球面复眼多通道信息融合

球面复眼多通道信息融合

ID:36556062

大小:4.86 MB

页数:60页

时间:2019-05-12

球面复眼多通道信息融合_第1页
球面复眼多通道信息融合_第2页
球面复眼多通道信息融合_第3页
球面复眼多通道信息融合_第4页
球面复眼多通道信息融合_第5页
资源描述:

《球面复眼多通道信息融合》由会员上传分享,免费在线阅读,更多相关内容在行业资料-天天文库

1、中国科学技术大学硕士学位论文球面复眼多通道信息融合姓名:张浩申请学位级别:硕士专业:精密机械与仪器指导教师:王克逸20100602摘要ABSTRACTCompoundeyeismoreandmoreconcernedbyacademiaandindustry,duetoitsadvantageoflargeviewfield,highagility,andmuti-channels.Thereforescholarsofmanycountriesbegintofocusontheirinterestsintotheresearchofartificialcompoundeye.Howe

2、ver,theadvantageofcompoundeyeisusuallylimitedbecauseoftherestrictionoffabricationtechnique.Thestructureofplanercompoundeyelimitsitsfieldofview.Althoughsphericalcompoundeyeisverysimilarwiththenaturecompoundeyeinlargefieldofview,theplanerimagesensorrequiresthateveryeyeletlensinthesphericalsurfaceh

3、asdifferentfocuslengthanddifferentprofilewhichisusuallyaspherical.Furthermore,theasphericallensisverydifficulttofabricatebyusingtraditionalfabricationtechnique.Ourlabdesignedanewartificialcompoundeyemodelbasedonthenaturecompound-eyestructure.Thismodelhandlesthecontradictionbetweenthesphericaldom

4、eandplanerimagesensor.Itsopticalperformancecanbeoptimizedbasedontheliquidlensfabricationsystemdevelopedbyourlab.Inthisworkreported,theopticalperformanceofthismodelisanalyzed.Weproposethetechniqueofimagedenoisingandimagetransferringintheimagepreprocessingsection,includingsub-pixelmethodandNeuraln

5、etworkarithmeticwhichsolvetheproblemofaberrationandnoiseincompoundeyeimagingprocess.Moreover,weproposemulti-channelinformationinfusingarithmetic,whichcontainsimagemosaic,superresolutionimagingandmovingobjectdetection.Toexaminethefeasibilityofthearithmeticinimagepreprocessingandmulti-channelinfor

6、mationinfusing,weperformedsimulationbyusingMatlab,andbuilttheexperimentalplatformforfurtherobservation.Bothofresultsshowthatneuralnetworkhasgoodperformanceinthenonlinearcalibrationandthecenterofgravitymethodcanrecordthepositionofspotprecisely.Besides,theresultsalsoshowthatalthoughcompoundeyeisan

7、opticalsystemthatsacrificeitsspatialresolutiontoimproveitsfieldofview,ourcompoundeyemodelcanstilldetecttheprecisepositionofmovingobject.Ourmodelwillhavehasgoodapplicationforeground.KeyWords:compoundeye,neuralnetwork,centerof

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。