Change detection of land use and land cover in an urban region with SPOT-5 images and partial Lanczos extreme learning machine

Abstract

Satellite remote sensing technology and the science associated with evaluation of land use and land cover (LULC) in an urban region makes use of the wide range images and algorithms. Improved land management capacity is critically dependent on real-time or near real-time monitoring of land-use/land cover change (LUCC) to the extent to which solutions to a whole host of urban/rural interface development issues may be well managed promptly. Yet previous processing with LULC methods is often time-consuming, laborious, and tedious making the outputs unavailable within the required time window. This paper presents a new image classification approach based on a novel neural computing technique that is applied to identify the LULC patterns in a fast growing urban region with the aid of 2.5-meter resolution SPOT-5 image products. The classifier was constructed based on the partial Lanczos extreme learning machine (PL-ELM), which is a novel machine learning algorithm with fast learning speed and outstanding generalization performance. Since some different classes of LULC may be linked with similar spectral characteristics, texture features and vegetation indexes were extracted and included during the classification process to enhance the discernability. A validation procedure based on ground truth data and comparisons with some classic classifiers prove the credibility of the proposed PL-ELM classification approach in terms of the classification accuracy as well as the processing speed. A case study in Dalian Development Area (DDA) with the aid of the SPOT-5 satellite images collected in the year of 2003 and 2007 and PL-ELM fully supports the monitoring needs and aids in the rapid change detection with respect to both urban expansion and coastal land reclamations.