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You Tube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。
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.
出处
《国防科技大学学报》
EI
CAS
CSCD
北大核心
2016年第2期68-74,共7页
Journal of National University of Defense Technology
基金
国家863计划资助项目(2009AA11Z205)
国家自然科学基金资助项目(50808025)
关键词
行为识别
词表压缩
信息瓶颈算法
生成模型
behavior recognition
vocabulary compression
agglomerative information bottleneck
generative model
