本文選題：場景自適應(yīng)　切入點：行人檢測　出處：《東南大學(xué)學(xué)報(自然科學(xué)版)》2017年04期

【摘要】：針對現(xiàn)有基于機器學(xué)習(xí)的行人檢測算法存在當(dāng)訓(xùn)練樣本和目標(biāo)場景樣本分布不匹配時檢測效果顯著下降的缺陷,提出一種基于深度模型的場景自適應(yīng)行人檢測算法.首先,受Bagging機制啟發(fā),以相對獨立源數(shù)據(jù)集構(gòu)建多個分類器,再通過投票實現(xiàn)帶置信度度量的樣本自動選取;其次,利用DCNN深度結(jié)構(gòu)的特征自動抽取能力,加入一個自編碼器對源-目標(biāo)場景下特征相似度進行度量,提出了一種基于深度模型的場景自適應(yīng)分類器模型并設(shè)計了訓(xùn)練方法.在KITTI數(shù)據(jù)庫的測試結(jié)果表明,所提算法較現(xiàn)有非場景自適應(yīng)行人檢測算法具有較大的優(yōu)越性;與已有的場景自適應(yīng)學(xué)習(xí)算法相比較,該算法在檢測率上平均提升約4%.
[Abstract]:In view of the shortcomings of the existing pedestrian detection algorithms based on machine learning, when the distribution of training samples and target scene samples mismatch, a scene adaptive pedestrian detection algorithm based on depth model is proposed. Inspired by Bagging mechanism, several classifiers are constructed from relative independent source data sets, and then automatic sample selection with confidence measure is realized by voting. Secondly, the feature extraction ability of DCNN depth structure is used. Adding a self-encoder to measure feature similarity in source-target scenarios, a scene adaptive classifier model based on depth model is proposed and a training method is designed. The test results in KITTI database show that, Compared with the existing scene adaptive learning algorithm, the proposed algorithm has more advantages than the existing non-scene adaptive pedestrian detection algorithm, and the average detection rate of the proposed algorithm is increased by about 4% compared with the existing scene adaptive learning algorithm.
【作者單位】： 江蘇大學(xué)汽車工程研究院;江蘇大學(xué)汽車與交通工程學(xué)院;
【基金】：國家自然科學(xué)基金資助項目(U1564201,61403172,61601203) 中國博士后基金資助項目(2014M561592,2015T80511) 江蘇省重點研發(fā)計劃資助項目(BE2016149) 江蘇省自然科學(xué)基金資助項目(BK20140555) 江蘇省六大人才高峰資助項目(2014-DZXX-040,2015-JXQC-012)
【分類號】：TP18;TP391.41

【相似文獻】

相關(guān)碩士學(xué)位論文 前1條

1 陳浩;基于中層語義特征表達的物體檢測方法研究[D];北京工業(yè)大學(xué);2016年

，

本文編號：1658082