Crop identification and area estimation by computer-aided analysis of Landsat dataThis report describes the results of a study involving the use of computer-aided analysis techniques applied to Landsat MSS data for identification and area estimation of winter wheat in Kansas and corn and soybeans in Indiana. Key elements of the approach included use of aerial photography for classifier training, stratification of Landsat data and extension of training statistics to areas without training data, and classification of a systematic sample of pixels from each county. Major results and conclusions are: (1) Landsat data was adequate for accurate identification and area estimation of winter wheat in Kansas, but corn and soybean estimates for Indiana were less accurate; (2) computer-aided analysis techniques can be effectively used to extract crop identification information from Landsat MSS data, and (3) systematic sampling of entire counties made possible by computer classification methods resulted in very precise area estimates at county as well as district and state levels.
Document ID
19780056256
Acquisition Source
Legacy CDMS
Document Type
Conference Proceedings
Authors
Bauer, M. E. (Purdue Univ. West Lafayette, IN, United States)
Hixson, M. M. (Purdue Univ. West Lafayette, IN, United States)
Davis, B. J. (Purdue Univ. West Lafayette, IN, United States)
Etheridge, J. B. (Purdue University West Lafayette, Ind., United States)
Date Acquired
August 9, 2013
Publication Date
January 1, 1977
Subject Category
Earth Resources And Remote Sensing
Meeting Information
Meeting: Annual Symposium on Machine Processing of Remotely Sensed Data