10 February 2017 Infrared small target tracking by discriminative classification based on Gaussian mixture model in compressive sensing domain
Author Affiliations +
Proceedings Volume 10250, International Conference on Optical and Photonics Engineering (icOPEN 2016); 102502L (2017) https://doi.org/10.1117/12.2266719
Event: Fourth International Conference on Optical and Photonics Engineering, 2016, Chengdu, China
Abstract
Addressing the problems of infrared small target tracking in forward looking infrared (FLIR) system, a new infrared small target tracking method is presented, in which features binding of both target gray intensity and spatial relationship is implemented by compressive sensing so as to construct the Gaussian mixture model of compressive appearance distribution. Subsequently, naive Bayesian classification is carried out over testing samples acquired with non-uniform sampling probability to identify the most credible location of targets from background scene. A series of experiments are carried out over four infrared small target image sequences with more than 200 images for each sequence, the results demonstrate the effectiveness and advantages of the proposed method in both success rate and precision rate.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Chuanyun Wang, Chuanyun Wang, Fei Song, Fei Song, Shiyin Qin, Shiyin Qin, } "Infrared small target tracking by discriminative classification based on Gaussian mixture model in compressive sensing domain", Proc. SPIE 10250, International Conference on Optical and Photonics Engineering (icOPEN 2016), 102502L (10 February 2017); doi: 10.1117/12.2266719; https://doi.org/10.1117/12.2266719
PROCEEDINGS
9 PAGES


SHARE
Back to Top