级联残差学习的红外图像非均匀性校正方法

doi:10.19665/j.issn1001-2400.2019.01.003

西安电子科技大学学报 ›› 2019, Vol. 46 ›› Issue (1): 14-19.doi: 10.19665/j.issn1001-2400.2019.01.003

级联残差学习的红外图像非均匀性校正方法

赖睿¹,官俊涛¹,徐昆然¹,熊皑²,杨银堂¹

^1. 西安电子科技大学微电子学院,陕西西安 710071
^2. 成都信息工程大学控制工程学院,四川成都 610103

收稿日期:2018-06-10 出版日期:2019-02-20 发布日期:2019-03-05
作者简介:赖睿(1980-),男,副教授,E-mail: rlai@mail.xidian.edu.cn
基金资助:
国家自然科学基金(61674120);中央高校基本科研业务费专项资金(300102328110);中央高校基本科研业务费专项资金(JBG161113)

Cascade residual learning method for infrared image nonuniformity correction

LAI Rui¹,GUAN Juntao¹,XU Kunran¹,XIONG Ai²,YANG Yintang¹

^1. School of Microelectronics, Xidian Univ., Xi’an 710071, China;
^2. School of Control Engineering, Chengdu University of Information Technology, Chengdu 610103, China

Received:2018-06-10 Online:2019-02-20 Published:2019-03-05

摘要/Abstract

摘要：

针对现有场景自适应非均匀性校正方法存在的图像过平滑和非均匀性残留问题,提出了一种基于级联残差学习的非均匀性校正方法。该方法将多尺度特征提取单元所获取的特征进行融合,并运用残差学习策略解决深度神经网络的过拟合问题。实验结果表明,该方法在平均峰值信噪比上较传统的场景自适应校正方法有近5dB的提升,主观视觉效果也更加清晰锐利。

关键词: 深度学习, 非均匀性校正, 图像去噪, 红外图像处理

Abstract:

Traditional scene adaptive nonuniformity correction methods generally suffer from the over smooth and residual nonuniformity in the corrected results. In view of this, a cascade residual learning based nonuniformity correction method is presented. This method uses the multiscale feature extraction unit to fuse the extracted features and employs the residual learning strategy to deal with the overfitting problem. Experimental results validate that the proposed method yields nearly 5dB improvement in the average peak signal-to-noise ratio (PSNR) as compared to the traditional scene adaptive correction methods. Moreover, its visual effects are clearer and sharper.

Key words: deep learning, nonuniformity correction, image denoising, infrared image processing

中图分类号:

TN215

赖睿,官俊涛,徐昆然,熊皑,杨银堂. 级联残差学习的红外图像非均匀性校正方法[J]. 西安电子科技大学学报, 2019, 46(1): 14-19.

LAI Rui,GUAN Juntao,XU Kunran,XIONG Ai,YANG Yintang. Cascade residual learning method for infrared image nonuniformity correction[J]. Journal of Xidian University, 2019, 46(1): 14-19.

图/表 6

图1

图2

图3

表1

图4

表2

参考文献 13

[1]	RONG S H, ZHOU H X, QIN H L , et al. Guided Filter and Adaptive Learning Rate Based Non-uniformity Correction Algorithm for Infrared Focal Plane Array[J]. Infrared Physics and Technology, 2016,76:691-697. doi: 10.1016/j.infrared.2016.04.037
[2]	SCRIBNER D A, SARKADY K A, KRUER M R, et al. Adaptive Retina-like Preprocessing for Imaging Detector Arrays [C]//Proceedings of the IEEE International Conference on Neural Networks. Piscataway: IEEE, 1993: 1955-1960.
[3]	HARRIS J G, CHIANG Y M. Minimizing the Ghosting Artifact in Scene-based Nonuniformity Correction [C]//The International Society for Optics Engineering: 3377. Bellingham: SPIE, 1998: 106-113.
[4]	QIAN W, CHEN Q, GU G . Space Low-pass and Temporal High-pass Nonuniformity Correction Algorithm[J]. Optical Review, 2010,17(1):24-29. doi: 10.1007/s10043-010-0005-8
[5]	BOUTEMEDJET A, DENG C, ZHAO B . Robust Approach for Nonuniformity Correction in Infrared Focal Plane Array[J]. Sensors, 2016,16(11):1890. doi: 10.3390/s16111890 pmid: 5134549
[6]	刘如意, 宋建锋, 权义宁 , 等. 一种自动的高分辨率遥感影像道路提取方法[J]. 西安电子科技大学学报, 2017,44(1):100-105. doi: 10.3969/j.issn.1001-2400.2017.01.018
	LIU Ruyi, SONG Jianfeng, QUAN Yining , et al. Automatic Road Extraction Method for High-resolution Remote Sensing Images[J]. Journal of Xidian University, 2017,44(1):100-105. doi: 10.3969/j.issn.1001-2400.2017.01.018
[7]	史鹤欢, 许悦雷, 马时平 , 等. PCA预训练的卷积神经网络目标识别算法[J]. 西安电子科技大学学报, 2016,43(3):161-166. doi: 10.3969/j.issn.1001-2400.2016.03.028
	SHI Hehuan, XU Yuelei, MA Shiping , et al. Convolutional Neural Networks Recognition Algorithm Based on PCA[J]. Journal of Xidian University, 2016,43(3):161-166. doi: 10.3969/j.issn.1001-2400.2016.03.028
[8]	ZHANG K, ZUO W, CHEN Y , et al. Beyond a Gaussian Denoiser: Residual Learning of Deep Cnn for Image Denoising[J]. IEEE Transactions on Image Processing, 2017,26(7):3142-3155. doi: 10.1109/TIP.2017.2662206 pmid: 28166495
[9]	SZEGEDY C, LIU W, JIA Y, et al. Going Deeper with Convolutions [C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2015: 1-9.
[10]	HE K, ZHANG X, REN S, et al. Deep Residual Learning for Image Recognition [C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington: IEEE Computer Society, 2016: 770-778.
[11]	DONG C, LOY C C, HE K , et al. Image Super-resolution Using Deep Convolutional Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016,38(2):295-307. doi: 10.1109/TPAMI.2015.2439281 pmid: 26761735
[12]	VERA E, MEZA P, TORRES S . Total Variation Approach for Adaptive Nonuniformity Correction in Focal-plane Arrays[J]. Optics Letters, 2011,36(2):172-174. doi: 10.1364/OL.36.000172 pmid: 21263490
[13]	HAYAT M M, TORRES S N, ARMSTRONG E , et al. Statistical Algorithm for Nonuniformity Correction in Focal-plane Arrays[J]. Applied Optics, 1999,38(5):772-780. doi: 10.1364/AO.38.000772 pmid: 18305743

评价指标	污染图像	校正后图像
评价指标	污染图像	NN-NUC	TV-NUC	文中方法
峰值信噪比/dB	20.29	28.10	28.31	33.25
粗糙度	0.2760	0.1093	0.1083	0.0835

图像序列	图像分辨率	处理速度/(帧·秒^-1)
图像序列	图像分辨率	NN-NUC	TV-NUC	文中方法
测试序列1	320×256	628	549	42
测试序列2	384×288	580	443	29

[1]	刘佳玮,张文辉,寇晓丽,李雁妮. 增强型深度对抗样本攻击防御算法[J]. 西安电子科技大学学报, 2021, 48(6): 23-31.
[2]	李鹏,冯存前,许旭光,唐子翔. 一种利用贝叶斯优化的弹道目标微动分类网络[J]. 西安电子科技大学学报, 2021, 48(5): 139-148.
[3]	闫佳,曹玉东,任佳兴,陈冬昊,李晓会. 深度非对称压缩型哈希算法[J]. 西安电子科技大学学报, 2021, 48(5): 212-221.
[4]	宁阳,杜建超,韩硕,杨传凯. 改进DeeplabV3+的火焰分割与火情分析方法[J]. 西安电子科技大学学报, 2021, 48(5): 38-46.
[5]	周鹏,杨军. 采用神经网络架构搜索的遥感影像分割方法[J]. 西安电子科技大学学报, 2021, 48(5): 47-57.
[6]	戚艳军,孔月萍,王佳婧,朱旭东. 一种LSTM与CNN相结合的步态识别方法[J]. 西安电子科技大学学报, 2021, 48(5): 78-85.
[7]	宋建锋,苗启广,王崇晓,徐浩,杨瑾. 注意力机制的多尺度单目标跟踪算法[J]. 西安电子科技大学学报, 2021, 48(5): 110-116.
[8]	张宇浩,程培涛,张书豪,王秀美. 一种自适应权重学习的轻量超分辨率重建网络[J]. 西安电子科技大学学报, 2021, 48(5): 15-22.
[9]	回海生,张雪英,吴泽林,李凤莲. 一种主辅路径注意力补偿的脑卒中病灶分割方法[J]. 西安电子科技大学学报, 2021, 48(4): 200-208.
[10]	乔鱼,冯象初. 博弈方法下的图像去噪与边界提取[J]. 西安电子科技大学学报, 2021, 48(4): 128-135.
[11]	宋剑桥,王峰,牛锦,师泽洲,马军辉. 一种面向时空神经网络的潜在情绪识别方法[J]. 西安电子科技大学学报, 2021, 48(4): 159-167.
[12]	孙豪杰,李苗钰,章盼盼,许鹏飞. 用于面瘫分级的自监督非对称特征学习方法[J]. 西安电子科技大学学报, 2021, 48(3): 115-122.
[13]	张华,高浩然,杨兴国,李文敏,高飞,温巧燕. TargetedFool:一种实现有目标攻击的算法[J]. 西安电子科技大学学报, 2021, 48(1): 149-159.
[14]	杨宏宇,曾仁韵. 一种深度学习的网络安全态势评估方法[J]. 西安电子科技大学学报, 2021, 48(1): 183-190.
[15]	张璐,孙蓉,刘景伟. 分布式存储中的克隆piggybacking框架[J]. 西安电子科技大学学报, 2020, 47(6): 139-147.

级联残差学习的红外图像非均匀性校正方法

Cascade residual learning method for infrared image nonuniformity correction

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 13

相关文章 15

Metrics

本文评价

推荐阅读 10