Action recognition based on motion of oriented magnitude patterns and feature selection

作者：Hai Hong Phan^*; Ngoc Son Vu; Vu Lam Nguyen; Quoy Mathias

来源：IET Computer Vision, 2018, 12(5): 735-743.

DOI：10.1049/iet-cvi.2017.0282

• object recognition
• image motion analysis
• feature selection
• support vector machines
• principal component analysis
• image sequences
• image classification
• action recognition
• motion-of-oriented magnitude patterns descriptor
• MOMP descriptor decorrelation
• feature selection
• local gradient distributions
• consecutive image sequences
• information changing
• feature post-processing principal component analysis
• aggregated descriptors encoding
• statistical dependency
• HMDB51 data set

Here, the authors introduce a novel system which incorporates the discriminative motion of oriented magnitude patterns (MOMP) descriptor into simple yet efficient techniques. The authors' descriptor both investigates the relations of the local gradient distributions in neighbours among consecutive image sequences and characterises information changing across different orientations. The proposed system has two main contributions: (i) the authors adopt feature post-processing principal component analysis followed by vector of locally aggregated descriptors encoding to de-correlate MOMP descriptor and reduce the dimension in order to speed up the algorithm; (ii) then the authors include the feature selection (i.e. statistical dependency, mutual information, and minimal redundancy maximal relevance) to find out the best feature subset to improve the performance and decrease the computational expense in classification through support vector machine techniques. Experiment results on four data sets, Weizmann (98.4%), KTH (96.3%), UCF Sport (82.0%), and HMDB51 (31.5%), prove the efficiency of the authors' algorithm.

• 出版日期2018-8