弹载侦察图像质量评价方法研究

doi:10.3969/j.issn.1000-1093.2017.01.009

摘要/Abstract

摘要： 针对弹载侦察图像由于受成像平台和条件限制存在多类型混杂失真，为了对图像后续处理和成像系统性能优化提供重要量化依据和指标参考，开展此类图像质量评价研究。分析了弹载侦察图像的特点，针对成像平台的多自由度、多姿态变化情况，提取与相机抖动、结构变化、颜色丢失相关的3类11种图像特征，利用高分辨率测绘图像作为原始图像集，分块提取特征进行多元高斯模型(MVG)拟合获得基准分布特性，对弹载图像也进行分块处理获得对应MVG分布特性，比较其与基准MVG特性马氏距离作为子块质量得分，计算各子块的得分均值作为整幅图像最终得分。以实际弹载成像平台获取的图像进行了实验验证。实验结果表明：与盲图像质量测度算法、基于离散余弦变换的图像完整性测度改进算法、基于失真度识别的图像验证与完整性评价算法、质量感知聚类算法、盲图像质量空域测度算法、自然图像质量测度算法、整体与局部的自然图像质量测度算法7种其他经典方法相比，该算法具有更好的准确度和主客观一致性。

关键词: 兵器科学与技术, 图像质量评价, 弹载侦察图像, 自然场景统计, 图像特征

Abstract: Many types of hybrid distortion of on-board reconnaissance images happen due to the imaging platform and constraints. The image quality assessment is carried out in order to provide an important quantitative basis and reference for the performance optimization of the image processing and imaging systems. The characteristics of on-board reconnaissance image are analyzed. In consideration of mutli-degree-of-freedom and multi-attitude change of imaging platform, 11 kinds of image features related to camera shake, structure change and color loss are extracted. The sub-block image features are extracted for multivariate Gaussian (MVG) fitting to obtion benchmark distribution characteristics by using high resolution mapping images as original image set, and the on-board reconnaissance images are also processed to obtain corresponding MVG distribution characteristics. The benchmark distribution characteristics are compared to the MVG distribution characteristics, and Mahalanobis distance is calculated as a score of block quality. The mean score of each sub-block is taken as final score of whole image. The images obtained by the actual on-board imaging platform are verified. The result shows that the proposed method has higher assessment accuracy. Key

Key words: ordnancescienceandtechnology, imagequalityassessment, on-boardimage, naturalscenestatistics, imagefeature

中图分类号:

TP391.413

李从利, 薛松, 陆文骏, 袁广林, 秦晓燕. 弹载侦察图像质量评价方法研究[J]. 兵工学报, 2017, 38(1): 64-72.

LI Cong-li， XUE Song， LU Wen-jun， YUAN Guang-lin， QIN Xiao-yan. Research on On-board Reconnaissance Images Quality Assessment[J]. Acta Armamentarii, 2017, 38(1): 64-72.

参考文献

［1］尤海平. 别样新锋:侦察弹[J]. 兵器知识, 2006(1):44-47.
YOU Hai-ping. Battle field image scout projectile[J]. Ordnance Knowledge, 2006(1):44-47.(in Chinese)
[2］桂延宁, 焦李成, 张福顺. 弹载图像小波实时处理技术研究[J]. 电波科学学报, 2002, 17(6):595-598.
GUI Yan-ning, JIAO Li-cheng, ZHANG Fu-shun. A real-time processing technique for onboard image based on wavelet transform[J]. Chinese Journal of Radio Science, 2002, 17(6):595-598. (in Chinese)
[3］岳冬雪, 黄新生, 谭红力. 基于仿射投影的弹载图像几何失真校正方法[J]. 中国图象图形学报, 2009, 14(4):663-668.
YUE Dong-xue, HUANG Xin-sheng, TAN Hong-li. Geometric distortion correction of missile-borne image[J]. Journal of Image and Graphics, 2009, 14(4):663-668.(in Chinese)
[4］钱立志, 王曙光, 张江辉, 等. 一种弹载视频图像实时消旋方法[J]. 弹箭与制导学报, 2009, 29(3):20-22.
QIAN Li-zhi, WANG Shu-guang, ZHANG Jiang-hui, et al. A real-time despinning method for onboard video image[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2009, 29(3):20-22.(in Chinese)
[5］李从利, 薛模根, 冷晓艳, 等. 空中侦察序列图像连续拼接的累积误差分析与消除[J]. 中国图象图形学报, 2008, 13(4):814-819.
LI Cong-li, XUE Mo-gen, LENG Xiao-yan, et al. Analysis and elimination on aerial recon sequential image stitching accumulative error[J]. Joural of Image and Graphics, 2008, 13(4):814-819.(in Chinese)
[6］刘洁瑜, 徐军辉, 汪立新. 基于结构信息分布的图像质量评估新算法[J]. 兵工学报, 2010, 31(8):1053-1058.
LIU Jie-yu, XU Jun-hui, WANG Li-xin. A novel image quality evaluation method based on structure information distribution[J]. Acta Armamentarii, 2010, 31(8):1053-1058.(in Chinese)
[7］ Pan F, Lin X, Rahardja S. A locally adaptive algorithm for measuring blocking artifacts in images and videos[J]. Signal Processing Image Communication, 2004, 19(6):499-506.
[8］ Liu H, Klomp N, Heynderickx I. A no-reference metric for perceived ringing artifacts in images[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2010, 20(4):529-539.
[9］ Ferzli R, Karam L J. A no-reference objective image sharpness metric based on the notion of just noticeable blur[J]. IEEE Transactions on Image Processing, 2009, 18(4):717-728.

[10］ Moorthy A K, Bovik A C. A two-step framework for constructing blind image quality indices[J]. IEEE Signal Processing Letters, 2010, 17(5):513-516.
[11］ Moorthy A K, Bovik A C. Blind image quality assessment: from natural scene statistics to perceptual quality[J]. IEEE Transactions on Image Processing, 2011, 20(12):3350-3364.
[12］ Saad M A, Bovik A C, Charrier C. Model-based blind image quality assessment: a natural scene statistics approach in the DCT domain[J]. IEEE Transactions on Image Processing, 2012, 21(8): 3339-9952.
[13］ Mittal A, Moorthy A K, Bovik A C. No-reference image quality assessment in the spatial domain[J]. IEEE Transactions on Image Processing, 2012, 21(12):4695-4708.
[14］ Ye P, Kumar J, Kang L, et al. Unsupervised featurelearning framework for no-reference image quality assessment[C]∥2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI, US:IEEE, 2012:1098-1105.
[15］ Mittal A, Muralidhar G S, Ghosh J, et al. Blind image quality assessment without human training using latent quality factors[J]. IEEE Signal Processing Letters, 2012, 19(2):75-78.
[16］ Zhang L, Zhang L, Bovik A C. A feature-enriched completely blind image quality evaluator[J]. IEEE Transactions on Image Processing, 2015, 24(8):2579-2591.
[17］ Oh T, Park J, Seshadrinathan K, et al. No-reference sharpness assessment of camera-shaken images by analysis of spectral structure[J]. IEEE Transactions on Image Processing, 2014, 23(12): 5428-5439.
[18］ Geisler W S. Visual perception and the statistical properties of natural scenes[J]. Annual Review of Psychology, 2008, 59(1): 167-192.
[19］ Simoncelli E P, Olshausen B A. Natural image statistics and neural representation[J]. Annual Review of Neuroscience, 2001, 24(5):1193-1216.
[20］ Ruderman D L. The statistics of natural images[J]. Network Computation in Neural Systems, 1994, 5(4):517-548.
[21］ Groen I I A, Ghebreab S, Prins H, et al. From image statistics to scene gist: evoked neural activity reveals transition from low-level natural image structure to scene category[J]. Journal of Neuroscience, 2013, 33(48):18814-18824.
[22］杨红颖, 吴俊峰, 于永健, 等. 一种基于HSV空间的彩色边缘图像检索方法[J]. 中国图象图形学报, 2008, 13(10):2035-2038.
YANG Hong-ying, WU Jun-feng, YU Yong-jian, et al. Content based image retrieval using color edge[J]. Joural of Image and Graphics, 2008, 13(10):2035-2038.(in Chinese)
[23］ Hasler D, Suesstrunk S E. Measuring colorfulness in natural images[J]. Proceedings of SPIE, 2003, 5007:87-95.
[24］ Bishop C. Pattern recognition and machine learning[M]. NY, US:Springer, 2006.
[25］ Zhang L, Zhang L, Mon X. FSIM:a feature similarity index for image quality assessment[J]. IEEE Transactions on Image Processing, 2011, 20(8):2378-2386.
[26］ Xue W，Zhang L，Mou X, Learning without human scores for blind image quality assessment[J]. Computer Vision & Pattern Recognition, 2013, 9(4):995-1002.
[27］ Rohaly A MJ, Corriveau P, Libert J M, et al. Video quality experts group: current results and future directions[C]∥SPIE Conference on Visual Communications and Image Processing. Perth, AUS:SPIE, 2000:742-753.
[28］ Liu L X, Liu B, Huang H, et al. No-reference image quality assessment based on spatial and spectral entropies[J]. Signal Processing:Image Communication, 2014, 29(6):856-863.

第38卷
第1期2017 年1月兵工学报ACTA
ARMAMENTARIIVol.38No.1Jan.2017

[1]	娄伟鹏，郑长松，李和言，陈建文，张周立，马源. 高速《Symbol》v湿式换挡离合器排油阀临界开启和关闭压力研究[J]. 兵工学报, 2017, 38(9): 1665-1672.
[2]	王宪成，杨绍卿，马宁，赵文柱. 车辆柴油机缸套动载荷磨损计算模型研究[J]. 兵工学报, 2017, 38(9): 1673-1680.
[3]	孙皓泽，常天庆，王全东，孔德鹏，戴文君. 一种基于分层多尺度卷积特征提取的坦克装甲目标图像检测方法[J]. 兵工学报, 2017, 38(9): 1681-1691.
[4]	张玉燕，孙莎莎，王振春，曹海要，战再吉. 高速载流电枢表面瞬态温度场仿真与测量[J]. 兵工学报, 2017, 38(9): 1692-1698.
[5]	李臣明，宦超，石怀龙. 某箱式火箭炮对面目标分布式杀伤最优火力分配[J]. 兵工学报, 2017, 38(9): 1699-1704.
[6]	雷娟棉，张嘉炜，谭朝明. 小攻角下船尾外形对旋转弹丸马格努斯效应影响的数值研究[J]. 兵工学报, 2017, 38(9): 1705-1715.
[7]	李泽，闫晓鹏，栗苹，郝新红，王建涛. 扫频式干扰对调频多普勒引信的干扰机理研究[J]. 兵工学报, 2017, 38(9): 1716-1722.
[8]	张浩为，谢军伟，张昭建，宗彬锋，陈唐军. 基于混合自适应遗传算法的相控阵雷达任务调度[J]. 兵工学报, 2017, 38(9): 1761-1770.
[9]	李茂，侯海量，朱锡，黄晓明，李典，陈长海，胡年明. 结构间隙对芳纶纤维增强复合装甲结构抗侵彻性能的影响[J]. 兵工学报, 2017, 38(9): 1797-1805.
[10]	王鉴, 韩焱, 王黎明, 张丕状, 陈平. 弹丸在膛内运动的回波信号瞬时频率估计方法研究[J]. 兵工学报, 2017, 38(9): 1806-1814.
[11]	刘海鸥，张文胜，徐宜，赵梓烨. 基于核密度估计的履带车辆传动轴载荷谱编制[J]. 兵工学报, 2017, 38(9): 1830-1838.
[12]	姜缪文，闫健卓，陈继民. 基于拓扑优化技术的军用头盔内胆结构三维打印[J]. 兵工学报, 2017, 38(9): 1845-1853.
[13]	张磊，李世民，朱刚. 基于时间连续灰色Markov模型的维修器材需求预测方法研究[J]. 兵工学报, 2017, 38(9): 1862-1866.
[14]	张亚舟，李贞晓，程年恺，田慧，栗保明. 一种真空触发开关脉冲电源系统研究[J]. 兵工学报, 2017, 38(8): 1469-1475.
[15]	尹冬梅，肖宏成，栗保明. 基于三维梁理论的电磁轨道炮复合身管抗弯性能分析[J]. 兵工学报, 2017, 38(8): 1476-1482.