Neutral beam infrared image distortion correction based on vanishing point detection
-
摘要: 传统的霍夫变换、Cannylines直线检测算法、霍夫概率变换方法在图像上的直线检测效果不佳，存在检测线段不连续不正确的问题，因而，利用Sobel滤波对红外图像横轴和纵轴两个方向分别进行锐化，通过线段检测（LSD）算法实现线段特征检测，进而经线段聚类拟合获得图像中完整的直线，通过对直线交点计算获得消失点，最后依据透视关系计算得到校正图像。实验结果表明，该方法可以实现对中性束红外图像的自动有效校正。Abstract: The key parameters of the neutral beam, such as beam uniformity and beam divergence angle, can be obtained by analyzing the infrared images generated by the beam bombarding the target surface. Due to the camera setup angle, the IR images show geometric distortion, which affects the accurate analysis of the beam parameters. Therefore, so the images should be corrected for the distortion. The traditional Hough transform, canny lines algorithm, and probabilistic Hough transform methods are not effective in detecting straight lines on this image, and there is a problem of detecting discontinuous and incorrect line segments. In this paper, Sobel filter is used to sharpen the infrared image in the horizontal and vertical directions respectively and line segment feature is detected by line segment detector (LSD) algorithm. Then complete straight lines are obtained in the image by clustering and fitting the line segments according to the geometric and angular relationships between them. Vanishing points is calculated by the intersection points of the lines. Finally, the corrected image is obtained based on the perspective relationship. Experiment results prove that this method can achieve automatic and effective correction of neutral beam infrared images and it lays a basis for obtaining key parameters of the beam.
-
图 2 诊断靶图像和实验时的红外图像
Figure 2. Diagnostic target and experimental thermal infrared image
图 4 Sobel卷积后图像直线检测结果
Figure 4. Results of line segment detection after Sobel convolution
图 8 各直线检测算法检测结果比较
Figure 8. Comparison of detection results of each line segment detection algorithm
表 1 线段聚类算法
Table 1. Line segment clustering algorithm
algorithm line segment clustering algorithm based on line segment relation input the sample set D = {L1,L2,…,Lm}, L means coordinate values of two endpoints of a line segment output coordinates of vanishing points 1: R = $ \varnothing $ 2: for i = 1,2,…,m do 3 C=$ \varnothing $ 4: for j = 1,2….,m do 5: calculate $ h $ between Li and Lj 6: calculate $ \Delta \theta $ between Li and Lj 7: if $ h $＜threshold and $ \Delta \theta $＜threshold then 8: C=C $ \cup $ Lj 9: remove Lj from D 10: R=R $ \cup $ C 11: remove Li from D 12: take the two sets from R with the largest number of line segments. 13: use the least square method to fit the two lines in Step 12. 14: calculate the intersection of two lines. That is the vanishing point. 
下载: 导出CSV
表 2 直线检测方法比较
Table 2. Comparison of linear detection methods
the degree
of
continuousthe number of
lines detected
in x-directionthe effective number
of lines detected
in x-directionthe number of
lines detected
in y-directionthe effective number
of lines detected
in y-directionrun
time/sHough transform 1 3 3 0 0 0.021 probabilistic Hough transform 0 105 98 11 0 0.014 Cannylines 0 53 44 31 24 3.08 our algorithm 1 5 5 5 5 4.61
下载: 导出CSV
-
[1] De Muri M, Cavallin T, Pasqualotto R, et al. High energy flux thermo-mechanical test of 1D-carbon-carbon fibre composite prototypes for the SPIDER diagnostic calorimeter[J]. Review of Scientific Instruments, 2014, 85: 02A718. doi: 10.1063/1.4827655 [2] 刘泽元, 尚永红, 林博颖, 等. 红外测温设备的空间环境影响及防护研究[J]. 电子测量与仪器学报, 2020, 34(4):165-171 doi: 10.13382/j.jemi.B1902645Liu Zeyuan, Shang Yonghong, Lin Boying, et al. Research on space environment influence and protection of infrared temperature measurement equipment[J]. Journal of Electronic Measurement and Instrumentation, 2020, 34(4): 165-171 doi: 10.13382/j.jemi.B1902645 [3] Xu Yongjian, Zhang Li, Yu Ling, et al. Feasibility analysis of 1-D carbon material in application of negative particle beam diagnostics[J]. Fusion Science and Technology, 2018, 73(4): 533-538. doi: 10.1080/15361055.2017.1392820 [4] Rizzolo A, Palma M D, De Muri M, et al. Design and analyses of a one-dimensional CFC calorimeter for SPIDER beam characterisation[J]. Fusion Engineering and Design, 2010, 85(10/12): 2268-2273. [5] 曾慧, 邓小明, 赵训坡, 等. 基于线对应的单应矩阵估计及其在视觉测量中的应用[J]. 自动化学报, 2007, 33(5):449-455 doi: 10.16383/j.aas.2007.05.001Zeng Hui, Deng Xiaoming, Zhao Xunpo, et al. Line-based homography estimation and its application in visual metrology[J]. Acta Automatica Sinica, 2007, 33(5): 449-455 doi: 10.16383/j.aas.2007.05.001 [6] Zeng Hui, Deng Xiaoming, Hu Zhanyi. A new normalized method on line-based homography estimation[J]. Pattern Recognition Letters, 2008, 29(9): 1236-1244. doi: 10.1016/j.patrec.2008.01.031 [7] Liu Tianyang, Xu Weiming, Yin Xiaodong, et al. Planar metric rectification from perspective image via vertical vanishing point[C]//2014 7th International Congress on Image and Signal Processing. 2014: 498-502. [8] Su Hongyu. Vanishing points in road recognition: a review[C]//11th International Symposium on Computational Intelligence and Design (ISCID). 2018: 132-136. [9] Tuytelaars T, Proesmans M, Van Gool L. The cascaded Hough transform[C]//Proceedings of International Conference on Image Processing. 1997: 736-739. [10] Chen Xuehui, Jia Ruiqing, Ren Hui, et al. A new vanishing point detection algorithm based on Hough transform[C]//Third International Joint Conference on Computational Science and Optimization. 2010: 440-443. [11] Zu Zhaozi, Hou Yingtuan, Cui Dixiao, et al. Real-time road detection with image texture analysis-based vanishing point estimation[C]//IEEE International Conference on Progress in Informatics and Computing (PIC). 2015: 454-457. [12] Rasmussen C. Texture-based vanishing point voting for road shape estimation[C]//Proceedings of the British Machine Vision Conference. 2004. [13] Stentiford F. Attention-based vanishing point detection[C]//International Conference on Image Processing. 2006: 417-420. [14] 吴曦. 基于MATLAB的图像边缘检测算法的研究和实现[D]. 长春: 吉林大学, 2014Wu Xi. Image edge detection based on MATLAB[D]. Changchun: Jilin University, 2014 [15] Von Gioi R G, Jakubowicz J, Morel J M, et al. LSD: A fast line segment detector with a false detection control[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(4): 722-732. doi: 10.1109/TPAMI.2008.300 [16] 曹义亲, 何恬, 刘龙标. 基于改进LSD直线检测算法的钢轨表面边界提取[J]. 华东交通大学学报, 2021, 38(3):95-101 doi: 10.16749/j.cnki.jecjtu.20210706.006Cao Yiqin, He Tian, Liu Longbiao. Rail surface boundary extraction based on improved LSD line detection algorithm[J]. Journal of East China Jiaotong University, 2021, 38(3): 95-101 doi: 10.16749/j.cnki.jecjtu.20210706.006 [17] Li Mengxuan, Yang Zhi, Zhao Bin, et al. Research on transmission conductor extraction method based on mainline projection LSD algorithm[C]//2022 2nd International Conference on Consumer Electronics and Computer Engineering (ICCECE). 2022: 747-750. -
点击查看大图
图(8) / 表(2)
计量
- 文章访问数: 655
- HTML全文浏览量: 207
- PDF下载量: 44
- 被引次数: 0
