

浏览全部资源
扫码关注微信
1. 新疆大学软件学院
2. 新疆维吾尔自治区信号检测与处理重点实验室
3. 新疆大学软件工程重点实验室
4. 中国石油吐哈油田公司勘探开发研究院
Published:2021
移动端阅览
[1]田宸玮,王雪纯,杨嘉能,等.Kirsch算子地质图像边缘检测算法并行化研究[J].新疆大学学报(自然科学版)(中英文),2021,38(01):54-60+68.
[1]田宸玮,王雪纯,杨嘉能,等.Kirsch算子地质图像边缘检测算法并行化研究[J].新疆大学学报(自然科学版)(中英文),2021,38(01):54-60+68. DOI: 10.13568/j.cnki.651094.651316.2020.06.05.0001.
DOI:10.13568/j.cnki.651094.651316.2020.06.05.0001.
针对大尺寸地质图像边缘检测算法计算密集和数据密集的特性
为提高地质图像边缘检测算法的计算效率
提出一种自适应阈值的Kirsch算子的边缘检测算法.从传统算法层面
通过减少运算次数以及针对阈值设定随机性较大的问题提出自适应阈值的方法对其进行优化.从算法并行层面
在CPU-GPU传输开销以及线程规模选取上分析优化.经测试
改进的算法比现有算法减少了计算量
获取的边缘更清晰
对大于2 048×2 048尺寸的地质图像加速比可以保持在80倍以上(不考虑传输开销可保持在300倍以上).该方法的并行较易实现
为实时在线的地质图像边缘检测提供了可能.
Aiming at the computation-intensive and data-intensive characteristics of the edge detection algorithm of large-scale geological images
in order to improve the computational efficiency of the edge detection algorithm of geological images
an adaptive threshold kirsch operator edge detection algorithm was proposed. From the perspective of traditional algorithm
an adaptive threshold method is proposed to optimize the algorithm by reducing the number of operations and aiming at the problem of setting the random threshold. At the parallel level
cpu-gpu transmission overhead and thread size were selected for analysis and optimization. Compared with the existing algorithm
the improved algorithm requires less computation and gets clearer edges. The acceleration ratio of the geological image larger than 2 048×2 048 can be maintained at more than 80 times(the transmission cost can be maintained at more than 300 times). The parallel optimization scheme is easy to implement and can be applied to the edge detection of online real-time geological images.
VASUKI Y,HOLDEN E J,KOVESI P,et al.An interactive image segmentation method for lithological boundary detection:Arapid mapping tool for geologists[J].Computers&Geosciences,2017,100:27-40.
JOSEPH S,UIIR H,HIPINY I.Unsupervised classification of intrusive igneous rock thin section images using edge detection and colour analysis[C]//2017 IEEE International Conference on Signal and Image Processing Applications(ICSIPA).IEEE,2017:530-534.
MARR D,HILDRETH E.Theory of edge detection[J].Proceedings of the Royal Society of London.Series B.Biological Sciences,1980,207(1167):187-217.
CANNY J.A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986(6):679-698.
GONZALEZ C I,MELIN P,CASTRO J R,et al.An improved sobel edge detection method based on generalized type-2 fuzzy logic[J].Soft Computing,2016,20(2):773-784.
SONG Y,MA B,GAO W.Medical image edge detection based on improved differential evolution algorithm and prewittoperator[J].Acta Microscopica,2019,28(1).
郭江,丰义,朱程辉.基于特征颜色的车牌边缘检测方法[J].新疆大学学报(自然科学版),2007,24(2):126-130.GUO J,FENG Y,ZHU C H.Detection method of license plate edge based on characteristic color[J].Journal of Xinjiang University(Natural Science Edition),2007,24(2):126-130.(In Chinese)
DORAFSHAN S,MAGUIRE M,CHANG M.Comparing automated image-based crack detection techniques in the spatial and frequency domains[C]//26th ASNT Research Symposium,2017:34-42.
ALI M M H,YANNAWAR P,GAIKWAD A T.Study of edge detection methods based on palmprint lines[C]//2016 International Conference on Electrical,Electronics,and Optimization Techniques(ICEEOT).IEEE,2016:1344-1350.
梅琪,哈力旦·A,帕力旦·吐尔逊.二维图像的基本处理与边缘检测[J].新疆大学学报(自然科学版),2008,25(2):235-240.MEI Q,HALIDAN A,PALIDAN T.Basic processing and edge detection of 2D images[J].Journal of Xinjiang University(Natural Science Edition),2008,25(2):235-240.(In Chinese)
NIKOLIC M,TUBA E,TUBA M.Edge detection in medical ultrasound images using adjusted Canny edge detection algorithm[C]//2016 24th Telecommunications Forum(TELFOR).IEEE,2016:1-4.
QIAO B,JIN L,YANG Y.An adaptive algorithm for grey image edge detection based on grey correlation analysis[C]//2016 12th International Conference on Computational Intelligence and Security(CIS).IEEE,2016:470-474.
郭萌,胡辽林,赵江涛.基于Kirsch和Canny算子的陶瓷碗表面缺陷检测方法[J].光学学报,2016,36(9):27-33.GUO M,HU L L,ZHAO J T.Detection method of ceramic bowl surface defects based on Kirsch and Canny operators[J].Acta Optics,2016,36(9):27-33.(In Chinese)
JAIN A,NAMDEV A,CHAWLA M.Parallel edge detection by SOBEL algorithm using CUDA-C[C]//2016 IEEE Students’Conference on Electrical,Electronics and Computer Science(SCEECS).IEEE,2016:1-6.
YAM-UICAB R,LOPEZ-MARTINEZ J L,TREJO-S′ANCHEZ J A,et al.A fast Hough Transform algorithm for straight lines detection in an image using GPU parallel computing with CUDA-C[J].The Journal of Supercomputing,2017,73(11):4823-4842.
张晗,钱育蓉,侯海耀.CUDA下地质图像边缘检测算法并行优化[J].计算机工程与设计,2019,40(3):98-105.ZHANG H,QIAN Y R,HOU H Y.Parallel optimization of geological image edge detection algorithm under CUDA[J].Computer Engineering and Design,2019,40(3):98-105.(In Chinese)
唐斌,龙文.基于GPU+CPU的CANNY算子快速实现[J].液晶与显示,2016,31(7):714-720.TANG B,LONG W.Fast implementation of CANNY operator based on GPU+CPU[J].LCD and Display,2016,31(7):714-720.(In Chinese)
马歌,肖汉.基于Open CL的Prewitt算法的并行实现[J].现代电子技术,2014(20):103-106.MA G,XIAO H.Parallel implementation of prewitt algorithm based on Open CL[J].Modern Electronic Technology,2014(20):103-106.(In Chinese)
0
Views
243
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621