本文選題：HOG特征 + 自適應(yīng)學(xué)習(xí)率背景建模�。� 參考：《計(jì)算機(jī)科學(xué)》2017年S1期

【摘要】：行人統(tǒng)計(jì)在智能監(jiān)控領(lǐng)域中具有重要意義,但復(fù)雜背景環(huán)境以及行人運(yùn)動(dòng)過程中出現(xiàn)的遮擋現(xiàn)象導(dǎo)致當(dāng)前方法的準(zhǔn)確率并不高。此外,傳統(tǒng)過線統(tǒng)計(jì)人數(shù)的方式的實(shí)際適用范圍有限�？紤]到現(xiàn)有方法的不足,提出了一種基于熱點(diǎn)區(qū)域定義的人數(shù)統(tǒng)計(jì)方法。首先,利用自適應(yīng)學(xué)習(xí)率背景建模提取運(yùn)動(dòng)目標(biāo)前景,得到前景區(qū)域的位置和大小,掃描計(jì)算運(yùn)動(dòng)目標(biāo)前景范圍內(nèi)的HOG特征,并判別是否存在頭肩目標(biāo);然后,利用基于KCF的目標(biāo)匹配算法跟蹤頭肩目標(biāo);最后,結(jié)合目標(biāo)運(yùn)動(dòng)軌跡與提出的區(qū)域人數(shù)統(tǒng)計(jì)算法進(jìn)行行人人數(shù)統(tǒng)計(jì)。采用24fps的手機(jī)拍攝的長度為10min、分辨率為960×720像素的視頻做人數(shù)統(tǒng)計(jì)實(shí)驗(yàn)。實(shí)驗(yàn)結(jié)果表明,所提算法在統(tǒng)計(jì)人數(shù)時(shí)正確率可達(dá)到93.1%,能滿足實(shí)時(shí)性要求。該方法結(jié)合了檢測效率和準(zhǔn)確率,在背景環(huán)境復(fù)雜的場景下具有良好的效果,能適應(yīng)各類人數(shù)統(tǒng)計(jì)的實(shí)際應(yīng)用場景。
[Abstract]:Pedestrian statistics is of great significance in the field of intelligent monitoring, but the accuracy of the current methods is not high due to the complex background environment and the occlusion phenomenon in the pedestrian movement process. In addition, the traditional method of over-line statistics of the actual scope of application is limited. Considering the shortcomings of the existing methods, a population statistics method based on the definition of hot spot region is proposed. First, using adaptive learning rate background modeling to extract the foreground of moving target, obtain the position and size of foreground region, scan and calculate the HOG feature in the foreground range of moving target, and judge whether there is head-shoulder target. The target matching algorithm based on KCF is used to track the head-shoulder target. Finally, the pedestrian number is calculated by combining the moving track of the target with the proposed regional population statistics algorithm. The 24fps mobile phone is used to record video with a length of 10 minutes and a resolution of 960 脳 720 pixels. The experimental results show that the accuracy of the proposed algorithm can reach 93.1, which can meet the real-time requirements. This method combines the detection efficiency and the accuracy, and has good effect under the background environment complex scene, and can adapt to the practical application scene of all kinds of population statistics.
【作者單位】： 浙江工業(yè)大學(xué)計(jì)算機(jī)科學(xué)與技術(shù)學(xué)院;
【基金】：國家自然科學(xué)基金資助項(xiàng)目(C12412135,61402410) 浙江省自然科學(xué)基金資助項(xiàng)目(LY13F020029,LQ14F020004)資助
【分類號(hào)】：TN948.6;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 趙法彬;;Wi-Fi的應(yīng)用前景更加廣闊[J];數(shù)字通信世界;2009年10期

2 付海濤;柴喬林;李濤;;完全覆蓋熱點(diǎn)區(qū)域的多重覆蓋算法[J];計(jì)算機(jī)工程與應(yīng)用;2010年35期

3 劉林峰;劉業(yè);;基于熱點(diǎn)區(qū)域場景的傳感器網(wǎng)絡(luò)拓?fù)淇刂扑惴╗J];計(jì)算機(jī)技術(shù)與發(fā)展;2010年10期

4 姚瑤;王強(qiáng);;PCC引入初期實(shí)現(xiàn)熱點(diǎn)區(qū)域控制的方案[J];電信工程技術(shù)與標(biāo)準(zhǔn)化;2014年08期

5 梁景舒;吳鈺鋒;詹曉生;黃偉鋒;;基于熱點(diǎn)區(qū)域EVDO網(wǎng)絡(luò)3G下切2G的優(yōu)化分析[J];信息通信;2014年02期

6 余小俊;;TD通信系統(tǒng)高校熱點(diǎn)區(qū)域HSDPA專題研究[J];信息通信;2011年05期

7 ;大唐移動(dòng)LTE全系統(tǒng)精細(xì)化覆蓋解決方案 打造無縫移動(dòng)寬帶體驗(yàn)[J];通信世界;2013年26期

8 郝黎凱;張磊;;“以動(dòng)制動(dòng)”——中興通訊TD-SCDMA話務(wù)流動(dòng)應(yīng)對(duì)方案[J];電信技術(shù);2008年09期

9 王自軍;;WLAN市場建設(shè)和運(yùn)營商發(fā)展模式[J];河北企業(yè);2012年09期

10 ;[J];;年期

相關(guān)碩士學(xué)位論文 前1條

1 王秋芳;干擾系統(tǒng)中的協(xié)作和協(xié)調(diào)機(jī)制及熱點(diǎn)區(qū)域Massive-MIMO容量分析[D];浙江大學(xué);2016年

，

本文編號(hào)：1856248