train-surfpmk.C File Reference

Interface for training and testing GistEstimatorSurfPMK. More...

#include "Util/log.H"

Include dependency graph for train-surfpmk.C:

Go to the source code of this file.

Functions
int	main ()

---

Detailed Description

Interface for training and testing GistEstimatorSurfPMK.

The train-bbof program in conjunction with the GistEstimatorSurfPMK class implements the following paper within the INVT framework:

Murillo, A. C., Guerrero, J. J., Sagues, C. SURF features for efficient robot localization with omnidirectional images ICRA, 2007.

Whereas the GistEstimatorSurfPMK class is only concerned with the portions of the above paper that deal with gist vector computations, this program provides the remaining structure required to implement the necessary training and image classification functionalities.

train-surfpmk has two modes of operation, viz., training and testing. Training mode consists of four distinct phases: SURF descriptor accumulation, hierarchical K-means clustering, training histograms collection, and SVM classifier generation. Testing mode operates in a single phase that uses the results of the hierarchical clustering, histograms collection and SVM classifier generation training phases to classify input images into appropriate categories.

Definition in file train-surfpmk.C.