Enforcing Label and Intensity Consistency for IR Target Detection

TL;DR

This paper presents a novel IR target detection method that models pixel labels and intensities with Markov Random Fields, enforcing neighborhood consistency and incorporating temporal data for improved accuracy.

Contribution

It introduces a combined MRF-based approach with SAR and Auto-Logistic models for pixel-level IR target detection, integrating temporal information for enhanced performance.

Findings

Achieved high detection accuracy on benchmark datasets.

Demonstrated the effectiveness of neighborhood dependency modeling.

Improved detection performance by incorporating temporal information.

Abstract

This study formulates the IR target detection as a binary classification problem of each pixel. Each pixel is associated with a label which indicates whether it is a target or background pixel. The optimal label set for all the pixels of an image maximizes aposteriori distribution of label configuration given the pixel intensities. The posterior probability is factored into (or proportional to) a conditional likelihood of the intensity values and a prior probability of label configuration. Each of these two probabilities are computed assuming a Markov Random Field (MRF) on both pixel intensities and their labels. In particular, this study enforces neighborhood dependency on both intensity values, by a Simultaneous Auto Regressive (SAR) model, and on labels, by an Auto-Logistic model. The parameters of these MRF models are learned from labeled examples. During testing, an MRF inference technique, namely Iterated Conditional Mode (ICM), produces the optimal label for each pixel. The detection performance is further improved by incorporating temporal information through background subtraction. High performances on benchmark datasets demonstrate effectiveness of this method for IR target detection.