Optical-Elevation Data Co-Registration and Classification-Based Height Normalization for Building Detection in Stereo VHR Images

Abstract

Building detection in very high resolution (VHR) images is crucial for mapping and analysing urban environments. Since buildings are elevated objects, elevation data need to be integrated with images for reliable detection. This process requires two critical steps: optical-elevation data co-registration and aboveground elevation calculation. These two steps are still challenging to some extent. Therefore, this paper introduces optical-elevation data co-registration and normalization techniques for generating a dataset that facilitates elevation-based building detection. For achieving accurate co-registration, a dense set of stereo-based elevations is generated and co-registered to their relevant image based on their corresponding image locations. To normalize these co-registered elevations, the bare-earth elevations are detected based on classification information of some terrain-level features after achieving the image co-registration. The developed method was executed and validated. After implementation, 80% overall-quality of detection result was achieved with 94% correct detection. Together, the developed techniques successfully facilitate the incorporation of stereo-based elevations for detecting buildings in VHR remote sensing images.

Study on Design Rainstorm Profile in Liuzhou City Based on Pilgrim & Cordery Method

“…Normalization method can change the number into decimal between (0,1), mainly for the convenience of data processing. Mapping the data into the range of 0 -1 is more convenient and fast, and should be included in the category of digital signal processing (Zhang et al, 2012;Suliman & Zhang, 2017). Then each rainfall process factor is evenly divided into n time periods according to its own rainfall duration at intervals of 5 min.…”