A Robust Approach for Action Recognition Based on Spatio-Temporal Features in RGB-D Sequences
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2016, Vol 7, Issue 5
Abstract
Recognizing human action is attractive research topic in computer vision since it plays an important role on the applications such as human-computer interaction, intelligent surveillance, human actions retrieval system, health care, smart home, robotics and so on. The availability the low-cost Microsoft Kinect sensor, which can capture real-time high-resolution RGB and visual depth information, has opened an opportunity to significantly increase the capabilities of many automated vision based recognition tasks. In this paper, we propose new framework for action recognition in RGB-D video. We extract spatiotemporal features from RGB-D data that capture both visual, shape and motion information. Moreover, the segmentation technique is applied to present the temporal structure of action. Firstly, we use STIP to detect interest points both of RGB and depth channels. Secondly, we apply HOG3D descriptor for RGB channel and 3DS-HONV descriptor for depth channel. In addition, we also extract HOF2.5D from fusing RGB and Depth to capture human’s motion. Thirdly, we divide the video into segments and apply GMM to create feature vectors for each segment. So, we have three feature vectors (HOG3D, 3DS-HONV, and HOF2.5D) that represent for each segment. Next, the max pooling technique is applied to create a final vector for each descriptor. Then, we concatenate the feature vectors from the previous step into the final vector for action representation. Lastly, we use SVM method for classification step. We evaluated our proposed method on three benchmark datasets to demonstrate generalizability. And, the experimental results shown to be more accurate for action recognition compared to the previous works. We obtain overall accuracies of 93.5%, 99.16% and 89.38% with our proposed method on the UTKinect-Action, 3D Action Pairs and MSR-Daily Activity 3D dataset, respectively. These results show that our method is feasible and superior performance over the-state-of-the-art methods on these datasets.
Authors and Affiliations
Ly Ngoc, Vo Viet, Tran Son, Pham Hoang
Keywords
Related Articles
- EP ID EP118000
- DOI 10.14569/IJACSA.2016.070526
- Views 108
- Downloads 0
Quizzes: Quiz Application Development Using Android-Based MIT APP Inventor Platform
This work deals with the development of Android-based multiple-choice question examination system, namely: Quizzes. This application is developed for educational purposes, allowing the users to prepare the multiple choic...
Negotiation as a Collaborative Tool for Determining Permissions and Detection of Malicious Applications
In Android OS users find it very difficult to understand and comprehend its permission mechanism. Frequently, users tend to ignore permission negotiations dialogs during installation of an application. Users, who pay att...
Skill Evaluation for Newly Graduated Students Via Online Test
Every year in each university many students are graduated holding a first university degree. For example Bachelor degree in Computer Science. Most of those students have a motivation to continue with further studies to g...
WordNet based Implicit Aspect Sentiment Analysis for Crime Identification from Twitter
Crime analysis has become an interesting field that deals with serious public safety issues recognized around the world. Today, investigating Twitter Sentiment Analysis (SA) is a continuing concern within this field. Asp...
Continuous Path Planning of Kinematically Redundant Manipulator using Particle Swarm Optimization
This paper addresses a problem of a continuous path planning of a redundant manipulator where an end-effector needs to follow a desired path. Based on a geometrical analysis, feasible postures of a self-motion are mapped...