本文選題：視頻監(jiān)控 + GPU并行計(jì)算��； 參考：《計(jì)算機(jī)應(yīng)用》2017年01期

【摘要】：為了解決人群遮擋嚴(yán)重、光照突變等惡劣環(huán)境下人群計(jì)數(shù)準(zhǔn)確率低的問題,提出基于混合高斯模型(GMM)和尺度不變特征變換(SIFT)特征的人群數(shù)量統(tǒng)計(jì)分析新方法。首先,基于GMM提取運(yùn)動(dòng)人群,并采用灰度共生矩陣(GLCM)和形態(tài)學(xué)方法去除背景中移動(dòng)的小物體和較密集的噪聲等非人群前景,針對(duì)GMM算法提出了一種效率較高的并行模型;接著,檢測(cè)運(yùn)動(dòng)人群的SIFT特征點(diǎn)作為人群統(tǒng)計(jì)的基礎(chǔ),基于二值圖像的特征提取大大減少了執(zhí)行時(shí)間;最后,提出基于人群特征數(shù)和人群數(shù)量進(jìn)行統(tǒng)計(jì)分析的新方法,選擇不同等級(jí)的人群數(shù)量的數(shù)據(jù)集分別進(jìn)行訓(xùn)練,統(tǒng)計(jì)得出平均單個(gè)特征點(diǎn)數(shù),并對(duì)不同密度的行人進(jìn)行計(jì)數(shù)實(shí)驗(yàn)。算法采用基于GPU多流處理器進(jìn)行加速,并針對(duì)所提算法在統(tǒng)一計(jì)算設(shè)備架構(gòu)(CUDA)流上任務(wù)的有效調(diào)度的方法進(jìn)行分析。實(shí)驗(yàn)結(jié)果顯示,相比單流提速31.5%,相比CPU提速71.8%。
[Abstract]:In order to solve the problem of low accuracy of population counting under severe occlusion and sudden change of illumination, a new method of population quantitative analysis based on mixed Gao Si model (GMMM) and scale-invariant feature transform (sift) was proposed.Firstly, based on GMM extraction, gray level co-occurrence matrix (GLCM) and morphological methods are used to remove the non-crowd foreground of moving small objects and dense noise in the background. A parallel model is proposed for the GMM algorithm.The detection of SIFT feature points of moving population is the basis of population statistics, and the feature extraction based on binary image greatly reduces the execution time. Finally, a new statistical analysis method based on the number of population features and the number of people is proposed.The data sets of the number of people of different grades were selected for training, and the average number of individual feature points was obtained by statistics, and the counting experiment of pedestrians with different density was carried out.The algorithm is accelerated based on GPU multi-stream processor, and the efficient scheduling method of the proposed algorithm on the unified computing device architecture is analyzed.The experimental results show that compared with single flow and CPU, the speed is increased by 31.5 and 71.8, respectively.
【作者單位】： 上海理工大學(xué)光電信息與計(jì)算機(jī)工程學(xué)院;上海理工大學(xué)管理學(xué)院;
【基金】：國(guó)家自然科學(xué)基金資助項(xiàng)目(61572325,60970012) 高等學(xué)校博士學(xué)科點(diǎn)專項(xiàng)科研博導(dǎo)基金資助項(xiàng)目(20113120110008) 上海重點(diǎn)科技攻關(guān)項(xiàng)目(14511107902) 上海市工程中心建設(shè)項(xiàng)目(GCZX14014) 上海市一流學(xué)科建設(shè)項(xiàng)目(XTKX2012) 滬江基金研究基地專項(xiàng)(C14001)~~
【分類號(hào)】：TN948.6;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 龍興明,周靜;基于混合高斯模型的圖象去噪方法研究[J];計(jì)算機(jī)工程與應(yīng)用;2005年21期

2 王威;張鵬;高偉;王潤(rùn)生;;基于局部層次化混合高斯模型的視頻序列運(yùn)動(dòng)目標(biāo)檢測(cè)[J];信號(hào)處理;2009年05期

3 陳延濤;;一種改進(jìn)的混合高斯模型運(yùn)動(dòng)目標(biāo)檢測(cè)方法[J];四川大學(xué)學(xué)報(bào)(自然科學(xué)版);2009年05期

4 張燕平;白云球;趙勇;趙姝;;應(yīng)用改進(jìn)混合高斯模型的運(yùn)動(dòng)目標(biāo)檢測(cè)[J];計(jì)算機(jī)工程與應(yīng)用;2010年34期

5 李娟;邵春福;楊勵(lì)雅;;基于混合高斯模型的行人檢測(cè)方法[J];吉林大學(xué)學(xué)報(bào)(工學(xué)版);2011年01期

6 金廣智;石林鎖;白向峰;滕明春;;基于混合高斯模型的新型目標(biāo)檢測(cè)系統(tǒng)[J];計(jì)算機(jī)應(yīng)用;2011年12期

7 田，

本文編號(hào)：1737169