A pipeline robot detection image enhancement method based on image fusion and improved threshold

Authors

YUAN Mingdao, Guangdong Research Institute of Water Resources and Hydropower, Guangzhou 510610, China
TAN Cai, Guangdong Research Institute of Water Resources and Hydropower, Guangzhou 510610, China
LI Yang, Department of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300384, China
XU Yunqian, Guangdong Research Institute of Water Resources and Hydropower, Guangzhou 510610, China
ZHANG Xuhui, Guangdong Research Institute of Water Resources and Hydropower, Guangzhou 510610, China
YANG Jingxue, Guangdong Research Institute of Water Resources and Hydropower, Guangzhou 510610, China

Abstract

Pipeline robot detection technology can quickly, accurately and intuitively identify the structure and hidden functional troubles of pipeline. However, due to the restriction of the pipeline environment, the detected images have problems such as uneven illumination, low contrast and blurred details. Therefore, an enhancement technique for detected image of pipeline robot is proposed. First, the contrast limited adaptive histogram equalization(CLAHE) and homomorphic filtrate(HF) are applied to deal with the problem of uneven illumination and low contrast, and the result images of the two methods are fused. Secondly, the fusion images are transformed by the Nonsubsampled Contourlet Transform(NSCT), and the improved Bayes-Shrink threshold is used to remove the noise of the high frequency coefficient. Finally, the nonlinear mapping function is used to enhance the details, and the NSCT inverse transform is used to get the final enhanced image. In order to verify the effectiveness and superiority of the method for pipeline robot detection image, 5 typical pipeline robot detection images were selected and enhanced by this method, and compared with 4 common image enhancement technologies. The results show that image enhancement method for pipeline robot detection image by using image fusion and improved threshold can effectively improve the overall and local contrast image, and effectively enhance the image details. It can solve the main problems in pipeline robot detected image effectively.

Keywords

pipeline robot, image fusion, nonsubsampled contourlet transform(NSCT), homomorphic filtering(HF), con-trast limited adaptive histogram equalization(CLAHE)

DOI

10.3969/j.issn.1001-1986.2019.04.027

Recommended Citation

YUAN Mingdao, TAN Cai, LI Yang, et al. (2019) "A pipeline robot detection image enhancement method based on image fusion and improved threshold," Coal Geology & Exploration: Vol. 47: Iss. 4, Article 28.
DOI: 10.3969/j.issn.1001-1986.2019.04.027
Available at: https://cge.researchcommons.org/journal/vol47/iss4/28

Reference

[1] 徐云乾. CCTV和三维激光扫描技术在水利工程输排水管道隐患探测中的应用[J]. 中国农村水利水电,2014(3):68-70. XU Yunqian. The application of CCTV and 3D laser scanning technology in the detection of hidden dangers of drainage pipeline in water conservancy engineering[J]. China Rural Water and Hydropower,2014(3):68-70.

[2] GUO X,LI Y,LING H. LIME:Low-light image enhancement via illumination map estimation[J]. IEEE Transactions on Image Processing a Publication of the IEEE Signal Processing Society,2017,26(2):982-993.

[3] LIU H,LU H,ZHANG Y. Image enhancement for outdoor long-range surveillance using IQ-learning multiscale Reti-nex[J]. Iet Image Processing,2017,11(9):786-795.

[4] KAUR A,SINGH C. Contrast enhancement for cephalometric images using wavelet-based modified adaptive histogram equalization[J]. Applied Soft Computing,2017,51:180-191.

[5] 李阳,常霞,纪峰. 图像增强方法研究新进展[J]. 传感器与微系统,2015,34(12):9-12. LI Yang,CHANG Xia,JI Feng. New progress of research on image enhancement method[J].Transducer and Microsystem Technologies,2015,34(12):9-12.

[6] GHARBI M,CHEN J,BARRON J T,et al. Deep bilateral learning for real-time image enhancement[J]. ACM Transac-tions on Graphics,2017,36(4):118.

[7] WANG Y,PAN Z. Image contrast enhancement using adja-cent-blocks-based modification for local histogram equalization[J]. Infrared Physics & Technology,2017,86:59-65.

[8] VOICU L I. Practical considerations on color image enhancement using homomorphic filtering[J]. Journal of Electronic Imaging,1997,6(1):108-113.

[9] YANG L,XIA C,CHANG J. Image edge detection based on gaussian mixture model in nonsubsampled contourlet do-main[J]. Journal of Electrical and Computer Engineering,2016(10):1-10.

[10] HEPSIBAH K,HEAVEN M S,SARAVANAN M. Image enhancement based on nonsubsampled contourlet transform using matrix factorization techniques[J]. International Journal of Computer Applications,2015,123(6):35-38.

[11] 闫利,向天烛. NSCT域内结合边缘特征和自适应PCNN的红外与可见光图像融合[J]. 电子学报,2016,44(4):761-766. YAN Li,XIANG Tianzhu. Fusion of infrared and visible images based on edge feature and adaptive PCNN in NSCT domain[J]. Acta Electronica Sinica,2016,44(4):761-766.

[12] 周飞,贾振红,杨杰,等. 基于NSCT和改进模糊的遥感图像增强方法[J]. 计算机工程与应用,2017,53(15):206-209. ZHOU Fei,JIA Zhenhong,YANG Jie,et al. Enhancement method of remote sensing image based on NSCT and improved fuzzy contrast[J]. Computer Engineering and Applications,2017,53(15):206-209.

[13] 吴一全,史骏鹏. 基于多尺度Retinex的非下采样Contourlet域图像增强[J]. 光学学报,2015,35(3):79-88. WU Yiquan,SHI Junpeng. Image enhancement in non-subsampled Contourlet transform domain based on multi-scale Retinex[J]. Acta Optica Sinica,2015,35(3):79-88.

[14] 王峰,程咏梅. 基于MSSTO与NSCT变换的可见光与红外图像增强融合[J]. 控制与决策,2017,32(2):269-274. WANG Feng,CHENG Yongmei. Visible and infrared image enhanced fusion based on MSSTO and NSCT transform[J]. Control and Decision,2017,32(2):269-274.

[15] XIAO L,LI C,WU Z,et al. An enhancement method for X-ray image via fuzzy noise removal and homomorphic filtering[J]. Neurocomputing,2016,195:56-64.

[16] 肖进胜,单姗姗,段鹏飞,等. 基于不同色彩空间融合的快速图像增强算法[J]. 自动化学报,2014,40(4):697-705. XIAO Jinsheng,SHAN Shanshan,DUAN Pengfei,et al. A fast image enhancement algorithm based on fusion of different color spaces[J]. 2014,40(4):697-705.

[17] HE H,LEE W J,LUO D S,et al. Insulator infrared image denoising method based on wavelet generic gaussian distribution and map estimation[J]. IEEE Transactions on Industry Applications,2017,53(4):3279-3284.

[18] 付晓薇,丁明跃,周成平,等. 基于量子概率统计的医学图像增强算法研究[J]. 电子学报,2010,38(7):1590-1596. FU Xiaowei,DING Mingyue,ZHOU Chengping,et al. Research on image enhancement algorithms of medical images based on quantum probability statistics[J]. Acta Electronica Sinica,2010,38(7):1590-1596.