|
Evaluation of conventional digital camera scenes for Thematic Information Extraction
 H. S. Lim M. Z. MatJafri and K. Abdullah School of Physics Universiti Sains Malaysia, 11800 Penang Abstract A study was carried out to assess the capability of a personal digital camera to provide useful remotely sensed images for land cover mapping. A Kodak DC290 digital camera was employed to capture images of several test sites. The airborne platform used in this study was a light aircraft, Cessna172Q, flown at an average altitude of 8000 ft above sea level during image acquisitions. The standard supervised classification techniques, such as the maximum likelihood, minimum distance-to-mean and parallelepiped, were applied to the multispectral images consisted of red, green and blue bands. Training sites were selected within each scene and five land cover classes were assigned to each classifier. The relative performance of the techniques was evaluated. The accuracy of each classification map was assessed using the reference data set consisted of a large number of samples collected per category. The study revealed that the maximum likelihood classifier produced superior result and achieved a high degree of accuracy. The preliminary result indicates that a conventional digital camera can be a useful tool for remote sensing. |