Volume IV-3
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-3, 105-112, 2018
https://doi.org/10.5194/isprs-annals-IV-3-105-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-3, 105-112, 2018
https://doi.org/10.5194/isprs-annals-IV-3-105-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

  23 Apr 2018

23 Apr 2018

FASTER TREES: STRATEGIES FOR ACCELERATED TRAINING AND PREDICTION OF RANDOM FORESTS FOR CLASSIFICATION OF POLSAR IMAGES

Ronny Hänsch and Olaf Hellwich Ronny Hänsch and Olaf Hellwich
  • Computer Vision & Remote Sensing, Technische Universität Berlin, Germany

Keywords: Random Forest, PolSAR, Information Extraction, Classification, Computation Time

Abstract. Random Forests have continuously proven to be one of the most accurate, robust, as well as efficient methods for the supervised classification of images in general and polarimetric synthetic aperture radar data in particular. While the majority of previous work focus on improving classification accuracy, we aim for accelerating the training of the classifier as well as its usage during prediction while maintaining its accuracy. Unlike other approaches we mainly consider algorithmic changes to stay as much as possible independent of platform and programming language. The final model achieves an approximately 60 times faster training and a 500 times faster prediction, while the accuracy is only marginally decreased by roughly 1 %.