基于场景理解的双波段彩色融合图像质量评价

高绍姝; 金伟其; 王岭雪; 骆媛; 李家琨

基于场景理解的双波段彩色融合图像质量评价

1.
北京理工大学光电学院光电成像技术与系统教育部重点实验室,北京100081;
2.
中国石油大学(华东)计算机与通信工程学院,山东青岛266580

基金项目:

国家自然科学基金（61231014）;教育部博士学科点专项科研基金（20131101130002）;总装重点预研项目（40405030302）;技术基础项目（BQBZS20121BZ08）;“光电成像技术与系统”教育部重点实验室开放基金（2013OEIOF01）

详细信息

作者简介:
高绍姝（1983-），女，博士后，主要从事光电图像与系统质量评价方面的研究。Email：gaoshaoshu@aliyun.com

中图分类号: TN219

Quality evaluation for dual-band color fusion images based on scene understanding

1.
MoE Key Laboratory of Photoelectronic Imaging Technology and System,School of Optoelectronics,Beijing Institute of Technology,Beijing 100081,China;
2.
College of Computer and Communication Engineering,China University of Petroleum,Qingdao 266580,China

摘要: 图像质量评价是双波段彩色融合处理算法及系统评价的基础，文中研究了一种可见光与红外彩色融合图像质量评价方法。提出了基于场景理解的图像感知质量PQSU 综合评价指标，选择三类典型场景彩色融合图像进行了主观视觉评价实验；通过对已有评价指标与PQSU 综合指标的主观评价实验结果进行多元线性回归分析，建立了PQSU 的预测模型。结果表明：融合图像的场景颜色协调性与自然感高度相关；利用图像清晰度和颜色协调性可以有效地预测PQSU；针对不同场景类型，已有评价指标在PQSU 的预测模型中所占的权重有所不同，但预测模型的基本形式保持不变。文中提出的PQSU 及其预测模型为进一步发展融合图像质量客观评价模型奠定了基础。
- 质量评价 /
- 彩色融合 /
- 主观评价 /
- 评价指标
Abstract: Image quality assessments are the basis for evaluations of dual-band color fusion algorithms and systems. A method of quality evaluation for visible and infrared color fusion images was explored. A comprehensive evaluation metric, image perceptual quality based on scene understanding (PQSU) was proposed, and color fusion images of three typical scenes were selected to perform a psychophysical experiment. The prediction model of PQSU was derived by multiple linear regression analysis of the experimental data for conventional image quality metrics and the proposed evaluation metric. The results show that the positive correlation between color harmony and color naturalness is very high. The variation of PQSU can be predicted effectively by color harmony and sharpness. In the three image categories, the proportional coefficients in prediction models for PQSU are different; whereas, the basic forms of Image quality assessments are the basis for evaluations of dual-band color fusion algorithms and systems. A method of quality evaluation for visible and infrared color fusion images was explored. A comprehensive evaluation metric, image perceptual quality based on scene understanding (PQSU) was proposed, and color fusion images of three typical scenes were selected to perform a psychophysical experiment. The prediction model of PQSU was derived by multiple linear regression analysis of the experimental data for conventional image quality metrics and the proposed evaluation metric. The results show that the positive correlation between color harmony and color naturalness is very high. The variation of PQSU can be predicted effectively by color harmony and sharpness. In the three image categories, the proportional coefficients in prediction models for PQSU are different; whereas, the basic forms of prediction models are unchanged. The proposed comprehensive evaluation metric and its prediction model provide a foundation for further developing objective quality evaluation of color fusion images.
- quality evaluation /
- color fusion /
- psychophysical experiment /
- evaluation metric

[1]	Choi S Y, Luo M R, Pointer M R, et al. Investigation of large display color image appearance I: important factors affecting perceived quality [J]. Journal of Imaging Science and Technology, 2008, 25(4): 040904.
[2]
[3]	Pedersen M, Bonnier N, Hardeberg J Y, et al. Attributes of image quality for color prints [J]. Journal of Electronic Imaging, 2010, 19(1): 011016.
[4]
[5]
[6]	Essock E A, Sinai M J, McCarley J S, et al. Perceptual ability with real-world nighttime scenes: image-intensified, infrared and fused-color imagery [J]. Human Factors, 1999, 41: 438.
[7]	Toet A, Schoumans N, Ijspeert J K. Perceptual evaluation of different nighttime imaging modalities [C]//Proc of Information Fusion, 2000, 1: TUD3- 17-TUD3-23.
[8]
[9]
[10]	Toet A, Frankenb E M. Perceptual evaluation of different image fusion schemes [J]. Displays, 2003, 24: 25-37.
[11]
[12]	Shi Junsheng, Jin Weiqi, Wang Lingxue. Study on perceptual evaluation of fusion image quality for color night vision[J]. Journal Infrared Millimeter and Waves, 2005, 24(3): 236-240. (in Chinese) 石俊生, 金伟其, 王岭雪. 视觉评价夜视彩色融合图像质量的实验研究[J]. 红外与毫米波学报, 2005, 24(3): 236-240.
[13]
[14]	Krebs W K, Sinai M J. Psychophysical assessments of image-sensor fused imagery [J]. Human Factors, 2002, 44: 257-271.
[15]	Xu Guili, Liu Xiaoxia, Tian Yupeng, et al. Image clarity- evaluation-function method[J]. Infrared and Laser Engineering, 2009, 38(1): 180-184. (in Chinese) 徐贵力, 刘小霞, 田裕鹏, 等. 一种图像清晰度评价方法[J]. 红外与激光工程, 2009, 38(1): 180-184.
[16]
[17]
[18]	Caviedes J, Oberti F. A new sharpness metric based on local kurtosis, edge and energy information[J]. Signal Processing: Image Communication, 2004, 19: 147-161.
[19]
[20]	Guan Shingsheng, Hung Posung. Influences of psychological factors on image color preferences evaluation [J]. Color Research and Application, 2010, 35(3): 213-232.
[21]
[22]	Burchett K E. Color harmony [J]. Color Research and Application, 2002, 27(1): 28-31.
[23]	Yendrikhovskij S N, Blommaert F J J, Ridder H. Color reproduction and the naturalness constraint[J]. Color Research and Application, 1999, 24(1): 52-67.
[24]
[25]	Toet A, Walraven J. New false color mapping for image fusion[J]. Optical Engineering, 1996, 35(3): 650-658.
[26]
[27]	Waxman A M, Gove A N, Fay D A, et al. Night vision: opponent processing in the fusion of visible and IR imagery[J]. Neural Networks, 1997, 10(1): 1-6.
[28]
[29]	Wang Lingxue, Shi Shiming, Jin Weiqi, et al. Hot targets enhancement for color fusion of visible and infrared image[J]. Transactions of Beijing Institute of Technology, 2008, 28(1): 1-4. (in Chinese) 王岭雪, 史世明, 金伟其, 等. 可见光与红外图像彩色融合中的热目标增强方法[J]. 北京理工大学学报, 2008, 28(1):1-4.
[30]
[31]
[32]	Shi Shiming, Wang Lingxue, Jin Weiqi, et al. A dual-band color imaging system for visible and thermal IR images based on color transfer in YUV color space [J]. Acta Armamentarii, 2009, 30(1): 30-35. (in Chinese) 史世明, 王岭雪, 金伟其, 等. 基于YUV 空间色彩传递的可见光/热成像双通道彩色成像系统[J]. 兵工学报, 2009, 30(1): 30-35.
[33]
[34]	Shi Shiming, Wang Lingxue, Jin Weiqi, et al. Natural-color- appearance steerable pyramid color fusion for visible and IR images [J]. Journal of Optoelectronics Laser, 2009, 20 (11): 1552-1560. (in Chinese) 史世明, 王岭雪, 金伟其, 等. 自然感色彩的可见光/红外控向金字塔融合[J]. 光电子激光, 2009, 20(11): 1552-1560.
[35]	Shi Shiming, Wang Lingxue, Jin Weiqi, et al. Color night vision based on color transfer in YUV color space[C]//SPIE, 2008, 6623: 66230B.
[36]
[37]
[38]	Shi Shiming, Wang Lingxue, Jin Weiqi, et al. Color night vision research based on multi-resolution color transfer [J]. Acta Photonica Sinica, 2010, 39(3): 553-558. (in Chinese) 史世明, 王岭雪, 金伟其, 等. 基于多分辨率色彩传递的彩色夜视方法研究[J]. 光子学报, 2010, 39(3): 553-558.
[39]
[40]
[41]	Berns R S. Methods for characterizing CRT displays [J]. Displays, 1996, 16: 173-182.
[42]
[43]	ITU -R Recommendation BT.500 -12. Methodology for the subjective assessment of the quality of the television pictures[S]. 2010.
[44]	Draper N R, Smith H. Applied Regression Analysis [M]. 3d ed. New York: John Wiley Sons, Inc, 1998: 335-345.

[1]	潘宏亮, 孙金霞, 韩希珍. 图像清晰度评价与变步长融合调焦方法 . 红外与激光工程, 2023, 52(1): 20220342-1-20220342-6. doi: 10.3788/IRLA20220342
[2]	任平川, 周琦, 金荷, 宋卿争, 缪鹏飞. 星敏感器动态精度评价方法 . 红外与激光工程, 2022, 51(3): 20210571-1-20210571-8. doi: 10.3788/IRLA20210571
[3]	范有臣, 马旭, 马淑丽, 钱克昌, 郝红星. 基于深度学习的激光干扰效果评价方法 . 红外与激光工程, 2021, 50(S2): 20210323-1-20210323-7. doi: 10.3788/IRLA20210323
[4]	王铭赫, 李硕, 金伟其, 米凤文. HDR热成像系统动态范围特性测试评价方法 . 红外与激光工程, 2021, 50(9): 20210526-1-20210526-10. doi: 10.3788/IRLA20210526
[5]	郭金权, 李国元, 左志强, 张宁, 裴亮, 卢刚. 高分七号卫星激光测高仪全波形数据质量及特征分析 . 红外与激光工程, 2020, 49(S2): 20200387-20200387. doi: 10.3788/IRLA20200387
[6]	韩宏伟, 张晓晖. 烟幕对红外热成像干扰效果评价 . 红外与激光工程, 2018, 47(12): 1204004-1204004(5). doi: 10.3788/IRLA201847.1204004
[7]	徐滨士, 董世运, 门平, 闫世兴. 激光增材制造成形合金钢件质量特征及其检测评价技术现状(特邀) . 红外与激光工程, 2018, 47(4): 401001-0401001(9). doi: 10.3788/IRLA201847.0401001
[8]	牛威, 郭世平, 史江林, 邹建华, 张荣之. 自适应光学成像事后处理LoG域匹配图像质量评价 . 红外与激光工程, 2018, 47(11): 1111005-1111005(9). doi: 10.3788/IRLA201847.1111005
[9]	姚旺, 刘云鹏, 朱昌波. 基于人眼视觉特性的深度学习全参考图像质量评价方法 . 红外与激光工程, 2018, 47(7): 703004-0703004(8). doi: 10.3788/IRLA201847.0703004
[10]	骆媛, 张科, 纪明. 增强无人机态势感知的彩色图像融合方法 . 红外与激光工程, 2016, 45(S1): 200-206. doi: 10.3788/IRLA201645.S126002
[11]	高绍姝, 金伟其, 王延江, 张晓东. 灰度融合图像目标与背景感知对比度客观评价模型 . 红外与激光工程, 2015, 44(5): 1660-1665.
[12]	刘恂, 华文深, 杨佳. 面向高光谱探测的伪装效果评价方法 . 红外与激光工程, 2014, 43(10): 3228-3232.
[13]	赵宏超, 张景旭, 张丽敏, 张彬. TMT三镜面形评价过程 . 红外与激光工程, 2014, 43(12): 3983-3987.
[14]	邓潺, 刘文, 黄彪, 詹振环, 张欣. 基于多核DSP 的微光与红外图像彩色融合系统 . 红外与激光工程, 2014, 43(9): 3141-3145.
[15]	苏宇, 高绍姝, 金伟其, 贾晓婷, 潘定平, 刘佳妮, 金凯佳. 典型场景彩色融合图像颜色协调性的主观评价 . 红外与激光工程, 2014, 43(11): 3767-3774.
[16]	崔建平, 王吉晖, 金伟其, 白廷柱, 高稚允. 焦平面热成像系统离散采样性能评价方法 . 红外与激光工程, 2013, 42(8): 1973-1978,2007.
[17]	郭惠楠, 曹剑中, 周祚峰, 唐利孬, 王华, 马楠. 基于色彩相关性的彩色图像清晰度评价算法 . 红外与激光工程, 2013, 42(11): 3132-3136.
[18]	张勇, 金伟其. 夜视融合图像质量客观评价方法 . 红外与激光工程, 2013, 42(5): 1360-1365.
[19]	安振宇, 史振威. 基于sc-NMF的高光谱图像融合 . 红外与激光工程, 2013, 42(10): 2718-2723.
[20]	张勇, 金伟其. 夜视融合图像质量主观评价方法 . 红外与激光工程, 2013, 42(2): 528-532.

点击查看大图

计量

文章访问数: 296
HTML全文浏览量: 65
PDF下载量: 214
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

基于场景理解的双波段彩色融合图像质量评价

作者简介:
高绍姝（1983-），女，博士后，主要从事光电图像与系统质量评价方面的研究。Email：gaoshaoshu@aliyun.com

Quality evaluation for dual-band color fusion images based on scene understanding

计量

基于场景理解的双波段彩色融合图像质量评价

1. 北京理工大学光电学院光电成像技术与系统教育部重点实验室,北京100081;

2. 中国石油大学(华东)计算机与通信工程学院,山东青岛266580

作者简介:
高绍姝（1983-），女，博士后，主要从事光电图像与系统质量评价方面的研究。Email：gaoshaoshu@aliyun.com

English Abstract

Quality evaluation for dual-band color fusion images based on scene understanding

1. MoE Key Laboratory of Photoelectronic Imaging Technology and System,School of Optoelectronics,Beijing Institute of Technology,Beijing 100081,China;

2. College of Computer and Communication Engineering,China University of Petroleum,Qingdao 266580,China

全文HTML

目录

留言板

基于场景理解的双波段彩色融合图像质量评价

作者简介: 高绍姝（1983-），女，博士后，主要从事光电图像与系统质量评价方面的研究。Email：gaoshaoshu@aliyun.com

Quality evaluation for dual-band color fusion images based on scene understanding

计量

出版历程

基于场景理解的双波段彩色融合图像质量评价

1. 北京理工大学光电学院光电成像技术与系统教育部重点实验室,北京100081; 2. 中国石油大学(华东)计算机与通信工程学院,山东青岛266580

作者简介: 高绍姝（1983-），女，博士后，主要从事光电图像与系统质量评价方面的研究。Email：gaoshaoshu@aliyun.com

English Abstract

Quality evaluation for dual-band color fusion images based on scene understanding

1. MoE Key Laboratory of Photoelectronic Imaging Technology and System,School of Optoelectronics,Beijing Institute of Technology,Beijing 100081,China; 2. College of Computer and Communication Engineering,China University of Petroleum,Qingdao 266580,China

全文HTML

目录

作者简介:
高绍姝（1983-），女，博士后，主要从事光电图像与系统质量评价方面的研究。Email：gaoshaoshu@aliyun.com

1. 北京理工大学光电学院光电成像技术与系统教育部重点实验室,北京100081;

2. 中国石油大学(华东)计算机与通信工程学院,山东青岛266580

作者简介:
高绍姝（1983-），女，博士后，主要从事光电图像与系统质量评价方面的研究。Email：gaoshaoshu@aliyun.com

1. MoE Key Laboratory of Photoelectronic Imaging Technology and System,School of Optoelectronics,Beijing Institute of Technology,Beijing 100081,China;

2. College of Computer and Communication Engineering,China University of Petroleum,Qingdao 266580,China