發(fā)布時(shí)間：2018-10-05 21:48

【摘要】：基于騎車人目標(biāo)識(shí)別的騎車人保護(hù)系統(tǒng)是保護(hù)道路環(huán)境中騎車人的重要手段。該文提出了騎車人目標(biāo)的候選區(qū)域選擇方法,并結(jié)合基于深度卷積神經(jīng)網(wǎng)絡(luò)的目標(biāo)分類與定位方法,實(shí)現(xiàn)了騎車人目標(biāo)的有效識(shí)別。候選區(qū)域選擇方法可分為3部分:騎車人共有顯著性區(qū)域檢測(cè)、基于冗余策略的候選區(qū)域生成和基于車載視覺幾何約束的候選區(qū)域選擇。在公開的騎車人數(shù)據(jù)庫(kù)上進(jìn)行的對(duì)比試驗(yàn)表明:相對(duì)于現(xiàn)有的目標(biāo)候選區(qū)域選擇及目標(biāo)識(shí)別方法,該方法顯著提升了騎車人目標(biāo)的識(shí)別率及識(shí)別精度,進(jìn)而驗(yàn)證了該方法的有效性。
[Abstract]:Biker protection system based on target recognition is an important method to protect cyclists in road environment. In this paper, a candidate region selection method for cyclists is proposed, and the method of target classification and location based on deep convolution neural network is combined to realize the effective recognition of cyclists. The candidate region selection method can be divided into three parts: rider common significant region detection, candidate region generation based on redundancy strategy and candidate region selection based on vehicle vision geometric constraints. A comparative experiment conducted on the open cyclists database shows that compared with the existing methods of target candidate selection and target recognition, this method has significantly improved the recognition rate and accuracy of cyclists' targets. The validity of the method is verified.
【作者單位】： 清華大學(xué)汽車安全與節(jié)能國(guó)家重點(diǎn)實(shí)驗(yàn)室;北京航空航天大學(xué)軟件學(xué)院;
【基金】：國(guó)家自然科學(xué)基金資助項(xiàng)目(51605245) 戴姆勒-清華大學(xué)聯(lián)合項(xiàng)目
【分類號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前1條

1 古杰;基于大規(guī)模仿真數(shù)據(jù)的騎車人碰撞行為研究[D];清華大學(xué);2014年

，

本文編號(hào)：2254989