Satellite remote-sensing monitoring of a railway construction project

摘要

Current satellite remote-sensing technologies enable the timely and detailed monitoring of human activities on the Earth's surface. Sub-metre spatial resolution satellite images can picture the ongoing works of railway and highway construction. The synoptic view of satellite images is useful to assist the monitoring and management of such construction projects. In this article, we present an integrated remote-sensing change detection framework applied to monitoring the Light Rail Transport construction in Kuala Lumpur, Malaysia, using sub-metre optical remote-sensing images, Pleiades. Focusing on the known local area surrounding a construction site, the recognition process starts from the completion stage, checking conditions based on pre-defined rules, applying the recognition process corresponding to that stage, or moving to the immediately preceding stage if appropriate. The process ends when a new stage is identified and recorded into a spatio-temporal database or it reaches the previously detected stage as retrieved from the database. The experiment proved the effectiveness of the proposed framework, with an overall accuracy of about 80% and a low false detection rate. The proposed framework can be extended to monitor other similar scheduled works. Future studies will integrate multi-sensor satellite images including synthetic aperture radar images to expand further the practicality of the framework.