Automated segmentation of urban features from landsat thematic mapper imagery for use in pseudoinvariant feature temporal image normalization
暂无分享,去创建一个
An automated segmentation algorithm for the isolation of pseudoinvariant features was developed. This algorithm utilizes rate-of-change information from the thresholding process previously associated with the pseudoinvariant feature normalization technique. This algorithm was combined with the normalization technique and applied to the six reflective bands of the Landsat Thematic Mapper for both urban and rural imagery. The segmentation algorithm and normalization technique were also applied to color infrared high resolution U2 imagery. The accuracy and precision of the normalization results were evaluated. The technique consistently produced normalization results with errors of approximately one or two reflectance units for both the rural and urban Thematic Mapper imagery as well as the visible bands of high resolution airphoto imagery. The segmentation algorithm shows great potential for the removal of human intervention in the pseudoinvariant feature temporal image normalization process.
[1] T. M. Lillesand,et al. Remote sensing and image interpretation. Second edition , 1987 .
[2] Owen Robert Mitchell,et al. Image segmentation using a local extrema texture measure , 1978, Pattern Recognit..
[3] John A. Hartigan,et al. Clustering Algorithms , 1975 .
[4] R. A. Schonengertt. Techniques for Image Processing and Classification in Remote Sensing , 1983 .
[5] E. P. F. Kan. ISODATA: Thresholds for splitting clusters , 1972 .