Search

Worldwide, many elders are suffering from Alzheimer's disease (AD). The elders with AD exhibit various abnormalities in their activities, such as sleep disturbances, wandering aimlessly, forgetting activities, etc., which are the strong signs and symptoms of AD progression. Recognizing these symptoms in advance could assist to a quicker diagnosis and treatment and to prevent the progression of Disease to the next stage. The proposed method aims to detect the behavioral abnormalities found in Daily activities of AD patients (ADP) using wearables. In the proposed work, a publicly available dataset collected using wearables is applied. Currently, no real-world data is available to illustrate the daily activities of ADP. Hence, the proposed method has synthesized the wearables data according to the abnormal activities of ADP. In the proposed work, multi-headed (MH) architectures such as MH Convolutional Neural Network-Long Short-Term Memory Network (CNN-LSTM), MH one-dimensional Convolutional Neural Network (1D-CNN) and MH two dimensional Convolutional Neural Network (2D-CNN) as well as conventional methods, namely CNN-LSTM, 1D-CNN, 2D-CNN have been implemented to model activity pattern. A multi-label prediction technique is applied to detect abnormal activities. The results obtained show that the proposed MH architectures achieve improved performance than the conventional methods. Moreover, the MH models for activity recognition perform better than the abnormality detection. [ABSTRACT FROM AUTHOR]

Remote monitoring is the process that monitors and observes information from a distance utilizing sensors or electronic types of equipment. Remote monitoring is used in real-time applications like traffic, forest, military, shops, and hospitals to determine abnormal activities. Earlier research has done video processing methods based on computer vision techniques, but the computational complexity regarding time and memory is high. This paper designs and implements a novel Slow-Fast Convolution Neural Network (SF–CNN) to identify, detect, and classify abnormal behaviours from a surveillance video. The proposed CNN architecture learns the video frames automatically, obtains the most appropriate properties about various objects' behaviour from a large set of videos. The learning process of SF-CNN is carried out in two ways, such as slow learning and fast learning. The slow learning process is enabled when the frame rate is less, and the rapid learning process is enabled when the frame rate is high. Both the learning processes learn spatial and temporal information from the input video. Different objects, such as humans, vehicles, and animals, are detected and recognized according to their actions. All the videos have normal and abnormal activities that vary in various contexts. The proposed SF-CNN architecture provides an end-to-end solution to dealing with multiple constraints abnormal movements. The experiment is carried out on several benchmark datasets, and the performance of the SF-CNN architecture is evaluated. The proposed approach obtained 99.6% of accuracy, which is higher than the other existing techniques.

Action recognition is an active research area in computer vision as it has enormous applications in today's world, out of which, recognizing violent action is of great importance since it is closely related to our safety and security. An intelligent surveillance system is the idea of automatically recognizing suspicious activities in surveillance videos and thereby supporting security personals to take up right action on the right time. Under this area, most of the researchers were focused on people detection and tracking, loitering, etc., whereas detecting violent actions or fights is comparatively a less studied area. Previous works considered the local spatiotemporal feature extractors; however, it accompanies the overhead of complex optical flow estimation. Even though the temporal derivative is a fast alternative to optical flow, it alone gives very low accuracy and scales-dependent result. Hence, here we propose a cascaded method of violence detection based on motion boundary SIFT (MoBSIFT) and movement filtering. In this method, the surveillance videos are checked through a movement filtering algorithm based on temporal derivative and avoid most of the nonviolent actions from going through feature extraction. Only the filtered frames may allow going through feature extraction. In addition to scale-invariant feature transform (SIFT) and histogram of optical flow feature, motion boundary histogram is also extracted and combined to form MoBSIFT descriptor. The experimental results show that the proposed MoBSIFT outperforms the existing methods in accuracy by its high tolerance to camera movements. Time complexity has also proved to be reduced by the use of movement filtering along with MoBSIFT. [ABSTRACT FROM AUTHOR]

Integrating image processing in video surveillance systems is a challenging task that has been attempted for the past several decades. Despite being susceptible to crime, automated teller machine (ATM) surveillance system has not been fully integrated with image processing application for detecting criminal activity. On the other hand, the conventional state of the art image processing algorithms available for occluded and covered face detection, human abnormal behavior analysis and illegal object detection may not work for ATM having different environment (i.e. illumination and camera view), abnormal gestures, and crime devices. This article reviews the previous research works on all possible image processing applications that can be used in the ATM surveillance camera. The review embarks with the aim of (1) categorizing the studies, (2) analyzing their weaknesses and strengths, (3) highlighting significant research findings and (4) providing future research directions. To achieve these goals, this review summarizes the information based on abnormality detection, features, system framework and methodology, image acquisition, sample specification, performance analysis and project funding. Furthermore, the survey evaluates the studies from the point of view of their applicability, suitability, and usage in dynamic environment such as ATM. Viewing as a whole, despite having huge potential, a full-fledged video surveillance system integrated with image processing methods has not been found in the existing literature for ATM. The findings of this review may help the future researchers to develop dynamic and multipurpose algorithms for surveillance system that can detect and prevent ATM crime. [ABSTRACT FROM AUTHOR]

Abnormal activity detection plays a crucial role in surveillance applications, and a surveillance system that can perform robustly in an academic environment has become an urgent need. In this paper, we propose a novel framework for an automatic real-time video-based surveillance system which can simultaneously perform the tracking, semantic scene learning, and abnormality detection in an academic environment. To develop our system, we have divided the work into three phases: preprocessing phase, abnormal human activity detection phase, and content-based image retrieval phase. For motion object detection, we used the temporal-differencing algorithm and then located the motions region using the Gaussian function. Furthermore, the shape model based on OMEGA equation was used as a filter for the detected objects (i.e., human and non-human). For object activities analysis, we evaluated and analyzed the human activities of the detected objects. We classified the human activities into two groups: normal activities and abnormal activities based on the support vector machine. The machine then provides an automatic warning in case of abnormal human activities. It also embeds a method to retrieve the detected object from the database for object recognition and identification using content-based image retrieval. Finally, a software-based simulation using MATLAB was performed and the results of the conducted experiments showed an excellent surveillance system that can simultaneously perform the tracking, semantic scene learning, and abnormality detection in an academic environment with no human intervention. [ABSTRACT FROM AUTHOR]

Healthy aging is one of the most important social issues. In this paper, we propose a method for abnormal activity detection without any manual labeling of the training samples. By leveraging the Field of View (FOV) modulation, the spatio-temporal characteristic of human activity is encoded into low-dimension data stream generated by the ceiling-mounted Pyroelectric Infrared (PIR) sensors. The similarity between normal training samples are measured based on Kullback-Leibler (KL) divergence of each pair of them. The natural clustering of normal activities is discovered through a self-tuning spectral clustering algorithm with unsupervised model selection on the eigenvectors of a modified similarity matrix. Hidden Markov Models (HMMs) are employed to model each cluster of normal activities and form feature vectors. One-Class Support Vector Machines (OSVMs) are used to profile the normal activities and detect abnormal activities. To validate the efficacy of our method, we conducted experiments in real indoor environments. The encouraging results show that our method is able to detect abnormal activities given only the normal training samples, which aims to avoid the laborious and inconsistent data labeling process. [ABSTRACT FROM AUTHOR]

People tracking is a key building block in many applications such as surveillance, abnormal activity detection and the monitoring of elderly persons or persons with restricted mobility. In this reported work, the problem of multipath signals, which is one of the main challenges in indoor and urban environments, is addressed. The proposed method integrates the aspect dependence feature of multipath signals into the tracking framework which allows making full use of more potentially useful information in the time domain in order to make more accurate decisions and to relax some constraints in the space domain such as the large number of antennas that are placed over a large area. An important feature of the proposed method is that it can suppress/mark the entire multipath track; furthermore, it does not assume any prior knowledge of the environment. [ABSTRACT FROM AUTHOR]

Healthy aging is one of the most important social issues. In this paper, we propose a method for abnormal activity detection without any manual labeling of the training samples. By leveraging the Field of View (FOV) modulation, the spatio-temporal characteristic of human activity is encoded into low-dimension data stream generated by the ceiling-mounted Pyroelectric Infrared (PIR) sensors. The similarity between normal training samples are measured based on Kullback-Leibler (KL) divergence of each pair of them. The natural clustering of normal activities is discovered through a self-tuning spectral clustering algorithm with unsupervised model selection on the eigenvectors of a modified similarity matrix. Hidden Markov Models (HMMs) are employed to model each cluster of normal activities and form feature vectors. One-Class Support Vector Machines (OSVMs) are used to profile the normal activities and detect abnormal activities. To validate the efficacy of our method, we conducted experiments in real indoor environments. The encouraging results show that our method is able to detect abnormal activities given only the normal training samples, which aims to avoid the laborious and inconsistent data labeling process.