引用本文: | 王军,夏利民,夏胜平.利用生成模型的人体行为识别[J].国防科技大学学报,2016,38(2):68-74.[点击复制] |
WANG Jun,XIA Limin,XIA Shengping.Human behavior recognition using generative model[J].Journal of National University of Defense Technology,2016,38(2):68-74[点击复制] |
|
|
|
本文已被:浏览 8001次 下载 6368次 |
利用生成模型的人体行为识别 |
王军1,2, 夏利民3,4, 夏胜平5 |
(1. 电子科技大学中山学院 机电工程学院, 广东 中山 528402;2.
2. 中南大学 信息科学与工程学院, 湖南 长沙 410075;3.2. 中南大学 信息科学与工程学院, 湖南 长沙 410075;4.;5.3. 国防科技大学 自动目标识别国家重点实验室, 湖南 长沙 410073)
|
摘要: |
选取关键点轨迹的方向-大小描述符、轨迹形状描述符、外观描述符作为人体行为的特征;为了降低人体行为特征维数,利用信息瓶颈算法进行词表压缩;利用生成模型,结合已标记样本和未标记样本提出一种人体行为识别的半监督学习方法,解决了行为识别中的小样本问题。在YouTube 数据库、 中佛罗里达大学运动数据库上利用提出的方法与已有的方法进行对比实验,结果表明该方法具有更高的识别精度。 |
关键词: 行为识别 词表压缩 信息瓶颈算法 生成模型 |
DOI:10.11887/j.cn.201602012 |
投稿日期:2015-05-31 |
基金项目:国家863计划资助项目(2009AA11Z205);国家自然科学基金资助项目(50808025) |
|
Human behavior recognition using generative model |
(1. College of Mechanical and Electrical Engineering, University of Electronics Science and Technology, Zhongshan Institute, Zhongshan 528402, China;2. School of Information Science and Engineering, Central South University, Changsha 410075, China;3. National Key Laboratory of ATR, National University of Defense Technology, Changsha 410073, China)
|
Abstract: |
A novel method based on generative model was proposed for human behavior recognition. The behavior was represented by using a set of descriptors computed from key point trajectories, which included the orientation magnitude descriptor, the trajectory shape descriptor and the appearance descriptor. In order to reduce feature dimensions, the agglomerative information bottleneck approach was used for vocabulary compression. The semi-supervised learning method for behavior recognition based on generative model was proposed to solve the problem of small sample in recognition, which made use of both the labeled and unlabeled samples. Compared with other state-of-the-art methods in both UCF sports database and YouTube database, results show that the proposed method has higher recognition accuracy. |
Keywords: behavior recognition vocabulary compression agglomerative information bottleneck generative model |
|
|
|
|
|