无参考的特征点复杂度激光干扰图像评估

钱方; 孙涛; 郭劲; 王挺峰

doi:10.3788/OPE.20152304.1179

您当前的位置：

首页 >

文章列表页 >

无参考的特征点复杂度激光干扰图像评估

信息科学 | 更新时间：2020-08-13

- 无参考的特征点复杂度激光干扰图像评估
- No-reference laser-dazzling image quality assessment based on feature-point complexity
- 光学精密工程 2015年23卷第4期页码：1179-1186
- 作者机构：
  
  1. 中国科学院大学北京,中国,100049
  2. 中国科学院长春光学精密机械与物理研究所激光与物质相互作用国家重点实验室,吉林长春,130033
- 作者简介：
- 基金信息：
  
  激光与物质相互作用国家重点实验室科研基金资助项目(No.SKLLIM1203-01)();吉林省重大科技攻关专项资助项目(No.20126015)()
- DOI：10.3788/OPE.20152304.1179
  中图分类号： TN977;TP391.4
- 收稿日期：2014-04-17，
  
  修回日期：2014-05-21，
  
  纸质出版日期：2015-04-25
- 稿件说明：
移动端阅览
钱方, 孙涛, 郭劲等. 无参考的特征点复杂度激光干扰图像评估[J]. 光学精密工程, 2015,23(4): 1179-1186

QIAN Fang, SUN Tao, GUO Jin etc. No-reference laser-dazzling image quality assessment based on feature-point complexity[J]. Editorial Office of Optics and Precision Engineering, 2015,23(4): 1179-1186
钱方, 孙涛, 郭劲等. 无参考的特征点复杂度激光干扰图像评估[J]. 光学精密工程, 2015,23(4): 1179-1186 DOI： 10.3788/OPE.20152304.1179.

QIAN Fang, SUN Tao, GUO Jin etc. No-reference laser-dazzling image quality assessment based on feature-point complexity[J]. Editorial Office of Optics and Precision Engineering, 2015,23(4): 1179-1186 DOI： 10.3788/OPE.20152304.1179.

摘要

由于目标识别和检测效果取决于目标提取的准确性

本文结合主动成像与目标识别技术搭建了激光主动成像系统实验平台

研究了激光干扰对获取图像质量以及特征点提取效果的影响。提出了一种无参考的特征点复杂度图像评估算法。该算法在目标区域位置计算图像的特征点、纹理、梯度和对比度复杂度

然后综合4个因子得到归一化的评估结果。利用激光主动成像系统对设定目标进行了照明成像实验

同时采集了不同干扰功率和光斑位置的干扰图像。使用本文提出的特征点复杂度算法对标准数据库及实验获得的激光干扰图像进行了评估。实验结果表明:提出的评估算法能够客观地反映图像质量的变化情况

可对不同程度的激光干扰图像给出合理的评估结果

其评价结果更符合主观视觉感受

并且能够指导激光主动成像识别系统的防护与应用。

Abstract

The validity of target recognition and target detection depend on the accuracy of target extraction

this paper establishes an experiment platform of laser active imaging system combining laser active image technology and target recognition technology. The image quality and feature-point extraction were researched in the target area after laser jamming

and a new No-reference Feature-point Complexity Metrics(NRFPCM) assessment algorithm was proposed. In the algorithm

the feature-point

texture

gradient and contrast complexity were computed in the target area

then the normalized NRFPCM was obtained via production of the four factors above. Finally

the luminance imaging experiment was performed for the target by utilizing the laser active imaging system and the disturbed images with different disturbing powers and different spot positions were obtained. The proposed NRFPCM algorithm was used to evaluate the standard image database and the newly obtained laser-dazzling images. The results show that the proposed algorithm reflects the image quality objectively and gives a more reasonable evaluation results for different laser-dazzling images. Moreover

evaluation results are more suitable for the subjective visual feeling. The NRFPCM gives the guidance to the laser active imaging system in the defense and application.

关键词

Keywords

references

WANG Z, SHEIKH H R, BOVIK A C. No-reference perceptual quality assessment of JPEG compressed images[C]. IEEE Image Processing International Conference, 2002, 1(1): 477-480.

LIU SH ZH, BOVIK A C. Efficient DCT-domain blind measurement and reduction of blocking artifacts [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2002, 12(12): 1139-1149.

桑庆兵, 苏媛媛, 李朝锋, 等. 基于梯度结构相似度的无参考模糊图像质量评价[J]. 光电子·激光, 2013, 24(3): 573-577. SANG Q B, SU Y Y, LI CH F, et al.. No-reference blur image quality assessment based on gradient similarity [J]. Journal of Optoelectronics Laser, 2013, 24(3): 573-577. (in Chinese)

LI C, BOVIK A C, WU X. Blind image quality assessment using a general regression neural network [J]. IEEE Transactions on Neural Networks, 2011, 22(5): 793-799.

SCHMID C, MOHR R, BAUCKHAGE C. Evaluation of interest point detectors [J].Journal of Computer Vision, 2000, 37(2):151-172.

ROSTEN E. High performance rigid body tracking[D]. Cambridge: University of Cambridge, 2006.

YUAN L H, FU L, YANG Y, et al.. Analysis of texture feature extracted by gray level co-occurrence matrix[J]. Journal of Computer Applications, 2009, 29(4):1018-1021.

唐永鹤, 卢焕章. 基于灰度差分不变量的快速局部特征描述算法[J]. 光学精密工程, 2012, 20(2):447-454. TANG Y H, LU H ZH. Fast local feature description algorithm based on greyvalue differential invariants [J]. Opt. Precision Eng., 2012, 20(2):447-454. (in Chinese)

刘志文, 刘定生, 刘鹏. 应用尺度不变特征变换的多源遥感影像特征点匹配[J]. 光学精密工程, 2013, 21(8):2146-2153. LIU ZH W, LIU D SH, LIU P. SIFT feature matching algorithm of mutil-source remote image[J]. Opt. Precision Eng., 2013, 21 (8):2146-2153. (in Chinese)

钱方, 郭劲, 孙涛, 等. 基于小波加权的激光干扰效果评估[J]. 液晶与显示, 2013, 28 (5):781-787. QIAN F, GUO J, SUN T, et al.. Assessment of laser-dazzling effects based on weighted wavelet transforms [J].Chinese Journal of Liquid Crystals and Displays, 2013, 28 (5):781-787. (in Chinese)

XU X, SUN X Q, SHAO L. Simulation of laser jamming and its influence on CCD imaging performance [J]. SPIE Optoelectronic Imaging and Multimedia Technology, 2010, 7850:1-7.

SCHLEIJPEN M A, DIMMELER A, EBERLE B, et al.. Laser dazzling of focal plane array cameras [J]. SPIE Technologies for Optical Countermeasures, 2007, 6738:1-9.

DUREUC A, BOURDON P, VASSEUR O. laser-dazzling effects on TV-cameras: analysis of dazzling effects and experimental parameters weight assessment [J]. SPIE Technologies for Optical Countermeasures, 2005, 6738:1-6.

DUREUC A, VASSEUR O, BOURDON P, et al.. Assessment of laser-dazzling effects on TV-cameras by means of pattern recognition algorithms [J]. SPIE Technologies for Optical Countermeasures Ⅳ, 2007, 6738:1-8.

浏览量

392

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

高速微扫描图像超分辨重建

复杂场景中航天器靶标的快速识别

结合光斑与目标特征的激光干扰效果评估

晶圆定位标记光学成像的自适应聚焦评价

基于双目结构光周视扫描的3D件三维重构与位姿估计研究