Vehicle detection using PLS Hough transform

Abstract

This paper proposes extended Generalized Hough Transform (GHT) to introduce training process by using Partial Least Squares (PLS) regression analysis. Hough transform can robustly detect patterns against noise and occlusions, and GHT is adapted to perform the generic object detection. In this study, we introduced training process to determine the voting weight of GHT by using PLS regression analysis. Thereby, it becomes possible to generic object detection, while maintaining the framework of Hough-based object detection. In this paper, we applied PLS Hough transform to the vehicle detection from satellite images. In addition, we compared PLS Hough transform with the previous approach (original GHT) on the vehicle detection, and our proposed method achieved high detection accuracy.