Title: Motion estimation and spatial-temporal filter-based infrared small target detection algorithm

Authors: Zhonghua Wang; Yuan Liao; Qingping Liu; Chunyong Li

Addresses: School of Information and Engineering, Nanchang Hangkong University, Nanchang, Jiangxi Province 330063, China; Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition, Nanchang Hangkong University, Nanchang, Jiangxi Province, 330063, China ' School of Information and Engineering, Nanchang Hangkong University, Nanchang, Jiangxi Province 330063, China; Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition, Nanchang Hangkong University, Nanchang, Jiangxi Province, 330063, China ' School of Information and Engineering, Nanchang Hangkong University, Nanchang, Jiangxi Province 330063, China; Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition, Nanchang Hangkong University, Nanchang, Jiangxi Province, 330063, China ' Department of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China

Abstract: Under the effect of solar variation, atmospheric attenuation and thermal radiation distribution, the grey value of interference source is close to or equal to the target grey value. With the distance between the imaging system and the target being very long, the target is dotted or mottled in the image. In addition, the target motion is usually unknown and abrupt. All these factors cause the negative effect of small target detection. In this paper, we present a motion estimation and spatial-temporal filter-based algorithm to detect infrared small targets under complex background. The algorithm is divided into three steps: (1) researching the image transformation technology from greyscale pattern to entropy pattern; (2) studying the anisotropic smoothing and local constraint criterion of entropy flow; and (3) introducing spatial-temporal filter for detecting small targets through energy accumulation and trial search of targets. Compared to other methods, experimental results indicate that the proposed method can robustly detect small targets under complicated background.

Keywords: entropy flow; motion estimation; spatial-temporal filters; infrared targets; small target detection; image transformation; greyscale pattern; anisotropic smoothing; local constraints; small targets; energy accumulation; trial search; infrared imaging; solar variation; atmospheric attenuation; thermal radiation.

DOI: 10.1504/IJWMC.2015.069388

International Journal of Wireless and Mobile Computing, 2015 Vol.8 No.3, pp.256 - 261

Received: 30 Aug 2014
Accepted: 03 Sep 2014
Published online: 14 May 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article