In the recent past, human action recognition is inviting increased attention in the automated video surveillance systems. An efficient human action classification technique in an unconstrained environment is proposed in this paper. A novel descriptor relying on joint entropy of difference in magnitude and orientation of the optical flow feature is developed in order to model human actions. Initially, flow feature is computed using Pyramid–Warping–Cost volume Network (PWCNet), considering every two consecutive frames. Then, the feature descriptor is formed based on the joint entropy of difference in flow magnitude and orientation collected from the regular grid of each frame in the action sequence. Finally, in order to incorporate long-term temporal dependency, a spiking neural network is embedded to aggregate the information across the frames. Different optimization techniques and different types of hidden nodes are utilized in the spiking neural network to analyze the performance of the proposed work. Extensive experiments on the benchmark datasets for human action recognition show the efficacy of the proposed method.

在最近的过去中，人类动作识别正在自动视频监视系统中引起越来越多的关注。提出了一种在不受约束的环境中有效的人类行为分类技术。为了模拟人类行为，开发了一种新颖的描述符，该描述符依赖于光流特征的大小和方向差异的联合熵。最初，考虑到每两个连续的帧，使用金字塔-翘曲-成本体积网络（PWCNet）计算流量特征。然后，基于从动作序列中的每个帧的规则网格收集的流大小和方向的差异的联合熵来形成特征描述符。最后，为了合并长期的时间依赖性，嵌入了尖峰神经网络以跨帧聚合信息。尖峰神经网络中使用了不同的优化技术和不同类型的隐藏节点来分析所提出工作的性能。在用于人类动作识别的基准数据集上的大量实验证明了该方法的有效性。