基于HOG與IOELM的人體檢測(cè)方法研究及系統(tǒng)實(shí)現(xiàn)
發(fā)布時(shí)間：2018-12-20 15:25
【摘要】：圖像目標(biāo)檢測(cè)是計(jì)算機(jī)視覺技術(shù)中的一個(gè)研究熱點(diǎn),其中人體檢測(cè)是圖像目標(biāo)檢測(cè)的重要內(nèi)容,旨在利用計(jì)算機(jī)模擬人腦的思維方式從圖像或視頻中找出人體所在區(qū)域。目前人體檢測(cè)技術(shù)廣泛應(yīng)用于智能視頻監(jiān)控、車輛輔助駕駛系統(tǒng)和虛擬現(xiàn)實(shí)等領(lǐng)域。本文主要從基于統(tǒng)計(jì)學(xué)習(xí)的角度出發(fā),對(duì)人體檢測(cè)方法展開了系統(tǒng)研究,具體的工作介紹如下:1、提出一種基于梯度方向直方圖(Histogram of Oriented Gradient,HOG)與優(yōu)化極限學(xué)習(xí)機(jī)(Optimization Extreme Learning Machine,OELM)相結(jié)合的人體檢測(cè)方法。首先,采用梯度方向直方圖方法提取圖像的特征值;然后,利用OELM算法對(duì)提取圖像的特征值進(jìn)行分類訓(xùn)練;最后,利用非極大值抑制方法準(zhǔn)確標(biāo)記出目標(biāo)人體區(qū)域。實(shí)驗(yàn)表明,此方法相對(duì)于傳統(tǒng)的HOG與ELM方法在訓(xùn)練精度上有顯著的提高,在算法運(yùn)行時(shí)間上相對(duì)于經(jīng)典HOG與SVM方法更是快了近20倍。2、針對(duì)分類問題,提出一種基于EAS(Efficient Active Set)算法優(yōu)化OELM的方法,即 IOELM(Improved Optimization Extreme Learning Machine)。首先,利用有效集算法在迭代求解優(yōu)化問題最優(yōu)解的過程中,找出符合條件的最大搜索步長(zhǎng)來保證函數(shù)值嚴(yán)格下降;然后,設(shè)置臨時(shí)迭代步長(zhǎng)找到最優(yōu)步長(zhǎng)使目標(biāo)優(yōu)化問題的函數(shù)值較有效集法進(jìn)一步下降,并通過推測(cè)賦值法來減少迭代過程中產(chǎn)生的誤迭代;最后,提出基于HOG與IOELM相結(jié)合的人體檢測(cè)方法。通過實(shí)驗(yàn)證明,此方法不僅減少了人體檢測(cè)中訓(xùn)練過程的計(jì)算代價(jià),同時(shí)降低了樣本的訓(xùn)練時(shí)間。3、基于上述提出的方法設(shè)計(jì)并實(shí)現(xiàn)人體檢測(cè)系統(tǒng)。該系統(tǒng)主要包括三個(gè)模塊:圖像界面功能模塊,人體檢測(cè)模塊和性能評(píng)價(jià)模塊。圖像界面功能包括輸入和保存圖像,人體檢測(cè)包含幾種經(jīng)典的人體檢測(cè)方法,性能評(píng)價(jià)模塊是記錄幾種方法的評(píng)價(jià)指標(biāo)。
[Abstract]:Image target detection is a hot topic in computer vision technology, in which human body detection is an important part of image target detection. It aims to find out the region of human body from image or video by computer simulation of human brain. At present, human detection technology is widely used in intelligent video surveillance, vehicle-assisted driving system and virtual reality. In this paper, the human body detection method is studied systematically from the point of view of statistical learning. The specific work is as follows: 1. A gradient direction histogram (Histogram of Oriented Gradient,) based method is proposed. HOG) and optimized extreme learning machine (Optimization Extreme Learning Machine,OELM). Firstly, the gradient histogram method is used to extract the image eigenvalues; then, the OELM algorithm is used to classify the extracted image eigenvalues. Finally, the non-maximum suppression method is used to accurately mark the target human body region. The experimental results show that the training accuracy of this method is significantly higher than that of the traditional HOG and ELM methods, and the running time of the algorithm is nearly 20 times faster than that of the classical HOG and SVM methods. A method of optimizing OELM based on EAS (Efficient Active Set) algorithm, that is, IOELM (Improved Optimization Extreme Learning Machine)., is proposed. Firstly, in the process of iterative solving the optimal solution of the optimization problem, the maximum search step size is found by using the effective set algorithm to ensure the strict decline of the function value. Then, the function value of the objective optimization problem is further reduced by setting the temporary step size to find the optimal step size, and the error iteration in the iterative process is reduced by the method of inferred assignment. Finally, a human detection method based on HOG and IOELM is proposed. It is proved by experiments that this method not only reduces the computational cost of training process in human body detection, but also reduces the training time of samples. 3. Based on the method mentioned above, a human body detection system is designed and implemented. The system consists of three modules: image interface function module, human detection module and performance evaluation module. The function of image interface includes input and preservation of image, human body detection includes several classical human detection methods, and performance evaluation module is the evaluation index of recording several methods.
【學(xué)位授予單位】：西安理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41
本文編號(hào)：2388183
[Abstract]:Image target detection is a hot topic in computer vision technology, in which human body detection is an important part of image target detection. It aims to find out the region of human body from image or video by computer simulation of human brain. At present, human detection technology is widely used in intelligent video surveillance, vehicle-assisted driving system and virtual reality. In this paper, the human body detection method is studied systematically from the point of view of statistical learning. The specific work is as follows: 1. A gradient direction histogram (Histogram of Oriented Gradient,) based method is proposed. HOG) and optimized extreme learning machine (Optimization Extreme Learning Machine,OELM). Firstly, the gradient histogram method is used to extract the image eigenvalues; then, the OELM algorithm is used to classify the extracted image eigenvalues. Finally, the non-maximum suppression method is used to accurately mark the target human body region. The experimental results show that the training accuracy of this method is significantly higher than that of the traditional HOG and ELM methods, and the running time of the algorithm is nearly 20 times faster than that of the classical HOG and SVM methods. A method of optimizing OELM based on EAS (Efficient Active Set) algorithm, that is, IOELM (Improved Optimization Extreme Learning Machine)., is proposed. Firstly, in the process of iterative solving the optimal solution of the optimization problem, the maximum search step size is found by using the effective set algorithm to ensure the strict decline of the function value. Then, the function value of the objective optimization problem is further reduced by setting the temporary step size to find the optimal step size, and the error iteration in the iterative process is reduced by the method of inferred assignment. Finally, a human detection method based on HOG and IOELM is proposed. It is proved by experiments that this method not only reduces the computational cost of training process in human body detection, but also reduces the training time of samples. 3. Based on the method mentioned above, a human body detection system is designed and implemented. The system consists of three modules: image interface function module, human detection module and performance evaluation module. The function of image interface includes input and preservation of image, human body detection includes several classical human detection methods, and performance evaluation module is the evaluation index of recording several methods.
【學(xué)位授予單位】：西安理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41
【參考文獻(xiàn)】
相關(guān)期刊論文 前1條
1 梁琛華;常青;;基于HOG隨機(jī)森林分類器的人體識(shí)別[J];電視技術(shù);2013年15期
相關(guān)碩士學(xué)位論文 前1條
1 丁肖;針對(duì)靜態(tài)圖像的人體姿態(tài)估計(jì)[D];遼寧大學(xué);2015年
，本文編號(hào)：2388183
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2388183.html
最近更新
教材專著
