Human action recognition using histogram of motion intensity and direction from multiple views

Abstract

This study presents a human action recognition system from multi‐view image sequences. The authors’ approach to human action recognition is based on an estimation of local motion from multiple camera views. The authors propose a new motion descriptor, called histogram of motion intensity and direction, to capture local motion characteristics of human activity. After image normalisation, they estimate motion flow using dense optical flow. Using regular grids, they extract local flow motion and estimate the dominant angle and the intensity of optical flow. The histogram of the dominant angle and its intensity are used as a descriptor for each sequence. After the identification of head direction, they concatenate descriptors in each view as a single feature vector from multiple‐view sequences. Classification based on the proposed feature vector using support vector machine shows better performance than three‐dimensional optical flow‐based approaches, but with lower computational requirements. The authors evaluated action recognition on the publicly available i3DPost and the Institut de Recherche en Informatique et en Automatique (INRIA) Xmas Motion Acquisition Sequences database. Experimental results show promising state‐of‐the‐art results and validate the advanced performance of the authors’ approach.

Human Action Recognition from Multiple Views Based on View-Invariant Feature Descriptor Using Support Vector Machines

“…The recognition rate of individual action is presented in a confusion matrix, shown in Figure 7. The results confirm that our method outperforms the similar state-of-the-art 2D based methods such as [12,19,21,24,29,[48][49][50][51][52] recorded in Table 2. It is important to be mentioned here that the number of classes, actors, and views used in experimentations vary among these methods.…”

“…This process is repeated for all possible combinations and results are averaged. This is a common strategy used by different researchers such as [19,29] for evaluation of their methods. This is helpful to compare our results with these state-of-the-art methods.…”

“…The change in orientation is indicated by action labels, and no additional information is provided other than these labels. Most of the existing methods use selected action classes and actors for experimentation [19,29]. For comparison, we have selected 11 action classes performed by 12 actors as shown in Figure 6.…”

A Comprehensive Review on Handcrafted and Learning-Based Action Representation Approaches for Human Activity Recognition

“…A novel motion descriptor was proposed in [93] for multi-view action representation. This motion descriptor is based on motion direction and histogram of motion intensity followed by the support vector machine for classification.…”

Learning a Mid-Level Representation for Multiview Action Recognition

“…Another group of methods resort to merging data from multiple views at feature level. These methods [12][13][14][15] utilize 3D or 2D models to build a discriminative representation of an action based on videos from multiple views. In fact, how to represent an action video with expressive features plays an especially important role in both multiview and singleview action recognition.…”