THE POTENTIAL OF BUILDING DETECTION FROM SAR AND LIDAR USING DEEP LEARNING

Abstract. The introduction of airborne Synthetic Aperture Radar (SAR) approach has successfully addressed several challenges for mapping and surveying applications Unlike other conventional sensors, airborne SAR mapping approach offers practicality and significant cost savings for the nation minimizing the need for ground control points on the ground in addition to providing high-resolution, day-and-night, cloud coverage and weather independent images, which in turn provides faster turnaround times for creation of large area geospatial data. Up-to-date building map is necessary to guide the decision making in many fields to understand the urban dynamics such as in disaster management, population estimation, planning and many other applications. Whilst mapping and surveying work using airborne SAR have started to capture many interest among surveyors, professionals and practitioners abroad, Malaysia however is still lacking behind in term of the knowledge and the usage of this technology together with Deep Learning, Machine Learning approach especially in building extraction for topographic mapping and urban planning and development. Deep learning is a subset of the machine learning algorithm. Recently, Deep Learning has been proposed to solve traditional artificial intelligent problems. In order to develop a sustainable national geospatial infrastructure for years to come, the integration between airborne SAR and other sensors as such LIDAR is therefore essential in Malaysia and in high demand for urban planning and management. Thus, this paper reviews current techniques and future trends of multi-sources Remote Sensing for building extraction.