Leakage Source Detection Based on Thermal Imaging
-
摘要: 针对屋面渗漏源难以检测的问题,研究了基于渗漏区域红外图像特征的灰度分段映射图像增强方法,提出了一种基于样板矩阵的图像快速识别技术,设计了一个屋面全自动渗漏源检测系统。在5 m×3 m屋面设置渗漏源形成多个渗漏区域,采用Mecanum轮小车搭载该系统对渗漏源进行检测,结果表明,该系统可以在89 s之内完成检测工作,总测试150个次渗漏点,漏测12个次渗漏点,识别准确率大于90%。该技术检测效率高、操作简单,配合相应载体可用于各类不明渗水源检测。Abstract: To address the difficulty in detecting the source of roof leakage, an image enhancement method that uses the infrared image features of the leakage area was studied using gray segmentation mapping. Rapid image recognition technology based on a template matrix was proposed, and an automatic roof leakage source detection system was designed. Leakage sources were set on a 5 m× 3 m roof to form multiple leakage areas. A mecanum wheeled trolley was used to support the system while detecting these sources. The results showed that the system could complete detection within 89 s, with a total of 150 leakage points tested and 12 leakage points missed, and the identification accuracy was greater than 90%. This technology has high detection efficiency and simple operation and can be used to detect all types of unknown water seepage sources with the corresponding carrier.
-
表 1 各种图像增强算法的峰值信噪比及其平均值
Table 1. Peak Signal to Noise Ratio of various image enhancement algorithms
Nearest neighbor interpolate-on Bicubic interpolate-on Enhancement method in this
paperFan 34.8049 36.1934 36.7289 Hand 33.6161 34.8478 35.2925 Lenna 28.9225 30.1287 30.4744 Cameraman 30.8624 32.311 32.6554 Sponge 33.0744 35.191 36.3204 表 2 各种图像增强算法的峰值信噪比平均值
Table 2. Average values of PSNR of various image enhancement algorithms
Nearest neighbor interpolation Bicubic interpolation Enhancement method in this
paperAverage peak SNR 32.25 33.73 34.29 表 3 算法处理先后顺序的区分差异
Table 3. Algorithm processing sequence difference
PSNR SSIM Pseudo - color processing followed by interpolation amplification 19.9055 0.9399 Grayscale interpolation and amplification followed by pseudo-color processing 23.3838 0.9805 表 4 不同算法处理红外识别问题的时间
Table 4. Time for different algorithms to deal with infrared recognition problems
Hough transform Multi-angle infrared image
target recognition methodThis paper
proposes a fast
recognition algorithmAccuracy/% 76.4 95.2 86.9 The average
time/ms214 127 32 表 5 系统测试结果-1个渗漏源
Table 5. System test results -1 leakage source
Times Time -consuming /s Results 1 70 √ 2 65 √ 3 74 √ 4 71 √ 5 73 × 6 78 √ 7 67 √ 8 64 √ 9 72 √ 10 63 √ 11 61 √ 12 81 √ 13 81 √ 14 61 × 15 68 √ 16 61 √ 17 78 √ 18 83 √ 19 81 √ 20 58 √ 21 64 √ 22 62 √ 23 67 √ 24 59 √ 25 68 √ 表 6 系统测试结果-2个渗漏源
Table 6. System test results -2 leakage sources
Times Time -
consuming/sThe source
1 resultsThe source
2 results1 72 √ √ 2 76 √ √ 3 81 √ √ 4 75 × √ 5 74 √ √ 6 73 √ √ 7 68 √ √ 8 84 √ √ 9 72 × √ 10 71 √ √ 11 69 √ √ 12 76 √ √ 13 73 √ √ 14 67 √ × 15 81 √ √ 16 88 × √ 17 81 √ √ 18 73 √ √ 19 72 √ √ 20 71 √ √ 21 68 √ √ 22 67 √ √ 23 69 √ √ 24 62 √ × 25 66 √ √ 表 7 系统测试结果-3个渗漏源
Table 7. System test results -3 leakage sources
Times Time -
consuming/sThe source 1 results The source 2 results The source 3 results 1 81 √ √ √ 2 82 √ √ × 3 89 √ √ × 4 75 √ √ √ 5 71 √ √ √ 6 65 √ √ √ 7 72 √ √ √ 8 73 √ √ √ 9 87 √ √ √ 10 81 × √ √ 11 59 √ √ √ 12 62 √ √ √ 13 76 √ √ √ 14 71 √ √ √ 15 69 √ √ √ 16 67 √ √ √ 17 81 √ √ √ 18 62 √ √ √ 19 69 √ √ √ 20 76 √ √ √ 21 77 √ √ √ 22 80 √ × √ 23 85 √ √ √ 24 74 √ √ √ 25 73 √ √ × -
[1] LIU Dunnan, HOU Rui, LI Qiang, et al. Research on fuzzy enhancement algorithms for infrared image recognition quality of power internet of things equipment based on membership function[J]. Journal of Visual Communication and Image Representation, 2019, 62(1): 359-367. [2] ZHENG Zhaoping, ZENG Hansheng, DING Cuijiao, et al. Summary on the infrared thermal imaging temperature measurement technology and its application[J]. Infrared Technology, 2003, 25(1): 96-98. [3] 赵璐, 熊森. 多视角红外图像目标识别方法[J]. 红外与激光工程, 2021, 50(11): 403-408. https://www.cnki.com.cn/Article/CJFDTOTAL-HWYJ202111051.htmZHAO Lu, XIONG Sen. Multi-view infrared image target recognition method[J]. Infrared and Laser Engineering, 2021, 50(11): 403-408. https://www.cnki.com.cn/Article/CJFDTOTAL-HWYJ202111051.htm [4] BAI Honggang, JIN Yingji. Application of infrared technology in military[J]. Journal of Engineering College of Armed Police Force, 2008(6): 5-7. [5] 蔡毅, 王岭雪. 红外成像技术中的9个问题[J]. 红外技术, 2013, 35(11): 671-682. doi: 10.11846/j.issn.1001_8891.201311001CAI Yi, WANG Lingxue. Nine problems in infrared imaging technology [J]. Infrared Technology, 2013, 35(11): 671-682. doi: 10.11846/j.issn.1001_8891.201311001 [6] 杨凯斌, 吴定祥, 龚金成, 等. 圆环陶瓷检测算法研究[J]. 中国陶瓷, 2017, 53(3): 39-44. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTC201703008.htmYANG Kaibin, WU Dingxiang, GONG Jincheng, et al. Research on detection algorithm of ring ceramics [J]. China Ceramics, 2017, 53(3): 39-44. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTC201703008.htm [7] Alwan Hassan M, Volkov A N, Shbani A. Solution of inverse and forward kinematics problems for mobile robot with six mecanum wheels[C]//IOP Conference Series: Materials Science and Engineering, 2021, 1094(1): 012071.