Statistical pattern recognition in remote sensing

  • Authors:
  • Chi Hau Chen;Pei-Gee Peter Ho

  • Affiliations:
  • Electrical and Computer Engineering Department, University of Massachusetts Dartmouth, 285 Old Westport Road, N. Dartmouth, MA 02747, USA;Electrical and Computer Engineering Department, University of Massachusetts Dartmouth, 285 Old Westport Road, N. Dartmouth, MA 02747, USA

  • Venue:
  • Pattern Recognition
  • Year:
  • 2008

Quantified Score

Hi-index 0.01

Visualization

Abstract

Remote sensing with sensors mounted on satellites or aircrafts is much needed for resource management, environmental monitoring, disaster response, and homeland defense. Remote sensing data considered include those from multispectral, hyperspectral, radar, optical, and infrared sensors. Classification is often one of the major tasks in information processing. For example, we need to identify vegetations, waterways, and man-made structures from remote sensing of earth. The large amount of data available makes remote sensing data uniquely suitable for statistical pattern recognition. This paper will address several issues on statistical pattern recognition that are related to information processing in remote sensing. Though the paper is largely tutorial in nature, some specific issues considered are image models for characterization of contextual information, neural networks for image classification, and the performance measures. Either to supplement the capability of sensors or to effectively utilize the enormous amount of sensor data, many advances in statistical pattern recognition can be very useful in machine recognition of the data. The potentials and opportunities of using statistical pattern recognition in remote sensing are indeed unlimited.