional Networks (MSCNs). The SLIC algorithm, improved by additionally imposing a digital surface model for superpixel segmentation, namely 6D-SLIC, is suited for building boundary detection under building and image backgrounds with similar radiometric signatures. The proposed MSCNs, including a feature learning network and a binary decision network, are used to automatically learn a multiscale hierarchical feature representation and detect building objects under various complex backgrounds. In addition, a gamma-transform green leaf index is proposed to truncate vegetation superpixels for further processing to improve the robustness and efficiency of building detection, the Douglas–Peucker algorithm and iterative optimization are used to eliminate jagged details generated from small structures as a result of superpixel segmentation. In the experiments, the UAV datasets, including many buildings in urban and rural areas with irregular shapes and different heights and that are obscured by trees, are collected to evaluate the proposed method. The experimental results based on the qualitative and quantitative measures confirm the effectiveness and high accuracy of the proposed framework relative to the digitized results. The proposed framework performs better than state-of-the-art building extraction methods, given its higher values of recall, precision, and intersection over Union (IoU).

Application of Deep Learning for Delineation of Visible Cadastral Boundaries from Remote Sensing Imagery

“…CNNs are one of the most popular and successful deep networks for image interpretation tasks. They are proven to work efficiently to identify various objects in remote sensing imagery [12][13][14][15][16]. Comprehensive overviews contextualizing the evolution of deep learning and CNNs in geoscience and remote sensing are provided by Bergen et al and Zhu et al [17,18].…”

Tree Height Estimation of Forest Plantation in Mountainous Terrain from Bare-Earth Points Using a DoG-Coupled Radial Basis Function Neural Network

“…where GLI denotes the green leaf index calculated using GLI = (2G − R − B)/(2G + R + B) [39], which is selected in accordance with favorable vegetation extraction from UAV images [40], and R, G, B are the three components of RGB channels; Gamma transform is exploited to enhance contrast of BEI values for highlighting BEPs; γ denotes the Gamma value, which is set to 2.5 that is approximately estimated from the range of 0 to 255 of the BEI value in this study. The GLI value is set to 0 when GLI ≤ 0, and the BEI value is set to 255 when BEI > 255.…”

Editorial for Special Issue: “Remote Sensing based Building Extraction”

“…This method outperforms the six existing methods and particularly shows better results for irregular-shaped and small-sized buildings. Zhang et al [18] use a nested network architecture for building extraction from aerial imageries. It can even extract the building areas covered by shadows.…”

“…Kang et al [13] design a dense spatial pyramid pooling to extract dense and multi-scale features simultaneously, to facilitate the extraction of buildings at all scales. He et al [18] present an effective approach to extracting buildings from Unmanned Aerial Vehicle (UAV) images through the incorporation of superpixel segmentation and semantic recognition. Pan et al [13] propose a generative adversarial network with spatial and channel attention mechanisms (GAN-SCA) for the robust segmentation of buildings in remote sensing images.…”