期刊文献+

基于树莓派的安全头盔视频稳像模块设计与实现 被引量:1

Design and Implementation of Video Stabilization Module for Safety Helmet Based on Raspberry Pi
原文传递
导出
摘要 安全头盔采集的视频具有与传统方式采集的视频不同的振动特性。在树莓派开发板上,基于经典的稀疏光流法,与基于特征点的方法相结合,设计与实现了一个安全头盔视频稳像模块,提高了输出视频图像的平稳度。重点讨论了如何结合树莓派开发板的特性,提高模块的运行速度的问题;从精简部分运算过程、波浪式并行执行、视频硬编码等角度,充分调用树莓派的运算能力,在实现视频稳像的同时减少了模块执行时间。 Compared with traditional methods,video captured by cameras mounted on the safety helmet has different vibration feature.A video stabilization module based on sparse optical flow algorithm combined with feature point method has been designed and implemented on the Raspberry Pi development board,and the stability of the output video is enhanced.The problem of how to accelerate the running speed of the module has been focused on according to the characteristics of Raspberry Pi.From the aspects including cancelling some of the calculation process,wave front style parallel operation and hardware based video coding,the calculation ability of Raspberry Pi is utilized.It efficiently helps to stabilize the output video while reduce the operation time of the module.
作者 张雨 林炳辉 李雨墨 罗彬 芦佳欣 舍志芳 刘志 ZHANG Yu;LIN Bing-hui;LI Yu-mo;LUO Bin;LU Jia-xin;SHE Zhi-fang;LIU Zhi(North China University of Technology,Beijing 100144,China)
机构地区 北方工业大学
出处 《工业技术创新》 2020年第1期17-22,共6页 Industrial Technology Innovation
基金 北方工业大学信息学院电子工程系、北京市大学生科学研究与创业行动计划项目的资助与支持。
关键词 安全头盔 视频稳像 树莓派 波浪式并行执行 稀疏光流法 Safety Helmet Video Stabilization Raspberry Pi Wave Front Style Parallel Operation Sparse Optical Flow Algorithm
  • 相关文献

参考文献2

二级参考文献14

  • 1LUCAS B, KANADE T. An iterative image registration technique with an application to stereo vision[C]// DARPA Image Understanding Workshop, 1981:121- 130.
  • 2ZUCCHELLI M. Optical flow based structure from motion[D]. CVAP Lab., Royal Institute of Technology, Stockholm, 2002.
  • 3ADIV G. Determining three-dimensional motion and structure from optical flow generated by several moving objects[J]. IEEE Trans. Pattern Analysis and Machine Intelligence. 1985,7(3):384-401.
  • 4SRINIVASAN S. Extracting structure from optical flow using the fast error search technique[J]. International Journal of Computer Vision, 2000,37(3):203-230.
  • 5OHTA N, KANATANI K. Optimal structure from motion algorithm for optical flow[J]. IEEE Trans. Information and System, 1995,E78-D(12):1559-1565.
  • 6POELMAN C, KANADE T. The para perspective and projective factorization methods for recovering shape and motion[R]. Technical Report CMU-CS-95-173, Carnegie Mellon University, 1995.
  • 7CHIBA N, KANADE T. A tracker for broken and closely-spaced lines[R]. Technical Report CMU-CS-97- 182, Carnegie Mellon University, 1997.
  • 8HARRIS C, STEPHENS M. A combined comer and edge detector[C]//Proceedings Fourth Alvey Vision Conference, Manchester, 1988:147-151.
  • 9TOMASI C, KANADE T. Shape and motion from image streams: a factorization method-Part 3 Detection and tracking of point features[R]. Technical Report CMU-CS-91-132, Carnegie Mellon University, 1991.
  • 10BARON J, FLEET D, BEAUCHEMIN S. Performance of optical flow techniques[J]. International Journal of Computer Vision, 1994,12(1 ):43-77.

共引文献15

同被引文献5

引证文献1

二级引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部