Faculty of Engineering and Technology, Multimedia University, Melaka, Malaysia.
Sci Prog. 2021 Apr-Jun;104(2):368504211005480. doi: 10.1177/00368504211005480.
Action recognition is a challenging time series classification task that has received much attention in the recent past due to its importance in critical applications, such as surveillance, visual behavior study, topic discovery, security, and content retrieval.
The main objective of the research is to develop a robust and high-performance human action recognition techniques. A combination of local and holistic feature extraction methods used through analyzing the most effective features to extract to reach the objective, followed by using simple and high-performance machine learning algorithms.
This paper presents three robust action recognition techniques based on a series of image analysis methods to detect activities in different scenes. The general scheme architecture consists of shot boundary detection, shot frame rate re-sampling, and compact feature vector extraction. This process is achieved by emphasizing variations and extracting strong patterns in feature vectors before classification.
The proposed schemes are tested on datasets with cluttered backgrounds, low- or high-resolution videos, different viewpoints, and different camera motion conditions, namely, the Hollywood-2, KTH, UCF11 (YouTube actions), and Weizmann datasets. The proposed schemes resulted in highly accurate video analysis results compared to those of other works based on four widely used datasets. The First, Second, and Third Schemes provides recognition accuracies of 57.8%, 73.6%, and 52.0% on Hollywood2, 94.5%, 97.0%, and 59.3% on KTH, 94.5%, 95.6%, and 94.2% on UCF11, and 98.9%, 97.8% and 100% on Weizmann.
Each of the proposed schemes provides high recognition accuracy compared to other state-of-art methods. Especially, the Second Scheme as it gives excellent comparable results to other benchmarked approaches.
动作识别是一项具有挑战性的时间序列分类任务，由于其在关键应用中的重要性，如监控、视觉行为研究、主题发现、安全和内容检索等，近年来受到了广泛关注。
本研究的主要目的是开发一种强大且高性能的人体动作识别技术。通过分析最有效的特征提取方法，结合局部和整体特征提取方法，以达到目标，然后使用简单且高性能的机器学习算法。
本文提出了三种基于一系列图像分析方法的鲁棒动作识别技术，用于检测不同场景中的活动。总体方案架构包括镜头边界检测、镜头帧率重采样和紧凑特征向量提取。通过强调特征向量中的变化并提取强模式来实现这一过程，然后再进行分类。
所提出的方案在具有杂乱背景、低分辨率或高分辨率视频、不同视角和不同相机运动条件的数据集上进行了测试，即 Hollywood-2、KTH、UCF11（YouTube 动作）和 Weizmann 数据集。与基于四个广泛使用的数据集的其他工作相比，所提出的方案在视频分析结果方面具有很高的准确性。第一、第二和第三方案在 Hollywood2 上的识别准确率分别为 57.8%、73.6%和 52.0%，在 KTH 上的识别准确率分别为 94.5%、97.0%和 59.3%，在 UCF11 上的识别准确率分别为 94.5%、95.6%和 94.2%，在 Weizmann 上的识别准确率分别为 98.9%、97.8%和 100%。
与其他最先进的方法相比，所提出的每个方案都提供了较高的识别准确率。特别是第二方案，因为它提供了与其他基准方法相当的结果。
