DCSE, CEG-Anna University, Guindy, Chennai, India.
RCC, CEG-Anna University, Guindy, Chennai, India.
Comput Intell Neurosci. 2020 Sep 10;2020:8852404. doi: 10.1155/2020/8852404. eCollection 2020.
Human action recognition is a trending topic in the field of computer vision and its allied fields. The goal of human action recognition is to identify any human action that takes place in an image or a video dataset. For instance, the actions include walking, running, jumping, throwing, and much more. Existing human action recognition techniques have their own set of limitations when it concerns model accuracy and flexibility. To overcome these limitations, deep learning technologies were implemented. In the deep learning approach, a model learns by itself to improve its recognition accuracy and avoids problems such as gradient eruption, overfitting, and underfitting. In this paper, we propose a novel parameter initialization technique using the Maxout activation function. Firstly, human action is detected and tracked from the video dataset to learn the spatial-temporal features. Secondly, the extracted feature descriptors are trained using the RBM-NN. Thirdly, the local features are encoded into global features using an integrated forward and backward propagation process via RBM-NN. Finally, an SVM classifier recognizes the human actions in the video dataset. The experimental analysis performed on various benchmark datasets showed an improved recognition rate when compared to other state-of-the-art learning models.
人体动作识别是计算机视觉及其相关领域的一个热门话题。人体动作识别的目标是识别图像或视频数据集中发生的任何人体动作。例如，这些动作包括行走、跑步、跳跃、投掷等等。现有的人体动作识别技术在模型准确性和灵活性方面都存在自身的局限性。为了克服这些局限性，人们采用了深度学习技术。在深度学习方法中，模型通过自我学习来提高识别准确性，并避免了梯度爆炸、过拟合和欠拟合等问题。在本文中，我们提出了一种新的参数初始化技术，使用 Maxout 激活函数。首先，从视频数据集中检测和跟踪人体动作，以学习时空特征。其次，使用 RBM-NN 对提取的特征描述符进行训练。然后，通过 RBM-NN 的正向和反向传播过程，将局部特征编码为全局特征。最后，使用 SVM 分类器识别视频数据集中的人体动作。在各种基准数据集上进行的实验分析表明，与其他最先进的学习模型相比，识别率得到了提高。
