Fusing directional wavelet local binary pattern and moments for human action recognition

• Published in: IET computer vision 2016-03, Vol.10 (2), p.153-162
• Main Authors: Al-Berry, Maryam Nabil, Salem, Mohammed A.-M, Ebeid, Hala Mousher, Hussein, Ashraf S, Tolba, Mohammed F
• Format: Article
• Language: English
• Subjects: 3D stationary wavelet transform; Computer vision; directional global feature fusion; directional wavelet local binary moment fusion; directional wavelet local binary pattern fusion; dynamic background; feature extraction; feature vector; gesture recognition; global descriptor; Hu invariant moment fusion; human action recognition; human action representation; Illumination; image fusion; image representation; Invariants; Lighting; local descriptor; local feature fusion; Moving object recognition; Representations; scale variations; State of the art; transformation-based method; voting scheme; Wavelet transforms
• ISSN: 1751-9632; 1751-9640; 1751-9640
• DOI: 10.1049/iet-cvi.2015.0087

Recently, transformation-based methods have been widely used in many computer vision areas because of their powerful representation ability. One of the most widely used transforms is the wavelet transform that has proved to be very useful in many applications. In this study, a new method for human action representation and description is proposed. This method combines the advantages of local and global descriptions. The method works by fusing the Hu invariant moments as global descriptors with a new local descriptor that is based on three-dimensional stationary wavelet transform and the concept of local binary patterns. The performance of the new method was examined in two different ways. The first one is by fusing the proposed directional global and local features in one feature vector, while the other is using the features of different directional bands separately to train multiple classifiers and then using a voting scheme to vote for the best match. The performance of the proposed method is verified using standard datasets, achieving high accuracy in comparison with state-of-the-art methods. In addition, the proposed method is proved to be robust to the changes in lighting and scale variations, but it exhibits limitations towards dynamic backgrounds.