采用自適應(yīng)變異粒子群優(yōu)化SVM的行為識(shí)別
[Abstract]:In order to improve the recognition ability of human behavior in video sequences, a motion recognition framework based on local features is established. The algorithms involved in this framework are studied in two parts: temporal and spatial feature extraction and coding and parameter optimization of SVM classifier. Firstly, the spatio-temporal interest point (STIP),) is obtained by Harris3D detector, and the STIP is described by the directional gradient histogram (HOG) and the optical flow direction histogram (HOF), and the Fisher vector is introduced to encode the feature descriptor. Due to the lack of generalization ability of SVM action classification model with fixed parameters, particle swarm optimization (PSO) algorithm is applied to the optimization of the parameters of each action classifier. According to the characteristics of population diversity generation by generation, the particle aggregation model is constructed. It is used to dynamically adjust the variation probability of each generation of particles. Finally, the proposed method is verified by using KTH and HMDB51 data sets. The results show that the proposed adaptive mutation particle swarm optimization (AMPSO) algorithm can effectively avoid population falling into local optimum and has strong global optimization ability, and the recognition accuracy on KTH and HMDB51 datasets is 87.50% and 26.41% respectively, which is superior to the other two recognition methods. Experiments show that the AMPSO algorithm has good convergence performance and high practicability and accuracy.
【作者單位】: 北京工業(yè)大學(xué)信息學(xué)部;
【基金】:國(guó)家自然科學(xué)基金項(xiàng)目(No.61175087) 北京工業(yè)大學(xué)智能機(jī)器人“大科研”推進(jìn)計(jì)劃“助老智能輪椅床自主測(cè)控系統(tǒng)的研究與實(shí)現(xiàn)”資助項(xiàng)目(No.040000546317552)
【分類號(hào)】:TP18;TP391.41
【相似文獻(xiàn)】
相關(guān)期刊論文 前10條
1 張興華;潘宏俠;;一種帶有自適應(yīng)變異的雙種群優(yōu)化算法[J];機(jī)械管理開(kāi)發(fā);2012年03期
2 易燕;沈云;王開(kāi)云;;在內(nèi)部演化硬件中實(shí)現(xiàn)自適應(yīng)變異參數(shù)控制[J];云南大學(xué)學(xué)報(bào)(自然科學(xué)版);2007年S1期
3 高海昌;馮博琴;侯蕓;朱利;;自適應(yīng)變異的混合粒子群優(yōu)化策略及其應(yīng)用[J];西安交通大學(xué)學(xué)報(bào);2006年06期
4 韓俊英;劉成忠;;自適應(yīng)變異的果蠅優(yōu)化算法[J];計(jì)算機(jī)應(yīng)用研究;2013年09期
5 劉悅婷;;帶有選擇和自適應(yīng)變異機(jī)制的混合蛙跳算法[J];計(jì)算機(jī)工程;2012年23期
6 陳世明;江冀海;鄭麗楠;聶森;;基于自適應(yīng)變異粒子群優(yōu)化算法的移動(dòng)機(jī)器人路徑規(guī)劃[J];機(jī)床與液壓;2010年23期
7 朱永利;陳英偉;韓凱;王磊;;基于熵的自適應(yīng)變異的粒子群優(yōu)化算法[J];信息化縱橫;2009年10期
8 樸昌浩;王進(jìn);孫志華;湯彬彬;;自適應(yīng)變異比率控制在虛擬可重構(gòu)結(jié)構(gòu)中的應(yīng)用[J];高技術(shù)通訊;2010年04期
9 張陸游;張永順;楊云;;基于混沌自適應(yīng)變異粒子群優(yōu)化的解相干算法[J];電子與信息學(xué)報(bào);2009年08期
10 陽(yáng)春華;谷麗姍;桂衛(wèi)華;;自適應(yīng)變異的粒子群優(yōu)化算法[J];計(jì)算機(jī)工程;2008年16期
相關(guān)會(huì)議論文 前2條
1 易燕;周暉;肖琦;;自適應(yīng)變異參數(shù)控制硬件進(jìn)化[A];第六屆全國(guó)信息獲取與處理學(xué)術(shù)會(huì)議論文集(3)[C];2008年
2 高憲文;張大勇;;熵極大自適應(yīng)變異粒子群優(yōu)化算法及其應(yīng)用[A];2007中國(guó)控制與決策學(xué)術(shù)年會(huì)論文集[C];2007年
相關(guān)碩士學(xué)位論文 前1條
1 靳文輝;自適應(yīng)變異量子粒子群優(yōu)化算法及其應(yīng)用研究[D];江南大學(xué);2008年
,本文編號(hào):2199527
本文鏈接:http://sikaile.net/kejilunwen/zidonghuakongzhilunwen/2199527.html