Regional land use/cover classification in Malaysia Based on conventional digital camera imageries

Abstract

This paper presents an economical analysis of land cover in Malaysia. Land cover classification from remotely sensed data is an important topic in remote sensing applications. We attempted to investigate the feasibility of using a conventional digital camera for acquiring high resolution imagery for land use/cover mapping. The objective of this study is to test the high-resolution digital camera imagery for land cover mapping using remote sensing technique. The study area is the Merbok River estuary, Kedah and Timah Tasoh Lake, Perlis, both located in Peninsular Malaysia. The digital images were taken from a low-attitude light aircraft. A Kodak camera, model DC290, was used to capture images from an elevation of 8000 feet on board Cessna 172Q. The use of a digital camera as a sensor to capture digital images is cheaper and more economical compared to the use of other airborne sensors. This technique overcomes the problem of the difficulty in obtaining cloud-free scenes in the Equatorial region from a satellite platform. The images consisted of the three visible bands-red, green, and blue. Supervised classification technique (maximum likelihood, ML, minimum distance-to-mean, MDM, and parallelepiped, P) was applied to the digital camera spectral bands (red, green and blue) to extract the thematic information from the acquired scenes. The accuracy of each classification map produced was validated using the reference data sets consisting of a large number of samples collected per category. The results produced a high degree of accuracy. This study indicates that the use of a conventional digital camera as a sensor in remote sensing studies can provide useful information for planning and development of a small area of coverage.