Recognition of Human Actions Based on Temporal Motion Templates

Identifying the human actions in unconfined videos is a difficult problem in several applications. The human action recognition is an active area of research. For this purpose the system proposes motion representation. In many proposed methods the motion pattern was avoided. So here these motion relationships which were discarded previously are now proposed. Identifying the actions in videos using motion scheme is been proposed. The video event representation used to recognize human activities is based on motion modeling. Dense local patch trajectories such as Histogram of Optical Flow (HOF), Histogram of Oriented Gradients (HOG) and Motion Boundary Histograms (MBH) areused in this approach which does not require the background foreground separation. The dimensions are reduced by Principal Components Analysis (PCA). The Support Vector Machine (SVM) is the classifier used for classification. The proposed video representation model is applied on the UT-Interaction dataset. The experimental results show that proposed representation produces a very competitive performance when compared with state-of-the-art methods and is more accurate.

Due to the growing use of human action recognition in every day life applications, it has become one of the very hot topics in image analysis and pattern recognition. This paper presents a new feature extraction method for human action recognition. The method is based on the extraction of Trace transforms from binarized silhouettes, representing different stages of a single action period. A final history template com-posed from the above transforms, represents the whole se-quence containing much of the valuable spatio-temporal in-formation contained in a human action. The new method takes advantage of the natural specifications of the specific Trace transform, such as noise robustness, translation invari-ance and scalability easiness and produces effective, simple and fast created features. Classification experiments performed on KTH action database using Radial Basis Function (RBF) Kernel SVM, provided very competitive results indicating the potentials of the proposed technique.

TheScientificWorldJournal, 2014

Recognition of human actions is an emerging need. Various researchers have endeavored to provide a solution to this problem. Some of the current state-of-the-art solutions are either inaccurate or computationally intensive while others require human intervention. In this paper a sufficiently accurate while computationally inexpensive solution is provided for the same problem. Image moments which are translation, rotation, and scale invariant are computed for a frame. A dynamic neural network is used to identify the patterns within the stream of image moments and hence recognize actions. Experiments show that the proposed model performs better than other competitive models.

Lecture Notes in Bioengineering, 2021

Human action recognition is a challenging area of research in the field of computer vision due to its complex analytical structure. Researches have been carried out in this field over the past few years. Now, as it has become possible to recognize human action successfully, the researchers are trying to make the recognition system real time in nature. But due to its complex video analysis, it has not been possible for the researchers to make it real time completely. Though some algorithms had been developed that will successfully recognize human action with the minimum delay possible in order to make the recognition system almost real time in nature. In this work, we have compared some of the successful human action recognition methodologies along with the recent trends to accomplish the task in negligible time delay.

Embedded Computer Vision, 2009

In this chapter, a compact human action recognition system is presented with a view to applications in security systems, human-computer interaction, and intelligent environments. There are three main contributions: Firstly, the framework of an embedded human action recognition system based on a support vector machine (SVM) classifier and some compact motion features has been presented. Secondly, the limitations of the well-known motion history image (MHI) are addressed and a new motion history histograms (MHH) feature is introduced to represent the motion information in the video. MHH not only provides rich motion information, but also remains computationally inexpensive. We combine MHI and MHH into a low-dimensional feature vector for the system and achieve improved performance in human action recognition over comparable methods that use tracking-free temporal template motion representations. Finally, a simple system based on SVM and MHI has been implemented on a reconfigurable embedded computer vision architecture for real-time gesture recognition.

2012

In this paper, we present an analysis of human motion that can assist the recognition of human actions irrespective of the selection of particular features. We begin with an analysis on the entire set of preclassified motions in order to derive the generic characteristics of articulated human motion and complement the analysis by a more detailed inter-class analysis. The statistical analysis concerns features that describe the significancecontribution of the human joints in performing an action. Furthermore, we adopt a hierarchical analysis on the human body itself in the study of different actions, by grouping joints that share common characteristics. We present our experiments on standard databases for human motion capture data as well as a new commercial dataset with additional classes of human motion and highlight certain interesting results.

… and Informatics (ICEEI), …, 2011

Human action recognition is gaining interest from many computer vision researchers because of its wide variety of potential applications. For instance: surveillance, advanced human computer interaction, content-based video retrieval, or athletic performance analysis. In this research, we focus to recognize some human actions such as waving, punching, clapping, etc. We choose exemplar-based sequential single-layered approach using Dynamic Time Warping (DTW) because of its robustness against variation in speed or style in performing action. For improving recognition rate, we perform body part tracking using depth camera to recover human joints body part information in 3D real world coordinate system. We build our feature vector from joint orientation along time series that invariant to human body size. Dynamic Time Warping is then applied to the resulted feature vector. We examine our approach to recognize several actions and we confirm our method can work well with several experiments. Further experiment for benchmarking the result will be held in near future.

Journal of Intelligent & Robotic Systems, 2007

This paper proposes a Qualitative Normalised Templates (QNTs) framework for solving the human motion classification problem. In contrast to other human motion classification methods which usually include a human model, prior knowledge on human motion and a matching algorithm, we replace the matching algorithm (e.g. template matching) with the proposed QNTs. The human motion is modelled by the time-varying joint angles and link lengths of an articulated human model. The ability to manage the trade-offs between model complexity and computational cost plays a crucial role in the performance of human motion classification. The QNTs is developed to categorise complex human motion into sets of fuzzy qualitative angles and positions in quantity space. Classification of the human motion is done by comparing the QNTs to the parameters learned from numerical motion tracking. Experimental results have demonstrated the effectiveness of our proposed method when classifying simple human motions, e.g. running and walking.

Lecture Notes in Computer Science, 2010

International Journal for Research in Applied Science and Engineering Technology, 2019

Human Action Recognition is one of the important research area in computer vision and image processing field. A machine can be interacted and controlled by gestures and facial expression using the visual modality. Human action recognition can be seen as a bridge for machines to understand human body language, an intelligent interacting system between machines and humans which limits majority of input devices such as keyboard and mouse. Thus, producing an accurate and meaningful information on human activities and behaviours is one of the important tasks in pervasive computing. In this survey, we tried to focus on advancement of action recognition after yr. 2010.