A classification method based on deep representation of input data and ensembles of decision trees is introduced and evaluated solving the problem of vehicle classification and image classification with large number of categories.

As digital cameras and powerful computers have become wide spread, the number of applications using vision techniques has increased enormously. One such application that has received significant attention from the computer vision community is traffic surveillance. We propose a new traffic surveillance system that works without prior, explicit camera calibration, and has the ability to perform s...