資源描述：
《基于融合動(dòng)態(tài)模板匹配的雙目測(cè)距算法①》由會(huì)員上傳分享，免費(fèi)在線閱讀，更多相關(guān)內(nèi)容在工程資料-天天文庫(kù)。
1、計(jì)算機(jī)系統(tǒng)應(yīng)用?ISSN?1003-3254,?CODEN?CSAOBNE-mail:?csa@iscas.ac.cnComputer?Systems?&?Applications,2018,27(11):218?223?[doi:?10.15888/j.cnki.csa.006639]http://www.c-s-a.org.cn?中國(guó)科學(xué)院軟件研究所版權(quán)所有.Tel:?+86-10-62661041基于融合動(dòng)態(tài)模板匹配的雙目測(cè)距算法①史珂路1,??田軍委2,??雷志強(qiáng)2,??張歡歡1,??孫 雷21(西安工業(yè)大學(xué)電子信息工程學(xué)院,?西安?710021)2(西安工業(yè)
2、大學(xué)機(jī)電工程學(xué)院,?西安?710021)通訊作者:?史珂路,?E-mail:?1543733488@qq.com摘 要:?高空無(wú)人機(jī)滅火時(shí),?要對(duì)火災(zāi)點(diǎn)進(jìn)行探測(cè).?傳統(tǒng)的探測(cè)方法易受環(huán)境的干擾,?并且它的反應(yīng)不靈敏,?實(shí)時(shí)性較差.?基于此本文提出了一種基于雙目立體視覺(jué)的探測(cè)方法:?首先搭建實(shí)驗(yàn)平臺(tái)并設(shè)計(jì)其硬件電路,?然后深入研究了經(jīng)典的雙目立體視覺(jué)測(cè)距算法,?提出了一種新的測(cè)距方法.?該方法主要內(nèi)容包括:?圖像獲取、感興趣區(qū)域提取、圖像預(yù)處理和基于權(quán)重融合的動(dòng)態(tài)模板匹配算法.?最后,采用多段非線性補(bǔ)償?shù)姆椒?gòu)建了測(cè)距模型,?并在實(shí)驗(yàn)平臺(tái)上對(duì)所構(gòu)建的測(cè)距模型進(jìn)行了大量的
3、實(shí)驗(yàn),?實(shí)驗(yàn)結(jié)果表明:?在50?m以內(nèi),?該測(cè)距模型的誤差在1?m以內(nèi),?100?m以內(nèi),?測(cè)距誤差在2?m,?匹配精度為6.947像素/m,?基本符合高空無(wú)人機(jī)滅火的精確測(cè)距要求,?故該測(cè)距模型測(cè)量的距離精度較好,?工程應(yīng)用性強(qiáng).關(guān)鍵詞:?測(cè)距模型;?測(cè)距算法;?圖像預(yù)處理;?動(dòng)態(tài)模板匹配算法;?多段非線性補(bǔ)償引用格式:??史珂路,田軍委,雷志強(qiáng),張歡歡,孫雷.基于融合動(dòng)態(tài)模板匹配的雙目測(cè)距算法.計(jì)算機(jī)系統(tǒng)應(yīng)用,2018,27(11):218–223.?http://www.c-s-a.org.cn/1003-3254/6639.htmlBinocularRangi
4、ngAlgorithmBasedonFusionDynamicTemplateMatchingSHI?Ke-Lu1,?TIAN?Jun-Wei2,?LEI?Zhi-Qiang2,?ZHANG?Huan-Huan1,?SUN?Lei21(School?of?Electronic?Information?and?Engineering,?Xi’an?Technological?University,?Xi’an?710021,?China)2(School?of?Mechatronic?Engineering,?Xi’an?Technological?University
5、,?Xi’an?710021,?China)Abstract:?When?the?high?altitude?unmanned?aerial?vehicle?is?extinguishing,?it?is?necessary?to?detect?the?fire?point.?Thetraditional?detection?method?is?easily?disturbed?by?the?environment,?its?reaction?is?insensitive?and?its?real-time?feature?ispoor.?Therefore,?a?n
6、ew?method?based?on?binocular?stereo?vision?is?proposed?in?this?study.?First,?we?set?up?the?experimentplatform?and?design?the?hardware?circuit.?Then?the?classical?binocular?stereo?vision?ranging?algorithm?is?studied?deeply,and?a?new?method?of?distance?measurement?is?proposed.?The?method?
7、mainly?includes:?image?acquisition,?region?ofinterest?extraction,?image?preprocessing,?and?dynamic?template?matching?based?on?the?weight?fusion.?Finally,?the?multisegment?nonlinear?compensation?method?is?used?to?construct?the?distance?measurement?model,?and?a?large?number?ofexp
