Human action recognition is a key component in modern artificial intelligent systems, such as sport analysis, video surveillance and human–computer interaction (HCI). Existing action recognition algorithms mainly depend on a predefined spatial sequence code book, which may fail to discover discriminative spatial–temporal features. In this paper, we propose to engineer the spatial–temporal action features that can deeply encode the similarity of within-class human actions and dissimilarity of between-class human actions. Specifically, given a series of training action video samples, we first segment each video into multiple key sections based on human contour. These sections of a video are related to time and space. Then, local human action and appearance information are combined to represent each video section. We quantize these extracted features into a feature vector, which can represent category-specific human actions. Subsequently, we develop an improved linear discriminative analysis to project the data points to a subspace, where data points with the same label are close while data points with different labels are far from each other. Experimental results on HMDB51 and KTH datasets have shown the effectiveness and robustness of our method. Moreover, the recognized human action sequence can guide the operation of robots in industrial area.

人体动作识别是现代人工智能系统中的重要组成部分，例如运动分析，视频监视和人机交互（HCI）。现有的动作识别算法主要依赖于预定义的空间序列码本，这可能无法发现具有区别性的时空特征。在本文中，我们建议对时空行为特征进行工程设计，以深度编码类内人类行为的相似性和类间人类行为的相似性。具体来说，给定一系列训练动作视频样本，我们首先根据人的轮廓将每个视频划分为多个关键部分。视频的这些部分与时间和空间有关。然后，将本地人的动作和外观信息组合起来以表示每个视频部分。我们将这些提取的特征量化为一个特征向量，该向量可以表示特定类别的人类行为。随后，我们开发了一种改进的线性判别分析，以将数据点投影到子空间中，在该子空间中，具有相同标签的数据点彼此靠近，而具有不同标签的数据点彼此远离。在HMDB51和KTH数据集上的实验结果表明了该方法的有效性和鲁棒性。此外，公认的人为动作顺序可以指导工业领域的机器人操作。在HMDB51和KTH数据集上的实验结果表明了该方法的有效性和鲁棒性。此外，公认的人为动作顺序可以指导工业领域的机器人操作。在HMDB51和KTH数据集上的实验结果表明了该方法的有效性和鲁棒性。此外，公认的人为动作顺序可以指导工业领域的机器人操作。