Sparse-representation-based clutter metric

Abstract

Background clutter is becoming one of the most important factors affecting the target acquisition performance of electro-optical imaging systems. A novel clutter metric based on sparse representation is proposed in this paper. Based on sparse representation, the similarity vector is defined to describe the similarity between the background and the target in the feature domain, which is a typical feature of the background clutter. This newly proposed metric is applied to the Search_2 data set, and the experiment results show that its prediction correlates well with the detection probability of observers.

© 2011 Optical Society of America

Selective visual attention based clutter metric with human visual system adaptability

Bo Zheng, Xiao-Dong Wang, Jing-Tao Huang, Jian Wang, and Yang Jiang
Appl. Opt. 55(27) 7700-7706 (2016)

Target acquisition performance in a cluttered environment

Qian Li, Cui Yang, and Jian-Qi Zhang
Appl. Opt. 51(31) 7668-7673 (2012)

Multi-class remote sensing object recognition based on discriminative sparse representation

Xin Wang, Siqiu Shen, Chen Ning, Fengchen Huang, and Hongmin Gao
Appl. Opt. 55(6) 1381-1394 (2016)

Clutter metric based on the Cramer-Rao lower bound on automatic target recognition

Guojing He, Jianqi Zhang, Delian Liu, and Honghua Chang
Appl. Opt. 47(29) 5534-5540 (2008)

Robust infrared small target detection via non-negativity constraint-based sparse representation

Minjie Wan, Guohua Gu, Weixian Qian, Kan Ren, and Qian Chen
Appl. Opt. 55(27) 7604-7612 (2016)