Online Action Recognition via Nonparametric Incremental Learning
Online Action Recognition via Nonparametric Incremental Learning
复制标题
DOI：
10.5244/c.28.113
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
R. D. Rosa;Nicolò Cesa-Bianchi;I. Gori;Fabio Cuzzolin
中科院分区：
文献类型：
--
作者：
R. D. Rosa;Nicolò Cesa-Bianchi;I. Gori;Fabio Cuzzolin
我们介绍了一个在线动作识别系统，可以与任何一组逐帧特征描述符相结合。我们的系统覆盖的框架特征空间与分类器，其分布适应局部逼近贝叶斯最优分类器的硬度。一个有效的最近邻搜索被用来找到和联合收割机的本地分类器，最接近的一个新的视频被分类的帧。我们的方法的优点是：增量训练，逐帧实时预测，非参数预测建模，用于连续动作识别的视频分割，无需将视频修剪为相等长度，并且只有一个调整参数（对于大型数据集，可以安全地设置为特征空间的直径）。标准基准测试的实验表明，我们的系统是有竞争力的最先进的非增量和增量基线。保留字：动作识别，增量学习，连续动作识别，非参数模型，真实的时间，多变量时间序列分类，时态分类
We introduce an online action recognition system that can be combined with any set of frame-by-frame feature descriptors. Our system covers the frame feature space with classifiers whose distribution adapts to the hardness of locally approximating the Bayes optimal classifier. An efficient nearest neighbour search is used to find and combine the local classifiers that are closest to the frames of a new video to be classified. The advantages of our approach are: incremental training, frame by frame real-time prediction, nonparametric predictive modelling, video segmentation for continuous action recognition, no need to trim videos to equal lengths and only one tuning parameter (which, for large datasets, can be safely set to the diameter of the feature space). Experiments on standard benchmarks show that our system is competitive with state-of-the-art nonincremental and incremental baselines. keywords: action recognition, incremental learning, continuous action recognition, nonparametric model, real time, multivariate time series classification, temporal classification