Simulation of Infrared 3D Image Reconstruction of High Voltage Switchgear Temperature Field Based on Lazy Snapping Hybrid Simulated Annealing Algorithm
-
摘要: 提出基于Lazy Snapping混合模拟退火算法的高压开关柜温度场红外三维图像重建仿真方法，以提升高压开关柜温度场仿真效果。该方法利用主动式红外图像传感器采集高压开关柜温度场红外图像后，使用直方图非线性拉伸算法对其实施增强处理；再使用Lazy Snapping算法对增强后的高压开关柜温度场红外图像进行分割，并通过混合遗传模拟退火算法合成二维纹理流场图像；以该图像为基础，使用Image Quiltingh纹理合成算法合成高压开关柜温度场三维图像，完成高压开关柜温度场红外三维图像重建仿真过程。实验结果表明：该方法可有效增强高压开关柜温度场红外图像，其分割红外图像时的交并比数值接近1.0；可依据其生成的二维纹理流场图像生成三维图像，温度场仿真数值最大偏差仅为0.03℃。
-
关键词:
- Lazy Snapping /
- 混合模拟退火 /
- 高压开关柜 /
- 温度场 /
- 三维图像重建
Abstract: A simulation method for the infrared three-dimensional (3D) image reconstruction of a high-voltage switchgear temperature field based on a lazy snapping hybrid simulated annealing algorithm is proposed to improve the simulation effect of the high-voltage switchgear temperature field. In this method, the active infrared image sensor was used to collect an infrared image of the temperature field of a high-voltage switchgear, and the square-graph nonlinear stretching algorithm was used to enhance it. Subsequently, the enhanced infrared image was segmented by lazy snapping algorithm, and the two-dimensional texture flow-field image was synthesized by a hybrid genetic simulated annealing algorithm. Based on the image, an image quilting texture synthesis algorithm was used to synthesize the 3D image of the high-voltage switchgear temperature field, and the infrared 3D image reconstruction simulation process of the temperature field was completed. The experimental results demonstrated that this method effectively enhanced the infrared image of the temperature field of a high-voltage switchgear, and the intersection and union ratio of the segmented infrared image had a value that was approximately 1.0. The 3D image was effectively generated according to the generated two-dimensional texture flow-field image, and the maximum deviation of the temperature field simulation value was only 0.03℃. -
图 4 高压开关柜侧面5.1 m位置处温度三维图像
Figure 4. 3D image of temperature at 5.1 m on the side of the high voltage switchgear
图 5 实验区域温度场的三维图像重建
Figure 5. 3D image reconstruction of temperature field in the experimental area
表 1 三维重建温度差值
Table 1. Temperature difference of 3D reconstruction
℃ Mark point Actual temperature Three-dimensional reconstruction temperature Difference value 1 42.33 42.34 0.01 2 38.24 38.25 0.01 3 19.91 19.94 0.03 4 21.56 21.57 0.01 5 40.55 40.57 0.02 6 36.51 36.52 0.01 7 11.03 11.05 0.02 8 8.95 8.96 0.01 
下载: 导出CSV
-
[1] 张莲, 李梦天, 余松林, 等. 基于改进Lazy Snapping算法的红外图像分割方法研究[J]. 红外技术, 2021, 43(4): 372-377. http://hwjs.nvir.cn/article/id/ebf85178-e375-4e52-b1d8-2f0eb42a6c9dZHANG Lian, LI Mengtian, YU Songlin, et al. An infrared image segmentation method based on improved lazy snapping algorithm[J]. Infrared Technology, 2021, 43(4): 372-377. http://hwjs.nvir.cn/article/id/ebf85178-e375-4e52-b1d8-2f0eb42a6c9d [2] 臧益鹏, 许振宇, 黄安, 等. 基于改进模拟退火算法的非均匀燃烧场分布重建[J]. 物理学报, 2021, 70(13): 229-240. https://www.cnki.com.cn/Article/CJFDTOTAL-WLXB202113017.htmZANG Yipeng, XU Zhenyu, HUANG An, et al. Distribution reconstruction of non-uniform combustion field based on improved simulated annealing algorithm[J]. Acta Physica Sinica, 2021, 70(13): 229-240. https://www.cnki.com.cn/Article/CJFDTOTAL-WLXB202113017.htm [3] 杨永通, 彭彦卿, 袁传镇, 等. 基于有限元分析的开关柜温度场研究与优化[J]. 高压电器, 2019, 55(10): 81-86, 92. https://www.cnki.com.cn/Article/CJFDTOTAL-GYDQ201910014.htmYANG Yongtong, PENG Yanqing, YUAN Chuanzhen, et al. Research and optimization of temperature rise of switch cabinet based on finite element analysis[J]. High Voltage Apparatus, 2019, 55(10): 81-86, 92. https://www.cnki.com.cn/Article/CJFDTOTAL-GYDQ201910014.htm [4] 王辰旭, 李永华, 彭志敏. 高压开关柜温度流场仿真研究[J]. 电工电能新技术, 2021, 40(11): 64-71. doi: 10.12067/ATEEE2104037WANG Chenxu, LI Yonghua, PENG Zhimin. Simulation of temperature flow field in high voltage switchgear[J]. Advanced Technology of Electrical Engineering and Energy, 2021, 40(11): 64-71. doi: 10.12067/ATEEE2104037 [5] 杨丹, 芦甜, 郭文欣, 等. 基于模拟退火粒子群算法的MIT图像重建方法[J]. 东北大学学报: 自然科学版, 2021, 42(4): 531-537. https://www.cnki.com.cn/Article/CJFDTOTAL-DBDX202104011.htmYANG Dan, LU Tian, GUO Wenxin, et al. MIT image reconstruction method based on simulated annealing particle swarm algorithm[J]. Journal of Northeastern University: Natural Science, 2021, 42(4): 531-537. https://www.cnki.com.cn/Article/CJFDTOTAL-DBDX202104011.htm [6] 吴航宇, 王铭群, 卢鑫, 等. 模拟退火算法色差校正的傅里叶叠层显微彩色成像技术[J]. 光子学报, 2021, 50(3): 18-29. https://www.cnki.com.cn/Article/CJFDTOTAL-GZXB202103004.htmWU Hangyu, WANG Mingqun, LU Xin, et al. Fourier ptychographic microscopy color imaging with simulated-annealing chromatic aberration correction[J]. Acta Photonica Sinica, 2021, 50(3): 18-29. https://www.cnki.com.cn/Article/CJFDTOTAL-GZXB202103004.htm [7] 谢安宁, 张宏伟, 赵志刚, 等. 基于三维旋转模型的红外全景图像拼接方法[J]. 激光与红外, 2019, 49(4): 507-512. doi: 10.3969/j.issn.1001-5078.2019.04.021XIE Anning, ZHANG Hongwei, ZHAO Zhigang, et al. Panoramic stitching of infrared image based on three-dimensional rotation model[J]. Laser & Infrared, 2019, 49(4): 507-512. doi: 10.3969/j.issn.1001-5078.2019.04.021 [8] 杨炎龙, 徐超. 一种人体体表三维温度场的融合重建方法[J]. 红外技术, 2022, 44(1): 33-40. http://hwjs.nvir.cn/article/id/940a3a38-ec2a-4ec7-a13b-03c48a1897f1YANG Yanlong, XU Chao. Fusion reconstruction method for 3d temperature fields on the human body surface[J]. Infrared Technology, 2022, 44(1): 33-40. http://hwjs.nvir.cn/article/id/940a3a38-ec2a-4ec7-a13b-03c48a1897f1 [9] 郭静菁, 费晓燕, 葛鹏, 等. 基于全光纤光子计数激光雷达的高分辨率三维成像[J]. 红外与激光工程, 2021, 50(7): 141-150. https://www.cnki.com.cn/Article/CJFDTOTAL-HWYJ202107022.htmGUO Jingjing, FEI Xiaoyan, GE Peng, et al. High-resolution three-dimensional imaging based on all-fiber photon-counting Lidar system[J]. Infrared and Laser Engineering, 2021, 50(7): 141-150. https://www.cnki.com.cn/Article/CJFDTOTAL-HWYJ202107022.htm [10] 王中任, 郭晓康, 赵刚. 两组双目立体深度图像信息融合与三维重建方法[J]. 激光与红外, 2019, 49(2): 246-250. https://www.cnki.com.cn/Article/CJFDTOTAL-JGHW201902022.htmWANG Zhongren, GUO Xiaokang, ZHAO Gang. Depth image information fusion and three-dimensional reconstruction method of double binocular stereo vision[J]. Laser & Infrared, 2019, 49(2): 246-250. https://www.cnki.com.cn/Article/CJFDTOTAL-JGHW201902022.htm [11] 张红涛, 常艳, 谭联, 等. 基于z轴权重的麦粒图像三维重建[J]. 光学学报, 2019, 39(3): 127-135. https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB201903014.htmZHANG Hongtao, CHANG Yan, TAN Lian, et al. Three-dimensional reconstruction of wheat grain images based on z-axis weight[J]. Acta Optica Sinica, 2019, 39(3): 127-135. https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB201903014.htm [12] 苏毅, 谢植飚, 李路, 等. 基于多物理场耦合的空气型开关柜发热故障温升仿真分析[J]. 高压电器, 2020, 56(11): 1-7. https://www.cnki.com.cn/Article/CJFDTOTAL-GYDQ202011002.htmSU Yi, XIE Zhibiao, LI Lu, et al. Temperature rise simulation analysis of air switchgear heating fault based on coupling of multi-physical field[J]. High Voltage Apparatus, 2020, 56(11): 1-7. https://www.cnki.com.cn/Article/CJFDTOTAL-GYDQ202011002.htm [13] 陆彪, 汤凯, 陈德敏, 等. 低压开关柜母线温度场数值计算与分析[J]. 电工电能新技术, 2020, 39(10): 65-71. https://www.cnki.com.cn/Article/CJFDTOTAL-DGDN202010008.htmLU Biao, TANG Kai, CHEN Demin, et al. Thermal field calculation and analysis of low-voltage switchgear busbar[J]. Advanced Technology of Electrical Engineering and Energy, 2020, 39(10): 65-71. https://www.cnki.com.cn/Article/CJFDTOTAL-DGDN202010008.htm [14] 张建勋, 韩明慧, 代煜. 面向低分辨率单目内窥镜图像的三维多孔结构重建[J]. 光学精密工程, 2020, 28(9): 2085-2095. https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM202009022.htmZHANG Jianxun, HAN Minghui, DAI Yu. Three-dimensional porous structure reconstruction for low-resolution monocular endoscopic images[J]. Optics and Precision Engineering, 2020, 28(9): 2085-2095. https://www.cnki.com.cn/Article/CJFDTOTAL-GXJM202009022.htm [15] 任靖娟, 王玖炜, 曹莉. VR全景视频制作软件目标可视化三维虚拟仿真[J]. 计算机仿真, 2020, 37(9): 299-302, 311. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJZ202009063.htmREN Jingjuan, WANG Jinwei, CAO Li. VR panoramic video production software object visualization 3D virtual simulation[J]. Computer Simulation, 2020, 37(9): 299-302, 311. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJZ202009063.htm -
点击查看大图
图(5) / 表(1)
计量
- 文章访问数: 236
- HTML全文浏览量: 76
- PDF下载量: 26
- 被引次数: 0
