Nowadays, enhancing the living standard with smart healthcare via Internet of Thing is one of the most critical goals of smart cities, in which Artificial Intelligence plays as the core technology. Many smart services, deployed according to wearable sensor-based physical activity (PA) recognition, have been able to early detect unhealthy daily behaviors and further medical risks. Numerous approaches have studied shallow handcrafted features coupled with traditional machine learning (ML) techniques, which find it difficult to model real-world activities. In this work, by revealing deep features from Deep Convolutional Neural Networks (DCNNs) in the fusion with conventional handcrafted features, we learn an intermediate fusion framework of human activity recognition (HAR). According to transforming raw signal value to pixel intensity value, a segmentation data acquired from a multi-sensor system is encoded to an activity image for deep model learning. Formulated by several novel Residual Triple-Convolutional blocks, the proposed DCNN allows extracting multi-scale spatiotemporal signal-and sensor-level correlations simultaneously from the activity image. In the fusion model, the hybrid feature merged from the handcrafted and deep features is learned by a multiclass Support Vector Machine (SVM) classifier. Based on several experiments of performance evaluation, our fusion approach for activity recognition has achieved the accuracy over 96.0% on three public benchmark datasets, including Daily and Sport Activities, Daily Life Activities, and RealWorld. Furthermore, the method outperforms several state-of-the-art HAR approaches and demonstrates the superiority of the proposed intermediate fusion model in multi-sensor systems.

Action recognition from videos is an important area of computer vision research due to its various applications, ranging from visual surveillance to human-computer interaction. To address action recognition problems, this paper presents a framework that jointly models multiple complex actions and motion units at different hierarchical levels. We achieve this by proposing a generative topic model, namely Multi-label Hierarchical Dirichlet Process (ML-HDP). The ML-HDP model formulates the co-occurrence relationship of actions and motion units, and enables highly accurate recognition. In particular, our topic model possesses the three-level representation in action understanding, where low-level local features are connected to high-level actions via mid-level atomic actions. This allows the recognition model to work discriminatively. In our ML-HDP, atomic actions are treated as latent topics and automatically discovered from data. In addition, we incorporate the notion of class labels into our model in a semi-supervised fashion to effectively learn and infer multi-labeled videos. Using discovered topics and inferred labels, which are jointly assigned to local features, we present the straightforward methods to perform three recognition tasks including: action classification, joint classification and segmentation of continuous actions, and spatiotemporal action localization. In experiments, we explore the use of three different features and demonstrate the effectiveness of our proposed approach for these tasks on four public datasets: KTH, MSR-II, Hollywood2, and UCF101.

In recent years, the amount of intelligent CCTV cameras installed in public places for surveillance has increased enormously and as a result, a large amount of video data is produced every moment. Due to this situation, there is an increasing request for the distributed processing of large-scale video data. In an intelligent video analytics platform, a submitted unstructured video undergoes through several multidisciplinary algorithms with the aim of extracting insights and making them searchable and understandable for both human and machine. Video analytics have applications ranging from surveillance to video content management. In this context, various industrial and scholarly solutions exist. However, most of the existing solutions rely on a traditional client/server framework to perform face and object recognition while lacking the support for more complex application scenarios. Furthermore, these frameworks are rarely handled in a scalable manner using distributed computing. Besides, existing works do not provide any support for low-level distributed video processing APIs (Application Programming Interfaces). They also failed to address a complete service-oriented ecosystem to meet the growing demands of consumers, researchers and developers. In order to overcome these issues, in this paper, we propose a distributed video analytics framework for intelligent video surveillance known as SIAT. The proposed framework is able to process both the real-time video streams and batch video analytics. Each real-time stream also corresponds to batch processing data. Hence, this work correlates with the symmetry concept. Furthermore, we introduce a distributed video processing library on top of Spark. SIAT exploits state-of-the-art distributed computing technologies with the aim to ensure scalability, effectiveness and fault-tolerance. Lastly, we implant and evaluate our proposed framework with the goal to authenticate our claims.