The multi-layer perceptron type artificial neural network model (MLP model) has been applied as a classifier in various classification fields, including remote sensing application. The back-propagation learning algorithm is widely employed in the MLP model as a simple learning algorithm. This algorithm, however, may lead to an unstable state of learning process, or take a lot of learning time in the learning process, if the learning rate is selected improperly. In this paper, a new learning rate institution equation is proposed for selecting of proper learning rate when the MLP model is employed in the classification of remote sensing satellite image data. At this time, a large scale training set is usually employed for learning of MLP model. Using the proposed institution equation, the learning rate is able to be directly determined by the training set size (number of training samples) and the network size (number of nodes) . At the same time, it guarantees that the learning process of MLP model is convergent. The proposed learning rate institution equation is more practical than conventional institution equations. The latter is often accompanied with a number of experiments, to obtain a proper learning rate. Using the proposed learning rate institution equation, not only a faster convergence is yielded but also a smaller error is obtained. To inspect the efficiency of proposed equation, two different size training sets are learned by two different MLP models respectively for the classification of multispectral image data.
In this study, the number of effective spectral bands and the band combinations were selected to classify the wetland vegetation types using airborne multi spectral scanner data acquired over the Kushiro Mire in June 1992 and August 1993. Effective spectral bands were selected : from June data, from August data, and from data of both months combind. In the method of this process, Jeffries-Matushita (JM) distance was used as a separability measure for 10 wetland vegetation types. Based on the results obtained from these cases, the first three selected effective bands were almost the same : near infrared band (820 to 900nm) which is sensitive to biomass, and two shortwave infrared bands (1520 to 1720nm and 2060 to 2450nm) which are sensitive to water content. To determin the number of effective spectral bands, training sample data were classified by the maximum likelihood method using the selected band combinations. The best classification accuracy was attained by using the 9 bands from combined data.
Many archeological sites are excavated yearly in JAPAN. At 1994, they were over 8, 000. It can be easily conjectured that archeological artifacts (e. g. Jomon and Yayoi property) of dig out from these sites are so much. Nevertheless, they must be drawn to detailed picture by archeologists themselves and part-timers, expending a great deal of time, labor and skills. In order to labor saving, the large format still camera or CCD camera are expected to become a useful tools in taking ortho photos. However, an ortho photo which are obtained from these system are only 2 dimensional image. Then, the authors concentrated to develop the new system which can be recorded of 3 dimensional information for. archeological artifacts
Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) is a multi-spectral imaging radiometer to be launched on NASA's Earth Observing System AM-1 (EOS AM-1) platform in 1998. ASTER has 3 spectral bands in the VNIR, 6 bands in the SWIR, and 5 bands in the TIR regions with 15, 30, and 90 m ground resolution respectively. The primary science objective of the ASTER mission is to improve understanding of the local- and regional-scale processes occurring on or near the Earth's surface and lower atmosphere, including surface-atmosphere interactions.