Object detection using hierarchical MRF and MAP estimation

This paper presents a new scale, position and orientation invariant approach to object detection. The proposed method first chooses attention regions in an image based on the region detection result on the image. Within the attention regions, the method then detects targets using a novel object detection algorithm that combines template matching methods with feature-based methods via hierarchical MRF and MAP estimation. Hierarchical MRF and MAP estimation provide a flexible framework to incorporate various visual clues. The combination of template matching and feature detection helps to achieve robustness against complex backgrounds and partial occlusions in object detection. Experimental results are given in the paper.