Co-Segmentation and Superpixel-Based Graph Cuts for Building Change Detection from Bi-Temporal Digital Surface Models and Aerial Images

Abstract

Thanks to the recent development of laser scanner hardware and the technology of dense image matching (DIM), the acquisition of three-dimensional (3D) point cloud data has become increasingly convenient. However, how to effectively combine 3D point cloud data and images to realize accurate building change detection is still a hotspot in the field of photogrammetry and remote sensing. Therefore, with the bi-temporal aerial images and point cloud data obtained by airborne laser scanner (ALS) or DIM as the data source, a novel building change detection method combining co-segmentation and superpixel-based graph cuts is proposed in this paper. In this method, the bi-temporal point cloud data are firstly combined to achieve a co-segmentation to obtain bi-temporal superpixels with the simple linear iterative clustering (SLIC) algorithm. Secondly, for each period of aerial images, semantic segmentation based on a deep convolutional neural network is used to extract building areas, and this is the basis for subsequent superpixel feature extraction. Again, with the bi-temporal superpixel as the processing unit, a graph-cuts-based building change detection algorithm is proposed to extract the changed buildings. In this step, the building change detection problem is modeled as two binary classifications, and acquisition of each period’s changed buildings is a binary classification, in which the changed building is regarded as foreground and the other area as background. Then, the graph cuts algorithm is used to obtain the optimal solution. Next, by combining the bi-temporal changed buildings and digital surface models (DSMs), these changed buildings are further classified as “newly built,” “taller,” “demolished”, and “lower”. Finally, two typical datasets composed of bi-temporal aerial images and point cloud data obtained by ALS or DIM are used to validate the proposed method, and the experiments demonstrate the effectiveness and generality of the proposed algorithm.

Special Section Guest Editorial: Change Detection Using Multi-Source Remotely Sensed Imagery

“…Using multi-source data, the Special Issue includes papers focusing on deep learning [3][4][5], multi-angle image processing [6], multi-source image fusion in heterogeneous environments [2,3,5], and object-based image analysis [5,7,8]. These interesting techniques applied various change detection applications, while most of them simultaneously mined the change information from the spectral, spatial, and temporal domains.…”

“…With the aid of fully convolutional neuron network, Pang et al [5] proposed a co-segmentation and superpixel-based graph cuts for building change detection. By modeling the characteristics of building in a 4-dimension feature space (i.e., horizontal, vertical, and temporal), this study can further identify the building change types (e.g., "newly built", "taller", "demolished", and "lower").…”

“…In addition to the airborne Light Detection and Ranging (LiDAR) /stereo aerial image (with extremely high spatial resolution) derived Digital Surface Model (DSM) [5], the space-borne multi-angle image derived DSM is also suitable for 3D building change and urban redevelopment patterns monitoring [6]. In the work of Wen et al [6], the multi-temporal 3D dynamic monitoring was conducted in an automatic way, which is an efficient approach to understand how inner-city areas have changed under urban redevelopment.…”

A Feature Space Constraint-Based Method for Change Detection in Heterogeneous Images

“…Different from homogeneous CD, the pixels in heterogeneous images are in different distinct feature spaces [7], and the change map (CM) cannot be obtained by simple linear operations or some homogeneous methods, which is also the main difficulty for heterogeneous CD. Over the past several decades, much attention has been paid to homogeneous CD [8], and many excellent methods have been explored [9][10][11][12][13]. With the increase of different types of satellite sensors, however, CD based on homogeneous images is far away from the practical demands [8] especially when the homogeneous images are not available.…”

A Survey of Change Detection Methods Based on Remote Sensing Images for Multi-Source and Multi-Objective Scenarios

“…Different from DEM, the digital surface model (DSM) accurately models shapes of the existing targets beyond terrain, representing the most realistic expression of ground fluctuation. It has been found that collaborating height change brought by DSM and texture difference extracted from RS images can get rid of variation ambiguity caused by conventional 2D change extraction, and even profitably to observe demolition and construction process in the case of inherent architectures [177,178].…”