本文關(guān)鍵詞：基于計(jì)算機(jī)視覺的摔倒檢測系統(tǒng)的設(shè)計(jì)　出處：《大連海事大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 摔倒檢測 計(jì)算機(jī)視覺 視頻壓縮

【摘要】：意外摔倒威脅著人們的健康生活,尤其是在人口老齡化問題日益突出的今天。為解決這一問題,研究者們提出基于可穿戴設(shè)備、環(huán)境傳感器與計(jì)算機(jī)視覺這三種技術(shù)方案,其中計(jì)算機(jī)視覺技術(shù)逐漸成為室內(nèi)檢測環(huán)境下國際研究的主流方案。因此本文提出一種基于計(jì)算機(jī)視覺的摔倒檢測算法,并通過編程設(shè)計(jì)出一款以摔倒檢測、視頻監(jiān)控為主要功能的嵌入式摔倒檢測系統(tǒng)。在摔倒檢測算法中,通過單攝像頭采集視頻,混合高斯模型識(shí)別運(yùn)動(dòng)目標(biāo)并從中提取特征變量以描述人的運(yùn)動(dòng),最后對特征變量進(jìn)行摔倒判決得到檢測結(jié)果。在算法設(shè)計(jì)上本文從運(yùn)動(dòng)目標(biāo)與場景環(huán)境這兩方面提取動(dòng)態(tài)特征與狀態(tài)特征,并把動(dòng)態(tài)特征與狀態(tài)特征同閾值法與機(jī)器學(xué)習(xí)法這兩類摔倒判決算法有效結(jié)合,發(fā)揮其各自在摔倒識(shí)別過程中的優(yōu)越性。此外,本文討論了對于物體遮擋下運(yùn)動(dòng)目標(biāo)的摔倒判決處理并在圖像預(yù)處理階段對矩形框做出優(yōu)化。系統(tǒng)采用WIFI網(wǎng)絡(luò)構(gòu)建客戶端/服務(wù)器模式,客戶端使用ARM+DSP雙核異構(gòu)嵌入式系統(tǒng)實(shí)現(xiàn)視頻采集、摔倒檢測、視頻壓縮、網(wǎng)絡(luò)傳輸?shù)裙δ?服務(wù)器使用個(gè)人計(jì)算機(jī)進(jìn)行網(wǎng)絡(luò)連接,摔倒報(bào)警與復(fù)位,視頻解碼播放與保存并以可視化界面進(jìn)行操作。通過客戶端與服務(wù)器間的數(shù)據(jù)傳輸,系統(tǒng)可實(shí)現(xiàn)摔倒檢測算法對場景中發(fā)生的摔倒情況自動(dòng)報(bào)警以及看護(hù)人員對網(wǎng)內(nèi)各住戶的遠(yuǎn)程監(jiān)控。實(shí)驗(yàn)結(jié)果表明,摔倒檢測算法在無遮擋條件下、透光物體遮擋下以及不同光照環(huán)境下的準(zhǔn)確率分別可達(dá)94.2%、91.5%與91.0%,可見本設(shè)計(jì)中采用的摔倒檢測算法能夠在光照變化、透光物體遮擋等復(fù)雜環(huán)境下有效地檢測出摔倒事件的發(fā)生,輔助以場景視頻可使看護(hù)人員對摔倒者進(jìn)行及時(shí)有效的救助。
[Abstract]:Accidental falls threaten people's healthy lives, especially at a time when the aging population is becoming more and more acute. To solve this problem, researchers have proposed a new approach based on wearable devices. Environmental sensor and computer vision are three technical solutions. Computer vision technology has gradually become the mainstream of international research in indoor detection environment. So this paper proposes a fall detection algorithm based on computer vision and designs a fall detection algorithm by programming. Video surveillance as the main function of the embedded fall detection system. Fall detection algorithm through a single camera to capture video mixed Gao Si model to identify moving targets and extract feature variables to describe human motion. Finally, the detection result is obtained by the fall decision of the feature variable. In the algorithm design, the dynamic feature and the state feature are extracted from the moving object and scene environment. The dynamic feature and the state feature are combined with the threshold method and the machine learning method to effectively combine the two kinds of fall decision algorithms to give play to their respective advantages in the process of fall recognition. This paper discusses the fall decision processing of moving object under object occlusion and optimizes the rectangle frame in the image preprocessing stage. The system uses WIFI network to construct client / server mode. The client uses ARM DSP dual-core heterogeneous embedded system to realize the functions of video acquisition, fall detection, video compression, network transmission and so on. The server uses a personal computer for network connection, a fall alarm and a reset, video decoding, playback, and operation with a visual interface. Data transmission between the client and the server is carried out. The system can realize the automatic alarm of the fall in the scene and the remote monitoring of the residents in the network by the fall detection algorithm. The experimental results show that the fall detection algorithm is in the condition of no occlusion. The accuracy of transparent object occlusion and different light environment can reach 91.5% and 91.0% respectively. It shows that the fall detection algorithm used in this design can change in illumination. In the complex environment such as transparent object occlusion, the fall events can be detected effectively, and the scene video can help the caregivers to rescue the fall in a timely and effective manner.
【學(xué)位授予單位】：大連海事大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 朱峻熙;周仕通;;養(yǎng)老院安全管理的現(xiàn)狀與建議——基于徐州地區(qū)的實(shí)地調(diào)研[J];農(nóng)村經(jīng)濟(jì)與科技;2016年17期

2 茅莉磊;高強(qiáng);;一種人體跌倒檢測方法[J];計(jì)算機(jī)系統(tǒng)應(yīng)用;2016年05期

3 鄒蕓鸝;;中國老齡化時(shí)代下的新型養(yǎng)老社區(qū)設(shè)計(jì)模式初探[J];藝術(shù)科技;2015年02期

4 劉鵬;盧潭城;呂愿愿;鄧永莉;陸起涌;;基于MEMS三軸加速度傳感器的摔倒檢測[J];傳感技術(shù)學(xué)報(bào);2014年04期

5 金純;尹遠(yuǎn)陽;;一種基于統(tǒng)計(jì)學(xué)判別分析的老人摔倒檢測算法的研究[J];計(jì)算機(jī)應(yīng)用研究;2014年01期

6 李海霞;范紅;;基于背景差法的幾種背景建模方法的研究[J];工業(yè)控制計(jì)算機(jī);2012年07期

7 鐘珞;劉劍;;基于混合高斯和均值濾波法的運(yùn)動(dòng)檢測方法[J];武漢理工大學(xué)學(xué)報(bào)(信息與管理工程版);2010年05期

相關(guān)碩士學(xué)位論文 前7條

1 唐滔;基于信息技術(shù)產(chǎn)品的養(yǎng)老院室內(nèi)設(shè)計(jì)研究[D];北京交通大學(xué);2016年

2 曹希;基于視頻的異常行為智能檢測[D];北方工業(yè)大學(xué);2015年

3 張斌彪;老人遠(yuǎn)程看護(hù)系統(tǒng)的設(shè)計(jì)和實(shí)現(xiàn)[D];吉林大學(xué);2015年

4 王笑笑;多特征融合的摔倒行為檢測算法研究[D];重慶大學(xué);2015年

5 宋菲;基于ZigBee和OpenCV的老人智能監(jiān)護(hù)系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[D];上海交通大學(xué);2015年

6 袁德璋;基于貝葉斯網(wǎng)絡(luò)人體摔倒預(yù)測的研究[D];哈爾濱工業(yè)大學(xué);2014年

7 周曉美;基于視頻的運(yùn)動(dòng)目標(biāo)檢測算法的研究與應(yīng)用[D];安徽大學(xué);2014年

，

本文編號(hào)：1392468