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.

Video Surveillance plays a pivotal role in today's world. The technologies have been advanced too much when artificial intelligence, machine learning and deep learning pitched into the system. Using above combinations, different systems are in place which helps to differentiate various suspicious behaviors from the live tracking of footages. The most unpredictable one is human behaviour and it is very difficult to find whether it is suspicious or normal. Deep learning approach is used to detect suspicious or normal activity in an academic environment, and which sends an alert message to the corresponding authority, in case of predicting a suspicious activity. Monitoring is often performed through consecutive frames which are extracted from the video. The entire framework is divided into two parts. In the first part, the features are computed from video frames and in second part, based on the obtained features classifier predict the class as suspicious or normal.

This paper proposes a method for detecting anomalies in video data. A Variational Autoencoder (VAE) is used for reducing the dimensionality of video frames, generating latent space information that is comparable to low-dimensional sensory data (e.g., positioning, steering angle), making feasible the development of a consistent multi-modal architecture for autonomous vehicles. An Adapted Markov Jump Particle Filter defined by discrete and continuous inference levels is employed to predict the following frames and detecting anomalies in new video sequences. Our method is evaluated on different video scenarios where a semi-autonomous vehicle performs a set of tasks in a closed environment.

The growing demand for safety in urban environments is supported by monitoring using video surveillance. The need to analyze multiple video-flows from different cameras deployed around the city by heterogeneous owners introduces vulnerabilities and privacy issues. Video frames, timestamps, and camera settings can be digitally manipulated by malicious users; the positions of cameras, their orientation and their mechanical settings can be physically manipulated. Digital and physical manipulations may have several effects, including the change of the observed scene and the potential violation of neighbors' privacy. To face these risks, we introduce BlockSee, a blockchain-based video surveillance system that jointly provides validation and immutability to camera settings and surveillance videos, making them readily available to authorized users in case of events. The encouraging results obtained with BlockSee pave the way to new distributed city-wide monitoring systems.

Deep learning has undergone tremendous advancements in computer vision studies. The training of deep learning neural networks depends on a considerable amount of ground truth datasets. However, labeling ground truth data is a labor-intensive task, particularly for large-volume video analytics applications such as video surveillance and vehicles detection for autonomous driving. This paper presents a rapid and accurate method for associative searching in big image data obtained from security monitoring systems. We developed a semi-automatic moving object annotation method for improving deep learning models. The proposed method comprises three stages, namely automatic foreground object extraction, object annotation in subsequent video frames, and dataset construction using human-in-the-loop quick selection. Furthermore, the proposed method expedites dataset collection and ground truth annotation processes. In contrast to data augmentation and data generative models, the proposed method produces a large amount of real data, which may facilitate training results and avoid adverse effects engendered by artifactual data. We applied the constructed annotation dataset to train a deep learning you-only-look-once (YOLO) model to perform vehicle detection on street intersection surveillance videos. Experimental results demonstrated that the accurate detection performance was improved from a mean average precision (mAP) of 83.99 to 88.03.

An abnormal behavior detection algorithm for surveillance is required to correctly identify the targets as being in a normal or chaotic movement. A model is developed here for this purpose. The uniqueness of this algorithm is the use of foreground detection with Gaussian mixture (FGMM) model before passing the video frames to optical flow model using Lucas-Kanade approach. Information of horizontal and vertical displacements and directions associated with each pixel for object of interest is extracted. These features are then fed to feed forward neural network for classification and simulation. The study is being conducted on the real time videos and some synthesized videos. Accuracy of method has been calculated by using the performance parameters for Neural Networks. In comparison of plain optical flow with this model, improved results have been obtained without noise. Classes are correctly identified with an overall performance equal to 3.4e-02 with & error percentage of 2.5.

We propose a method for analysis of surveillance video by using low rank and sparse decomposition (LRSD) with low latency combined with compressive sensing to segment the background and extract moving objects in a surveillance video. Video is acquired by compressive measurements, and the measurements are used to analyze the video by a low rank and sparse decomposition of a matrix. The low rank component represents the background, and the sparse component, which is obtained in a tight wavelet frame domain, is used to identify moving objects in the surveillance video. An important feature of the proposed low latency method is that the decomposition can be performed with a small number of video frames, which reduces latency in the reconstruction and makes it possible for real time processing of surveillance video. The low latency method is both justified theoretically and validated experimentally.