Action recognition using fast HOG3D of integral videos and Smith–Waterman partial matching. Issue 6 (1st June 2018)

• Record Type: Journal Article
• Authors: El‐Henawy, Ibrahim; Ahmed, Kareem; Mahmoud, Hamdi
• Is Part Of: IET image processing. Volume 12:Issue 6(2018)
• Page Start: 896
• Page End: 908
• Publication Date: 2018-06-01
• Subjects: image matching -- image fusion -- support vector machines -- decision trees -- image classification -- feature extraction; fast HOG3D feature classification -- integral videos -- human activity recognition -- video stream -- computer vision -- human action recognition -- Smith‐Waterman partial shape matching -- frame fusion -- 3D gradient orientation -- spatiotemporal volumetric data -- nonlinear support vector machine decision tree -- nonlinear SVM decision tree; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2016.0627
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Recognising human activity from video stream has become one of the most interesting applications in computer vision. In this study, a novel hybrid technique for human action recognition is proposed based on fast HOG3D of integral videos and Smith–Waterman partial shape matching of the fused frame. The proposed technique is divided into two main stages, the first stage extracts a set of foreground snippets from the input video, and extracts the histogram of 3D gradient orientations from the spatio‐temporal volumetric data; and the second stage fuses a set of key frames from current snippet and extracts the contours from the fused frame. Non‐linear support vector machine (SVM) decision trees are used to classify HOG3D features into one of fixed action categories. On the other hand, Smith–Waterman partial shape matching is used to compare between the contour of the fused frame and the stored template contour of specified action. The results from SVM and Smith–Waterman partial shape matching are then combined. The experimental results show that combining non‐linear SVM decision trees of HOG3D features and Smith–Waterman partial shape matching of fused contours improved the accuracy of the classification model while maintaining efficiency in time elapsed for training.