基于背景減法的運(yùn)動(dòng)檢測(cè)算法研究.pdf

1、上海交通大學(xué)碩士學(xué)位論文基于背景減法的運(yùn)動(dòng)檢測(cè)算法研究姓名：張志付申請(qǐng)學(xué)位級(jí)別：碩士專(zhuān)業(yè)：軟件工程指導(dǎo)教師：付宇卓沈理20080908上海交通大學(xué)碩士學(xué)位論文基于背景減法的運(yùn)動(dòng)檢測(cè)算法研究VIAResearchonMotionDetectionAlgithmBasedonBackgroundSubtractionABSTRACTMotiondetectionisaveryimptprocessthequalityofdetectionr

2、esultiscriticaltothefurtherprocessing.Thispaperresearchesonexistingmotiondetectionalgithmsbasedonbackgroundsubtraction.thispaperalsopresentsasimplemodelfperfmanceevaluationofmotiondetectionalgithmbasedonbackgroundsubtrac

3、tionwiththeuseofprincipleofthetraditionalperfmanceevaluationmethodsofmotiondetectionalgithm.Thismodelbasesonthefollowingtruth:Thegroundtruthcanbegottenbymanualbyotherreliableprocedure.Thispapermeasuresseveralmotiondetect

4、ionalgithmsbasedonbackgroundsubtractiontheexperimentresultsshowthatthismodelcanquantitativelyshowthatwhichalgithmdobetteronspecialdetectionenvironment.What’smethispaperimplementstheenhancedW4algithmaccdingtoW4algithm.Enh

5、ancedW4inheritstheadvantagesofW4weaddperfmanceevaluationmodelofmotiondetectionalgithmtoit.ByshowingpeoplequantitativeresultswecanconcludethatenhancedW4dobetterjobthanW4.Finallythispapersetupsinputimageseriestheircrespond

6、ingreferencelibrary(GroundTruth).AfterthatthispaperdoessomeexperimentsonW4enhancedW4.Experimentalresultsshowthatwhichalgithmhasbetterdetectionresultsquantitatively.KEYWDS:motiondetection、backgroundsubtraction、W4、W4、evalu