基于尺度不變特征和位置先驗的行人檢測算法
發(fā)布時間：2019-07-18 16:26
【摘要】：基于相鄰和非相鄰特征(NNNF)行人檢測算法,提出了一種方法來解決行人特征對尺度變化敏感的問題以及窗口誤檢的問題.首先,在NNNF基礎(chǔ)上,設(shè)計了一種尺度不變的特征.由韋伯定理啟發(fā),該特征表示為兩個相鄰或非相鄰區(qū)域的差分值與這兩個區(qū)域特征和的比值.這種新的特征具有很強的尺度不變性.此外,還提出了基于行人位置先驗的上下文信息,作為一種簡單有效的后處理方法.在行人場景中,行人的高度與位置存在一定的映射關(guān)系.利用SVM(support vector machine)訓練了行人高度關(guān)于行人位置的回歸模型.該模型能有效地濾除那些行人高度與位置信息不符合回歸模型的檢測窗口.實驗表明,相比于NNNF-L2和NNNF-L4,本文提出的方法在Caltech數(shù)據(jù)庫的檢測性能分別提高了2.90%,和2.28%,.同時,本文提出的方法也在所有基于非深度網(wǎng)絡的行人檢測方法中具有最好的檢測性能,平均漏檢率為14.56%,.
[Abstract]:Based on (NNNF) pedestrian detection algorithm with adjacent and non-adjacent features, a method is proposed to solve the problem that pedestrian features are sensitive to scale change and window error detection. First of all, on the basis of NNNF, a scale invariant feature is designed. Inspired by Weber's theorem, this feature is represented by the ratio of the difference score of two adjacent or non-adjacent regions to the sum of the characteristics of the two regions. This new feature has strong scale invariance. In addition, a context information based on pedestrian location priori is proposed as a simple and effective post-processing method. In pedestrian scene, there is a certain mapping relationship between pedestrian height and position. The regression model of pedestrian height about pedestrian position is trained by SVM (support vector machine). The model can effectively filter out the detection window where the pedestrian height and position information do not conform to the regression model. The experimental results show that the detection performance of the proposed method in Caltech database is improved by 2.90% and 2.28%, respectively, compared with NNNF-L2 and NNNF-L4,. At the same time, the method proposed in this paper also has the best detection performance among all pedestrian detection methods based on non-depth network, and the average missed detection rate is 14.56%.
【作者單位】： 天津大學電氣自動化與信息工程學院;
【基金】：國家自然科學基金資助項目(61472274)~~
【分類號】：TP391.41
本文編號：2515969
[Abstract]:Based on (NNNF) pedestrian detection algorithm with adjacent and non-adjacent features, a method is proposed to solve the problem that pedestrian features are sensitive to scale change and window error detection. First of all, on the basis of NNNF, a scale invariant feature is designed. Inspired by Weber's theorem, this feature is represented by the ratio of the difference score of two adjacent or non-adjacent regions to the sum of the characteristics of the two regions. This new feature has strong scale invariance. In addition, a context information based on pedestrian location priori is proposed as a simple and effective post-processing method. In pedestrian scene, there is a certain mapping relationship between pedestrian height and position. The regression model of pedestrian height about pedestrian position is trained by SVM (support vector machine). The model can effectively filter out the detection window where the pedestrian height and position information do not conform to the regression model. The experimental results show that the detection performance of the proposed method in Caltech database is improved by 2.90% and 2.28%, respectively, compared with NNNF-L2 and NNNF-L4,. At the same time, the method proposed in this paper also has the best detection performance among all pedestrian detection methods based on non-depth network, and the average missed detection rate is 14.56%.
【作者單位】： 天津大學電氣自動化與信息工程學院;
【基金】：國家自然科學基金資助項目(61472274)~~
【分類號】：TP391.41
【相似文獻】
相關(guān)期刊論文 前6條
1 黃小蘭;;比較幾種挑選“最優(yōu)”回歸模型的指標[J];中國衛(wèi)生統(tǒng)計;1988年04期
2 李君;;基于路徑的多元標準回歸模型及其應用[J];湛江師范學院學報;2006年06期
3 韓立強,姜興序;機床主軸結(jié)構(gòu)回歸模型近似重分析優(yōu)化設(shè)計[J];吉林工學院學報;1990年04期
4 李海濤;;重回歸模型在軟件開發(fā)預估工作量中的應用[J];電腦與電信;2011年03期
5 潘寶駿,張文彤,張錫斌,吳思英;以SPSS軟件包擬合條件logistic回歸模型的探索[J];海峽預防醫(yī)學雜志;2002年06期
6 朱玨鈺;;利用EXCEL實現(xiàn)計酬分配預測的回歸分析[J];長沙大學學報;2010年02期
相關(guān)碩士學位論文 前2條
1 鄧健康;基于級聯(lián)回歸模型的人臉配準研究[D];南京信息工程大學;2015年
2 李昊鑫;三維手姿態(tài)建模及其交互系統(tǒng)研究[D];電子科技大學;2016年
，本文編號：2515969
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2515969.html
最近更新
教材專著
