Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
5488632 | Infrared Physics & Technology | 2017 | 16 Pages |
Abstract
Blind pixel compensation is an ill-posed inverse problem of infrared imaging systems and image restoration. The performance of a blind pixel compensation algorithm depends on the accuracy of estimation for the underlying true infrared images. We propose an adaptive regression method (ARM) for blind pixel compensation that integrates the multi-scale framework with a regression model. A blind-pixel is restored by exploiting the intra-scale properties through the nonparametric regressive estimation and the inter-scale characteristics via parametric regression for continuous learning. Combining the respective strengths of a parametric model and a nonparametric model, ARM establishes a set of multi-scale blind-pixel compensation method to correct the non-uniformity based on key frame extraction. Therefore, it is essentially different from the traditional frameworks for blind pixel compensation which are based on filtering and interpolation. Experimental results on some challenging cases of blind compensation show that the proposed algorithm outperforms existing methods by a significant margin in both isolated blind restoration and clustered blind restoration.
Related Topics
Physical Sciences and Engineering
Physics and Astronomy
Atomic and Molecular Physics, and Optics
Authors
Suting Chen, Hao Meng, Tao Pei, Yanyan Zhang,