Recognition of human activities using a multiclass relevance vector machine

Abstract

We address the issue of human activity recognition by introducing the multiclass relevance vector machine (mRVM), the current state-of-the-art kernel machine learning technology given the multiclass classification problems (actually, activity recognition can commonly be viewed as a multiclass classification problem). Under our proposed recognition framework, the required procedure consists of three functional cascade modules: a. detecting the human silhouette blobs from the image sequence by the background subtraction method; b. extracting the shape and the motion features from the variation energy image (VEI); and c. sending the obtained features to the mRVM and recognizing the human activity. There are two types of mRVM: the constructive mRVM 1 and the top-down mRVM 2 . We performed 10 times three-fold crossvalidation on the Weizmann benchmark data set to examine the effectiveness of the proposed method. We also compared our method with other existing approaches, and the experimental results show that the proposed method offers superior performance. In summary, the mRVM, especially the mRVM 2 , has advantages both in terms of recognition rate and sparsity, along with a simple feature extraction process. The mRVM also significantly simplifies the classification process, by comparison with traditional binary-tree style multiclass classifiers. © 2012 Society of Photo-Optical Instrumentation Engineers (SPIE).

Human action recognition using motion energy template

“…17,28 The moment-based method provides a very useful analysis tool for HAR and obtains some satisfying results. 25 Intuitively, the method we proposed has a higher recognition rate than these state-of-the-art methods. This is mainly due to the following three reasons: (1) the MET model is more effective; (2) the Weizmann dataset is not challenging enough because of its single static scenario; and (3) SVM, which is based on statistical principle, is one of the most successful classification techniques.…”

“…The quantitative recognition performance and some state-of-the-art methods are shown in Table 1, such Shao, Guo, and Gao: Human action recognition using motion energy template as the variation energy image (VEI) model, 25 dynamic templates 19 and local motion pattern descriptors. 39 Table 1 shows that RVM has a higher recognition accuracy than SVM when based on a similar feature expression.…”

“…For instance, some methods may require background estimation, 6,25 noise reduction, period estimation, 25 object segmentation, human localization or tracking, 23 and so on. These pretreatments may not be conducive to automatically recognize action in real applications.…”

“…Heretofore, many famous pattern classification techniques [for instance, k-nearest neighbor, 10 probabilistic latent semantic analysis (pLSA), 26 neural network (NN, 17 SVM, 21,27 relevance vector machine (RVM), 25,28 and multiple kernel learning] 29 and their modifications have been proposed and employed in the action recognition field.…”

Position and locality constrained soft coding for human action recognition

“…Human action recognition [1][2][3] in videos has been widely studied over the last decade due to its widespread application prospects in areas such as human computer interaction, human motion analysis, video surveillance, video retrieval, and video content analysis. [4][5][6] However, it still remains a challenging problem because of some factors such as camera motion, cluttered background, occlusion, and varied object appearance.…”