Fault Diagnosis of Reliability Test for Low-Light-Level Vision Device Based on Structural Similarity Algorithm
-
摘要: 本文针对目前直视型微光装备可靠性试验存在鉴定效率低、易发生漏检和缺乏有效记录手段的情况,提出了一种基于机器视觉的自动故障诊断方法。该方法通过设计系列专用转接环实现工业相机与被试装备的可靠连接,自动采集被试品目镜视场图像并实时传输监视图像;采用结构相似性(Structural SIMilarity,SSIM)算法实时计算监视图像与事先确定的正常模板图像相似度并自动进行异常检测警告、生成异常检测日志,实现故障诊断。实践表明,该方法与主观判断具有一致性,在环境照度条件稳定时,异常诊断准确度达到实际使用需求。Abstract: At present, fault diagnosis in direct-view low-light-level photo-optical equipment is mainly conducted by manual detection, which is inefficient, error prone (faults will often be missed), and does not create a valid record. This paper proposes an automatic diagnostic method based on machine vision. In this method, a series of special adaptors are designed for developing a reliable connection between the industrial camera and the object to be tested, automatically collecting the images of the eyepiece field of view image of the tested product, and transmitting the monitoring image in real time. We used the Structural SIMilarity (SSIM) algorithm to calculate the similarity between the monitoring images and the template image in real time to automatically warn of abnormalities using a judgment threshold, which is determined in advance. When a failure occurs, the system issues an abnormal warning, generates a detection log, and stores the current monitoring images. Practice shows consistency of the results of our method with those of subjective judgment. Under stable illumination conditions, the accuracy of the diagnostic technique meets the actual requirements.
-
表 1 图像采集设备基本参数
Table 1. Basic parameters of image acquisition equipment
Parameter Value Resolution 1920×1200 Maximum frame rate 54fps@1920×1200 Camera type Color camera Pixel size 4.8μm×4.8μm Exposure time 59μs-10s Data interface Gigabit Ethernet Power supply Voltage range 5-15 V,Support PoE power supply Power consumption 2.9 W@12VD Lens interface C-Mout -
[1] 何国伟, 许海宝. 可靠性试验技术[M]. 北京: 国防工业出版社, 1995.HE Guowei, XU Haibao. Reliability Test Technology[M]. Beijing: National Defense Industry Press, 1995. [2] 邱有成, 解放军总装备部. 可靠性试验技术[M]. 北京: 国防工业出版社, 2003.QIU Youcheng, PLA General Armament Department. Reliability Test Technology[M]. Beijign: National Defense Industry Press, 2003. [3] 白晓东, 李洪祚, 宫玉琳. 微光瞄具可靠性试验设备中故障图像判别研究[J]. 长春理工大学学报: 自然科学版, 2014(2): 18-21. https://www.cnki.com.cn/Article/CJFDTOTAL-CGJM201402005.htmBAI Xiaodong, LI Hongzuo, GONG Yulin. Research on the identification of fault images in the reliability test equipment of low-light sight[J]. Journal of Changchun University of Science and Technology: Natural Science Edition, 2014(2): 18-21. https://www.cnki.com.cn/Article/CJFDTOTAL-CGJM201402005.htm [4] ZHOU Wang, A C Bovik. A universal image quality index[J]. IEEE Signal Processing Letters, 2002, 9(3): 81-84. doi: 10.1109/97.995823 [5] ZHOU Wang, A C Bovik, H R Sheikh, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image processing, 2004, 13(4): 600-612. doi: 10.1109/TIP.2003.819861 [6] XU W, Hauske G. Picture quality evaluation based on error segmentation[J]. Proc SPIE, 1994, 2308(2308): 1454-1465. http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=976444 [7] 王虹, 潘晓露, 李一民, 等. 一种基于梯度幅度值的图像质量客观评价方法[J]. 光学与光电技术, 2004, 2(6): 23-25. https://www.cnki.com.cn/Article/CJFDTOTAL-GXGD200406007.htmWANG Hong, PAN Xiaolu, LI Yimin, et al. An objective evaluation method of image quality based on gradient amplitude value[J]. Optics and Optoelectronic Technology, 2004, 2(6): 23-25. https://www.cnki.com.cn/Article/CJFDTOTAL-GXGD200406007.htm [8] 杨光义, 陈浩, 李梦涵, 等. 基于图像熵的无参考图像质量评价方法: CN109325550A[P]. 2019.YANG Guangyi, CHEN Hao, LI Menghan, et al. No-reference image quality evaluation method based on image entropy: CN109325550A[P]. 2019. [9] 倪晓明. 基于小波变换图像质量评价新算法[D]. 厦门: 厦门大学, 2009.NI Xiaoming. A new image quality evaluation algorithm based on wavelet transform[D]. Xiamen: Xiamen University, 2009. [10] 叶盛楠, 苏开娜, 肖创柏, 等. 基于结构信息提取的图像质量评价[J]. 电子学报, 2008, 36(5): 856-861. doi: 10.3321/j.issn:0372-2112.2008.05.005YE Shengnan, SU Kaina, XIAO Chuangbai, et al. Image quality assessment based on structural information extraction[J]. Acta Electronica Sinica, 2008, 36(5): 856-861. doi: 10.3321/j.issn:0372-2112.2008.05.005 [11] 马丽红, 龚紫平. 频率与方向敏感SSIM的图像质量评价方法[J]. 计算机工程, 2012, 38(5): 19-24. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJC201205007.htmMA Lihong, GONG Ziping. Image Quality Assessment Method for Frequency and Direction Sensitive SSIM[J]. Computer Engineering, 2012, 38(5): 19-24. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJC201205007.htm [12] 闫乐乐, 李辉, 邱聚能, 等. 基于区域对比度和SSIM的图像质量评价方法[J]. 应用光学, 2015, 36(1): 58-63. https://www.cnki.com.cn/Article/CJFDTOTAL-YYGX201501012.htmYAN Lele, LI Hui, QUI Juneng, et al. Image quality assessment method based on reginal contrast and structural similarity[J]. Journal of Applied Optics, 2015, 36(1): 58-63. https://www.cnki.com.cn/Article/CJFDTOTAL-YYGX201501012.htm [13] 王利平, 孙韶远, 陈钱, 等. 微光图像特征分析及图像融合技术研究[J]. 红外与毫米波学报, 2000(4): 289-292. https://www.cnki.com.cn/Article/CJFDTOTAL-HWYH200004008.htmWANG Liping, SUN Shaoyuan, CHEN Qian, et al. Low-light level image feature analysis and image fusion technology research[J]. Journal of Infrared and Millimeter Waves, 2000(4): 289-292. https://www.cnki.com.cn/Article/CJFDTOTAL-HWYH200004008.htm [14] 周燕, 金伟其, 张建勇. 基于人眼视觉的直视型微光成像系统MRC模型[J]. 光学技术, 2006(6): 817-819. https://www.cnki.com.cn/Article/CJFDTOTAL-GXJS200606004.htmZHOU Yan, JIN Qiwei, ZHANG Jianyong. THE MRC method for watched directly imaging system[J]. Optical Technique, 2006(6): 817-819. https://www.cnki.com.cn/Article/CJFDTOTAL-GXJS200606004.htm [15] 武英, 王庆宝, 喻春雨. 外界因素对微光图像的影响[J]. 红外与激光工程, 2002(3): 225-228. https://www.cnki.com.cn/Article/CJFDTOTAL-HWYJ200203008.htmWU Ying, WANG Qingbao, YU Chunyu. Effect of external factors on low light level image[J]. Infrared and Laser Engineering, 2002(3): 225-228. https://www.cnki.com.cn/Article/CJFDTOTAL-HWYJ200203008.htm