SF6 Leakage Region Enhancement Algorithm Based on Improved HE
-
摘要: SF6气体红外成像易受环境噪声影响,呈低对比度与低信噪比特性。导致现有算法无法自适应增强SF6泄漏区域和抑制高斯噪声。针对上述问题,提出一种基于改进HE的SF6泄漏区域增强算法。该算法首先采用单尺度Retinex处理原始SF6图像获得反射图像,然后利用引导滤波将反射图像分解为细节层和基本层,最后采用改进的直方图均衡化来自适应处理基本层,并将增强后的图像进行融合来获得最终的图像。实验结果表明:本文算法不仅能够自适应增强泄漏区域的对比度,而且具有良好边缘保持特性和抑制高斯噪声的性能。其增强效果优于现有的SF6红外图像增强算法。有效改善了SF6红外图像低对比度和低信噪比特性。
-
关键词:
- 单尺度Retinex /
- 引导滤波 /
- SF6红外图像 /
- 直方图均衡化
Abstract: Infrared imaging of SF6 gas is easily affected by environmental noise and exhibits low contrast and signal-to-noise ratio. As a result, existing algorithms cannot adaptively enhance the SF6 leakage area or suppress Gaussian noise. Therefore, this study proposes an improved HE-based SF6 leakage-area enhancement algorithm. The algorithm first uses SSR to process the original SF6 image to obtain the reflection image R, and then uses guided filtering to decompose the reflection image R into detail and base layers. Finally, an improved histogram equalization is used to adaptively process the base layer, and the enhanced images are fused to obtain the final image. The experiment results demonstrate that the proposed algorithm can not only adaptively enhance the contrast of the leaked area but also has good edge preservation and Gaussian noise suppression performance. Its enhancement effect is superior to that of the existing SF6 infrared image enhancement algorithm. This effectively improves the low-contrast and low signal-to-noise ratio characteristics of the SF6 infrared images.-
Key words:
- single-scale-retinex /
- guide filtering /
- SF6 infrared image /
- histogram equalization
-
表 1 不同算法的客观评价指标
Table 1. Objective evaluation indicators for the different algorithms
Image Index Original HE Literature [7] Proposed Image a IE 6.031 7.103 7.066 7.227 SD 37.046 73.821 44.946 46.465 PSNR - 6.615 9.975 16.045 T/s - 0.047 0.089 0.082 Image b IE 6.405 7.118 6.781 7.273 SD 62.109 74.408 63.094 64.496 PSNR - 4.891 5.561 8.951 T/s - 0.046 0.086 0.085 -
[1] ZHANG X, XIAO H, HU X, et al. Effects of reduced electric field on sulfur hexafluoride removal for a double dielectric barrier discharge reactor[J]. IEEE Transactions on Plasma Science, 2018, 46(3): 563-570. doi: 10.1109/TPS.2018.2796134 [2] 郭瑛, 周会高. 高压开关行业热点分析[J]. 电气时代, 2019, 1(6): 20-24. https://www.cnki.com.cn/Article/CJFDTOTAL-DQSD201906007.htmGUO Ying, ZHOU Huigao. Hot spot analysis of high-voltage switch industry[J]. Electric Age, 2019, 1(6): 20-24. https://www.cnki.com.cn/Article/CJFDTOTAL-DQSD201906007.htm [3] LIU C, GU W, SHI L, et al. A method to construct early-warning and emergency response system for sulfur hexafluoride leakage in substations[J]. IEEE Access, 2020(8): 47082-47091. [4] 季怡萍, 邓先钦, 徐鹏, 等. SF6气体泄漏红外成像检测的技术分析和应用探讨[J]. 红外技术, 2022, 44(2): 198-204. http://hwjs.nvir.cn/article/id/54e422ef-acce-4c36-9dbc-66801c99d8beJI Yiping, DENG Xianqin, XU Peng, et al. Analysis of SF6 leakage detection using infrared imaging[J]. Infrared Technology, 2022, 44(2): 198-204. http://hwjs.nvir.cn/article/id/54e422ef-acce-4c36-9dbc-66801c99d8be [5] 王俊波, 徐鑫, 刘志陆, 等. 电气设备SF6气体泄漏的红外检测技术[J]. 无损检测, 2017, 39(8): 43-46. https://www.cnki.com.cn/Article/CJFDTOTAL-WSJC201708011.htmWANG Junbo, XU Xin, LIU Zhilu. Infrared detection technology of SF6 gas leakage of electrical equipment [J]. Nondestructive Testing, 2017, 39(8): 43-46. https://www.cnki.com.cn/Article/CJFDTOTAL-WSJC201708011.htm [6] 李军卫, 张英, 赵乐, 等. 基于红外视频图像处理的瓷柱式SF6断路器泄漏区域检测研究[J]. 高压电器, 2018, 54(12): 50-55. https://www.cnki.com.cn/Article/CJFDTOTAL-GYDQ201812009.htmLI Junwei, ZHANG Ying, ZHAO Le, et al. Detection of leakage area of porcelain column SF6 circuit breaker based on infrared video image processing [J]. High Voltage Apparatus, 2018, 54(12): 50-55. https://www.cnki.com.cn/Article/CJFDTOTAL-GYDQ201812009.htm [7] 刘陈瑶, 胡梦竹, 张龙飞. 基于改进CLAHE的SF6红外图像增强[J]. 光学技术, 2021, 47(1): 107-112. https://www.cnki.com.cn/Article/CJFDTOTAL-GXJS202101019.htmLIU Chenyao, HU Mengzhu, ZHANG Longfei. Infrared image enhancement of SF6 based on improved CLAHE[J]. Optical Technique, 2021, 47(1): 107-112. https://www.cnki.com.cn/Article/CJFDTOTAL-GXJS202101019.htm [8] 张志恒. 基于图像自适应分解及多方向特征的多聚焦图像融合算法研究[D]. 西安: 西安电子科技大学, 2021.ZHANG Zhiheng. Research on Multi-focus Images Fusion Algorithm Based on Image Adaptivc Decomposition and Multi-directional Features[D]. Xi'an: XIDIAN University, 2021. [9] Land E H, McCann J J. Lightness and retinex theory[J]. J. Opt. Soc. Am. , 1971, 61(1): 1-11. [10] Jobson D J, Rahman Z, Woodell G A. Properties and performance of a center/surround retinex[J]. IEEE Transactions on Image Process, 1997, 6(3): 451-462. [11] HE Kaiming, SUN Jian, TANG Xiaoou. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397-1409. [12] 乔闹生. 一种改进的直方图均衡化[J]. 光学技术, 2008, 34(S1): 141-142. https://www.cnki.com.cn/Article/CJFDTOTAL-GXJS2008S1047.htmQIAO Naosheng. An improved histogram equalization[J]. Optical Technique, 2008, 34(S1): 141-142. https://www.cnki.com.cn/Article/CJFDTOTAL-GXJS2008S1047.htm