Recent Advances on 2D and 3D Change Detection in Urban Environments from Remote Sensing Data

Abstract

Urban environments are dynamic and complex by nature, evolve over time, and constitute the key elements for currently emerging environmental and engineering applications in global, regional, and local spatial scales. Their modeling and monitoring is a mature research field that has been extensively studied from the remote sensing, computer vision, and geography scientific communities. In this chapter, a comprehensive survey of the recent advances in 2D and 3D change detection and modeling is presented. The analysis is structured around the main change detection components including the properties of the change detection targets and end products; the characteristics of the remote sensing data; the initial radiometric, atmospheric, and geometric corrections; the core unsupervised and supervised methodologies and the urban object extraction and reconstruction algorithms. Experimental results from the application of unsupervised and supervised methods for change detection and building detection are given along with their qualitative and quantitative evaluation. Based on the current status and state of the art, the validation reports of relevant studies, and the special challenges of each detection component separately, the present study highlights certain issues and insights that may be applicable for future research and development, including (i) the need for novel multimodal computational frameworks and (ii) for efficient unsupervised techniques able to identify “from-to” change trajectories, along with the importance (iii) of automation, (iv) of open data policies, and (v) of innovative basic research in the core of the change detection mechanisms.