网站大量收购独家精品文档,联系QQ:2885784924

基于软硬件协同设计的车道线实时识别方法.pdf

基于软硬件协同设计的车道线实时识别方法.pdf

  1. 1、本文档共9页,可阅读全部内容。
  2. 2、有哪些信誉好的足球投注网站(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
  3. 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载
  4. 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
查看更多
基于软硬件协同设计的车道线实时识别方法.pdf

——— 1 1 1 2 1 .,,410082 2 .,,201620 :,, 。 ,, ,; 。 (FPGA)、 ,。 , ,60 。 :;;; :U461 DOI:10 .3969/ .issn.1004 132X.2015 .10 .011 j Real-time Lane Recognition Method Based on Hardware-software Co-design 1 1 1 2 Zhang Weiwei Song Xiaolin Zhang Sanlin WuXuncheng 1 .State Key Laboratory of AdvancedDesign and Manufacturing for Vehicle Body, Hunan University,Changsha,410082 2 .Shanghai University of Engineering Science,Shanghai,201620 Abstract :In order to obtain robustness and real timing for lane recognition, a lane recognition scheme was designed based on embedded system taking the effective allocation of hardware resource and softwarefunction into account. From the erspective of roducer/consumer model of the wholep p system,the necessity of matched enhancement was ut forward, and multi-scale matched filtering p method was roposed according to the different width characteristicsof lane markings,then an adapp - tive dynamic threshold was set based on local noiseestimationfrom theimproved mathematics model of CFAF.The road images of high frame rate and wide dynamic range were captured through field programmable ate array(FPGA) and then the matched filtering was speeded up through the coeffig - cient decomposition technology in the hardware optimization design. Experiments and evaluation prove the roposedsystem can robustly detect lane markingsunder different traffic scenarioswith thep processing frame rate of 60fps. Key words :multi-scalematchedfilter;constantfalsealarm rate(CFAR);embeddedsystem;lane recognition 0 ,

文档评论(0)

整理王 + 关注
实名认证
内容提供者

该用户很懒,什么也没介绍

1亿VIP精品文档

相关文档