全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于视频分析的地震检测
Earthquake Detection Based on Video Analysis

DOI: 10.12677/AIRR.2019.83016, PP. 126-139

Keywords: 地震烈度分析,运动目标分割,特征匹配,视频分析
Earthquake Intensity Analysis
, Moving Object Segmentation, Feature Matching, Video Analysis

Full-Text   Cite this paper   Add to My Lib

Abstract:

传统的地震烈度分析是基于传统地震测量仪器以及光学式地震仪进行的。虽然这种分析的方法应用广泛,技术相对成熟,但是其响应速度较慢、设备成本高。相比之下,基于视频分析的地震检测是对传统方法的一种补充,有着响应速度快,投入成本较小的优势。因此本文将计算机视觉技术应用到地震分析中,通过运动估计的方法获取视频中的运动矢量序列,由该序列分析得出该视频中是否发生地震,并实现截取地震部分视频、地震的烈度以及绘制其抖动图的功能。再通过灰度值分析、目标分割、特征点匹配等方法滤除一些特殊场景的误判。本文将该算法应用于地震中的现场地震视频和网络上的一些地震视频,并通过实验验证了该算法的有效性。
Traditional seismic intensity analysis is based on traditional seismograph and optical seismograph. Although this method is widely used and relatively mature in technology, its response speed is slow and equipment cost is high. In contrast, seismic detection based on video analysis is a complement to traditional methods, which has the advantages of fast response and low cost. In this paper, computer vision technology is applied to seismic analysis. Motion vector sequence in video is obtained by motion estimation method. From this sequence analysis, whether earthquake occurs in the video is obtained, and the function of intercepting seismic video, seismic intensity and drawing acceleration and jitter maps is realized. Then, the gray value analysis, target segmentation, feature point matching and other methods are used to filter out the misjudgments of some special scenes. For the validity of this method, this method is applied to a large number of in-situ seismic videos and some seismic videos on the network. Experiments show that the proposed method can effectively accomplish these tasks.

References

[1]  罗福龙, 蔺大禄. 地震仪器检测技术探讨[J]. 石油管材与仪器, 2018, 4(1): 1-4.
[2]  郭志宇. 基于视频监控的震害快速评估与地震应急技术可行性研究[D]: [硕士学位论文]. 兰州: 中国地震局兰州地震研究所, 2017.
[3]  李东平, 刘倩倩, 龚俊. 基于海量视频监控的中小地震烈度快速判断方法尝试[J]. 地震研究, 2017, 40(2): 324-332.
[4]  于飞, 黄士坦. H.264运动估计算法分析[J]. 计算机技术与发展, 2009, 19(4): 115-118.
[5]  Wenger, S.H. (2003) 264/AVC over IP. IEEE Transactions on Circuits and Systems for Video Technology, 13, 645-656.
https://doi.org/10.1109/TCSVT.2003.814966
[6]  夏东. 智能视频监控中目标检测、跟踪和识别方法研究[D]: [博士学位论文]. 长沙: 国防科学技术大学, 2012.
[7]  杨勇, 王桥, 吴乐南. 基于标号场的光流法二维运动估计[J]. 电子与信息学报, 2001, 23(12): 1321-1325.
[8]  钟平, 于前洋, 金光. 基于特征点匹配技术的运动估计及补偿方法[J]. 光电子?激光, 2004, 15(1): 73-77.
[9]  Lowe, D.G. (2004) Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 60, 91-110.
https://doi.org/10.1023/B:VISI.0000029664.99615.94
[10]  Koenderink, J. (1991) Affine Structure from Motion. Journal of the Optical Society of America A, 8, 377-385.
https://doi.org/10.1364/JOSAA.8.000377
[11]  余洪山. 基于三维视觉系统图像特征和三维信息的运动估计方法[P]. 中国专利, CN201310544349.7, 2014-02-05.
[12]  秦晓波, 霍立文, 柴志成. 基于宏块的Hs光流算法运动估计优化研究[J]. 电脑迷, 2018(10): 150+152.
[13]  肖丽君. 基于背景减与帧间差分结合的视频运动目标分割[J]. 北华大学学报(自然科学版), 2010, 11(5): 467-470.
[14]  崔振兴, 曾威, 杨明强, 等. 一种改进的SURF快速匹配算法[J]. 江苏师范大学学报(自然科学版), 2014, 32(3): 41-46.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133