Translator Disclaimer
30 December 1994 Geometric parameter estimation for agriculture fields
Author Affiliations +
Geometric parameter estimation is a common task in remote sensing image processing. Quite often, it is needed to find out the area and location of a certain kind of crop in a remotely sensed image. If we take a parcel of a uniform crop type in a remote sensing image as an object, the task is to determine the orientation, location, and scale of the object. In this paper, we propose a model based method for parameter estimation in which the radiometric distribution obtained by radar simulation is used as a global feature of an object to characterize its spectral properties. A cost function is defined as a quantitative evaluation for the hypothesis of object parameters in terms of its feature fitting and the minimum cost corresponds to the best parameters of the object with the least misclassified pixels. The feature matching is completed through cost minimization. Experiments show that this method is quite efficient especially in the cases of bad signal to noise ratios.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Liu Lu, Fang Luo, and Nanno J. Mulder "Geometric parameter estimation for agriculture fields", Proc. SPIE 2315, Image and Signal Processing for Remote Sensing, (30 December 1994);


Non-monotonic model-based system for scene interpretation
Proceedings of SPIE (January 01 1990)
Task-focused modeling in automated agriculture
Proceedings of SPIE (January 12 1993)
Damage estimation on agricultural crops by a flood
Proceedings of SPIE (October 06 2011)
3D modeling of terrace in the Loess Plateau
Proceedings of SPIE (November 03 2008)
Bayesian inference for model-based vision
Proceedings of SPIE (February 01 1992)

Back to Top