Applicability of pattern recognition techniques to the analysis of urban quality from satellites

摘要

The information available in space imagery (Apollo, ERTS, etc.) of urban features is perishable. Near-real time extraction and application of urban quality information from space imagery is important in the light of the perishability of these types of data. Automated pattern recognition and classical photointerpretation methods are relevant to that problem.Initial efforts currently under way at Allied Research Associates, Inc., Earth Resource Analysis Center, are directed toward development of techniques for: 1.a. Urban quality analysis through spatial density evaluation.2.b. Analysis of urban quality through Fourier transforms of space imagery.Future application of hardwired Fourier operators mounted on the spacecraft and operating on imagery transforms could provide data compression, thereby reducing the burden imposed on the down-link, and permit near-real time application of the reduced data to various user-oriented decision models.