Automatic feature extraction techniques were developed for use with digital images and map data to assess the feasibility of employing expert systems for map revision. Urban test areas were selected and SPOT images, map separates, and printed map sheets acquired. The digitized map and image data were placed in register to create a cartographic database suitable for use with a prototype expert system optimized for the extraction of building features. Input images were segmented with the region growing method using optimum threshold values derived from map data. Twenty descriptors of shape, size, and tone such as area and elongatedness were calculated for each of the segmented regions using these descriptors. The expert system was also designed to direct the image processing routines with specific instructions (“how to analyze”) applied to focused areas (“where to look”) in the iteration process. The map data were useful for determining initial parameter values for image processing and for change detection of existing features. An expert system approach permitted control of the iterations required for feature extraction and the refinement of threshold values. The accuracy of feature extraction increased as the image pixel resolution was improved. In order to realize feature extraction results comparable to those achieved by human interpreters, digital images must be resampled to pixel resolutions of one-half to one-fourth the original pixel dimension.
NDVI values of GVI data derived from NOAA AVHRR data are fluctuated by various factors without land cover change. In order to utilize GVI data for global land cover monitoring, it should be considered these fluctuation factors. In this paper, these factors and their mutual relationship are discussed. Radiometric effect caused by solar zenith angle, change of solar zenith angle caused by the delay of satellite equator crossing time, sampling method of GVI data and inclination of scan angle mainly discussed. By this study, problems of GVI data were clarified.
A new automatic classification method with high and stable accuracy for multitemporal data is presented in this paper. This method is based on prior condition that a classified map of the target area already exists, or at least one of the multitemporal data had been classified. The classified map is used as a reference map to specify training areas of classification categories. The new automatic classification method consists of five steps, i. e., extraction of training data using the reference map, detection of changed pixels based upon the homogeneity of training data, clustering of changed pixels, reconstruction of training data, and maximum likelihood classification. In order to evaluate the performance of this method, each temporal Landsat TM data were classified by using this method and a conventional method. As a result, we could get classified maps with high reliability and fast throughput, without a skilled operator.
Pattern classification of image data is one of the most important processing in the analysis of remote sensing image. Different classification results may be obtained when different classification methods are applied to the same image data or a fixed classification method is applied to different image data. Therefore it is necessary to find a criterion to assess the different classification results. In order to assess the different classification results the criterion called“Equivocation Quantification”is proposed. However there are some problems to be resolved in the application of equivocation quantification. To resolve part of the problems existing in the equivocation quantification a new assessment criterion of classification results of image pattern called“Fuzzy Set Quantification”is proposed in this paper. And equivocation quantification and fuzzy set quantification are computed with classification score based on mathematical models. The calculation results with both assessment criteria are compared and the efficiency of fuzzy set quantification is also described.
In recent years, GIS is used increasingly and rapidly for researches and analyses. Most of these GIS are the system based on vector data. On the other hand, many type of inf ormations are used for researches and analyses of environmental management, land conservation, regional planning. So, adding GIS based on vector data, it seems that GIS based on raster data are necessary. They can directly connect remote sensing data and geographic information, and simplicity of data structure used on them help user to develop exclusive function easily. Therefore, in this study, we tried to study on the simple type of GIS based on raster data using a personal computer (PC-9800) . This paper reports about the basic idea of system production, functional analysis basing on analytical examples, discussion on hardware and software and production of pilot system, and prospect for the extension function of the system in the future.