本文選題：人體姿態(tài)估計 + 混合部件模型　； 參考：《光學精密工程》2017年04期

【摘要】：基于混合部件模型的人體姿態(tài)估計方法忽視了人體結構的對稱位姿約束關系,從而導致對稱部件容易被重復檢測、人體姿態(tài)估計準確率較低,為此,提出一種基于位姿約束與軌跡尋優(yōu)的姿態(tài)估計新方法。首先估計人體單部件和對稱部件在單幀圖像中的多個合理位置,利用對稱部件之間的位姿約束關系構建標識部件。然后根據(jù)單部件和標識部件各自的目標優(yōu)化函數(shù),通過動態(tài)規(guī)劃算法反復迭代獲得初始軌跡候選集,再結合軌跡的全局特征剔除檢測得分較低的運動軌跡。最后引入樹形合約模型,聯(lián)系時空上下文信息,準確求解出視頻序列光滑且兼容的最優(yōu)軌跡。在N-best、Outdoor Pose和Scene數(shù)據(jù)集中的實驗結果表明,對于存在背景復雜、運動模糊、部件遮擋等問題的視頻序列中,該方法平均姿態(tài)估計準確率達87%以上,有效減少了對稱部件的誤判,提高了視頻中人體姿態(tài)估計的準確率。
[Abstract]:The method of human body attitude estimation based on hybrid component model neglects the symmetrical pose constraint relation of human body structure, which leads to the symmetry component being easily detected repeatedly, and the accuracy of human body attitude estimation is low. A new attitude estimation method based on pose constraint and trajectory optimization is proposed. Firstly, the reasonable position of human body single component and symmetrical component in a single frame image is estimated, and the identification components are constructed by using the pose constraint relationship between symmetric components. Then according to the objective optimization function of the single component and the marking component, the initial trajectory candidate set is iterated through dynamic programming algorithm, and then the motion track with low score is eliminated by combining the global feature of the trajectory. Finally, a tree contract model is introduced to accurately solve the smooth and compatible optimal trajectory of video sequences with temporal and spatial context information. The experimental results in N-best outdoor Pose and Scene data sets show that for video sequences with complex background, motion blur and component occlusion, the average attitude estimation accuracy of this method is over 87%, which effectively reduces the misjudgment of symmetric components. The accuracy of human pose estimation in video is improved.
【作者單位】： 河海大學物聯(lián)網(wǎng)工程學院;常州市傳感網(wǎng)與環(huán)境感知重點實驗室;
【基金】：國家自然科學基金(41301448) 江蘇省重點研發(fā)計劃(BE2016071)
【分類號】：TP391.41

【相似文獻】

相關期刊論文 前10條

1 韓貴金;朱虹;;一種基于圖結構模型的人體姿態(tài)估計算法[J];計算機工程與應用;2013年14期

2 王浩;劉則芬;方寶富;陳金金;;基于約束樹形圖結構外觀模型的人體姿態(tài)估計[J];計算機科學;2014年03期

3 蘇延超;艾海舟;勞世z，

本文編號：1991223