Biblio

Human action recognition in video is one of the most widely applied topics in the field of image and video processing, with many applications in surveillance (security, sports, etc.), activity detection, video-content-based monitoring, man-machine interaction, and health/disability care. Action recognition is a complex process that faces several challenges such as occlusion, camera movement, viewpoint move, background clutter, and brightness variation. In this study, we propose a novel human action recognition method using convolutional neural networks (CNN) and deep bidirectional LSTM (DB-LSTM) networks, using only raw video frames. First, deep features are extracted from video frames using a pre-trained CNN architecture called ResNet152. The sequential information of the frames is then learned using the DB-LSTM network, where multiple layers are stacked together in both forward and backward passes of DB-LSTM, to increase depth. The evaluation results of the proposed method using PyTorch, compared to the state-of-the-art methods, show a considerable increase in the efficiency of action recognition on the UCF 101 dataset, reaching 95% recognition accuracy. The choice of the CNN architecture, proper tuning of input parameters, and techniques such as data augmentation contribute to the accuracy boost in this study.

We investigate a deep learning model for action recognition that simultaneously extracts spatio-temporal information from a raw RGB input data. The proposed multiple spatio-temporal scales recurrent neural network (MSTRNN) model is derived by combining multiple timescale recurrent dynamics with a conventional convolutional neural network model. The architecture of the proposed model imposes both spatial and temporal constraints simultaneously on its neural activities. The constraints vary, with multiple scales in different layers. As suggested by the principle of upward and downward causation, it is assumed that the network can develop a functional hierarchy using its constraints during training. To evaluate and observe the characteristics of the proposed model, we use three human action datasets consisting of different primitive actions and different compositionality levels. The performance capabilities of the MSTRNN model on these datasets are compared with those of other representative deep learning models used in the field. The results show that the MSTRNN outperforms baseline models while using fewer parameters. The characteristics of the proposed model are observed by analyzing its internal representation properties. The analysis clarifies how the spatio-temporal constraints of the MSTRNN model aid in how it extracts critical spatio-temporal information relevant to its given tasks.

For an action recognition system a decisive component is represented by the feature encoding part which builds the final representation that serves as input to a classifier. One of the shortcomings of the existing encoding approaches is the fact that they are built around hand-crafted features and they are not also highly competitive on encoding the current deep features, necessary in many practical scenarios. In this work we propose two solutions specifically designed for encoding local deep features, taking advantage of the nature of deep networks, focusing on capturing the highest feature response of the convolutional maps. The proposed approaches for deep feature encoding provide a solution to encapsulate the features extracted with a convolutional neural network over the entire video. In terms of accuracy our encodings outperform by a large margin the current most widely used and powerful encoding approaches, while being extremely efficient for the computational cost. Evaluated in the context of action recognition tasks, our pipeline obtains state-of-the-art results on three challenging datasets: HMDB51, UCF50 and UCF101.

The world is witnessing a remarkable increase in the usage of video surveillance systems. Besides fulfilling an imperative security and safety purpose, it also contributes towards operations monitoring, hazard detection and facility management in industry/smart factory settings. Most existing surveillance techniques use hand-crafted features analyzed using standard machine learning pipelines for action recognition and event detection. A key shortcoming of such techniques is the inability to learn from unlabeled video streams. The entire video stream is unlabeled when the requirement is to detect irregular, unforeseen and abnormal behaviors, anomalies. Recent developments in intelligent high-level video analysis have been successful in identifying individual elements in a video frame. However, the detection of anomalies in an entire video feed requires incremental and unsupervised machine learning. This paper presents a novel approach that incorporates high-level video analysis outcomes with incremental knowledge acquisition and self-learning for autonomous video surveillance. The proposed approach is capable of detecting changes that occur over time and separating irregularities from re-occurrences, without the prerequisite of a labeled dataset. We demonstrate the proposed approach using a benchmark video dataset and the results confirm its validity and usability for autonomous video surveillance.

Spatial-multiplexing cameras have emerged as a promising alternative to classical imaging devices, often enabling acquisition of `more for less'. One popular architecture for spatial multiplexing is the single-pixel camera (SPC), which acquires coded measurements of the scene with pseudo-random spatial masks. Significant theoretical developments over the past few years provide a means for reconstruction of the original imagery from coded measurements at sub-Nyquist sampling rates. Yet, accurate reconstruction generally requires high measurement rates and high signal-to-noise ratios. In this paper, we enquire if one can perform high-level visual inference problems (e.g. face recognition or action recognition) from compressive cameras without the need for image reconstruction. This is an interesting question since in many practical scenarios, our goals extend beyond image reconstruction. However, most inference tasks often require non-linear features and it is not clear how to extract such features directly from compressed measurements. In this paper, we show that one can extract nontrivial correlational features directly without reconstruction of the imagery. As a specific example, we consider the problem of face recognition beyond the visible spectrum e.g in the short-wave infra-red region (SWIR) - where pixels are expensive. We base our framework on smashed filters which suggests that inner-products between high-dimensional signals can be computed in the compressive domain to a high degree of accuracy. We collect a new face image dataset of 30 subjects, obtained using an SPC. Using face recognition as an example, we show that one can indeed perform reconstruction-free inference with a very small loss of accuracy at very high compression ratios of 100 and more.