Detection of Man-Made Structures in Natural Images Based on the Improved Discriminative Random Fields

Abstract

This paper presents a new Discriminative Random Fields (DRFs) framework. Based on the DRFs framework proposed by Kumar and Hebert, the following improvements have been conducted. Firstly, the interaction potential and the associated potential model are simplified. Secondly, we reduce the dimension of the multi-scale features, re-define dimension of the single-scale feature, and increase the color feature of man-made structure. Thirdly, the quasi-Newton method with linear search and gradient descent method are adopted to solve parameters, which get a simple model and achieve good performance. Finally, the partition function of the DRF is eliminated by using Pseudo-likelihood method for parameter learning. The simulation results show that the proposed method's false positive rate is lower than the method from Kumar and Hebert, while the correct rate and detection ratearehigher than their experimental effects after these improvements.