An Adaptive Multifeature Sparsity-Based Model for Semiautomatic Road Extraction From High-Resolution Satellite Images in Urban Areas

Despite its ability to handle occlusions and noise, sparse tracking may be inadequate to describe complex noise corruption, for instance, in urban road tracking, where road surfaces are often significantly disrupted by the existence of occlusions and noise in high-resolution (HR) satellite imagery. To address this issue, this letter presents a semiautomatic approach for road extraction from HR satellite images. Firstly, a multifeature sparse model is introduced to represent the road target appearance. Next, a novel sparse constraint regularized mean-shift algorithm is used to support the road tracking. Furthermore, multiple features are combined by weighting their contributions using a novel reliability measure derived to distinguish target from background. The experiments confirm that the proposed method performs better than the current state-of-the-art methods for the extraction of roads from HR imagery, in terms of reliability, robustness, and accuracy.