Electrical and Electronic Engineering - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 19
-
ItemA robust algorithm for foreground extraction in crowded scenes(IEEE, 2012-12-01)The widespread availability of surveillance cameras and digital technology has improved video based security measures in public places. Surveillance systems have been assisting officials both in civil and military applications. It is helping to identify unlawful activities by means of uninterrupted transmission of surveillance videos. By this, the system is adding extraneous onus on to the already existing workload of security officers. Instead, if the surveillance system is intelligent and efficient enough to identify the events of interest and alert the officers, it alleviates the burden of continuous monitoring. In other words, our existing surveillance systems are lacking to identify the objects that are dissimilar in shape, size, and color especially in identifying human beings (nonrigid motions). Global illumination changes, frequent occurrences of shadows, insufficient lighting conditions, unique properties of slow and fast moving objects, unforeseen appearance of objects and its behavior, availability of system memory, etc., may be ascribed to the limitations of existing systems. In this paper, we present a filtering technique to extract foreground information, which uses RGB component and chrominance channels to neutralize the effects of nonuniform illumination, remove shadows, and detect both slow-moving and distant objects.
-
ItemA Pilot Study of Urban Noise Monitoring Architecture Using Wireless Sensor Networks(IEEE, 2013-01-01)Internet of Things (IoT) is denned as interconnection of sensing and actuating devices providing the ability to share information across platforms through a unified framework, developing a common operating picture for enabling innovative applications. As the world urban population is set to cross unprecedented levels, adequate provision of services and infrastructure poses huge challenges. The emerging IoT that offers ubiquitous sensing and actuation can be utilized effectively for managing urban environments. In this paper, a new architecture for noise monitoring in urban environments is proposed. The architecture is scalable and applicable to other sensors required for city management. In addition to the architecture, a new noise monitoring hardware platform is reported and visualization of the data is presented. An emerging citizen centric participatory sensing is discussed in the context of noise monitoring.
-
ItemA Pilot Study on the use of Accelerometer Sensors for Monitoring Post Acute Stroke Patients(IEEE, 2013)The high incidence of stroke has raised a major concern among health professionals in recent years. Concerted efforts from medical and engineering communities are being exercised to tackle the problem at its early stage. In this direction, a pilot study to analyze and detect the affected arm of the stroke patient based on hand movements is presented. The premise is that the correlation of magnitude of the activities of the two arms vary significantly for stroke patients from controls. Further, the cross-correlation of right and left arms for three axes are differentiable for patients and controls. A total of 22 subjects (15 patients and 7 controls) were included in this study. An overall accuracy of 95.45% was obtained with sensitivity of 1 and specificity of 0.86 using correlation based method.
-
ItemCrowd Density Estimation Based on Optical Flow and Hierarchical Clustering(IEEE, 2013-01-01)Crowd density estimation has gained much attention from researchers recently due to availability of low cost cameras and communication bandwidth. In video surveillance applications, counting people and creating a temporal profile is of high interest. Surveillance systems face difficulties in detecting motion from the scene due to varying environmental conditions and occlusion. Instead of detecting and tracking individual person, density estimation is an approximate method to count people. The approximation is often more accurate than individual tracking in occluded scenarios. In this work, a new technique to estimate crowd density is proposed. A block-based dense optical flow with spatial and temporal filtering is used to obtain velocities in order to infer the locations of objects in crowded scenarios. Furthermore, a hierarchical clustering is employed to cluster the objects based on Euclidean distance metric. The Cophenetic correlation coefficient for the clusters highlighted the fact that our preprocessing and localizing of object movements form hierarchical clusters that are structured well with reasonable accuracy without temporal post-processing.
-
ItemDetermination of Object Directions Using Optical Flow for Crowd Monitoring(SPRINGER-VERLAG BERLIN, 2013-01-01)Determination of object direction in a multi-camera tracking system is critical. The absence of object direction from other cameras pose challenges if the object is along the optical axis. The problem of determining object direction worsens further if the cameras in the existing infrastructure are improperly placed and are uncontrollable. To determine the direction of an object in such situations, three methods based on optical flow (OF) are presented. The first method uses centroids of optical flow vector magnitudes and Kalman filter for tracking and is suitable for less crowded scenarios. The second method uses geometric moments to evaluate the flow vector distribution and to ascertain the direction in case of crowded scenarios by partitioning the scene and then applying moments to individual partitions independently. The third method is appropriate for small-sized objects near vanishing points where global object motion is less. During surveillance, whether multi-object, single-object or crowded scenarios, the aforementioned methods are applicable accordingly. The results show that the object directions can be accurately inferred from three methods for different scenarios.
-
ItemProbabilistic detection of crowd events on riemannian manifolds(IEEE, 2015-01-12)Event detection in crowded scenarios becomes complex due to articulated human movements, occlusions and complexities involved in tracking individual humans. In this work, we focus on crowd event (activity) detection and classification. We focus on active crowd (continuously moving crowd) events. First, event primitives such as motion, action, activity and behaviour are defined. Furthermore, a distinction is made among event detection, action recognition and abnormal event detection. Further, event detection and classification are defined on Riemannian Manifolds that yields six different probabilities of the event occurring. Using a new probabilistic approach, an automated event detection algorithm is proposed that temporally segments the event using a novel framework. The results indicate that the proposed approach delivers superior performance in selected cases and similar results in other cases, whilst the detection model delay allows operation in near real-time. The Performance Evaluation of Tracking and Surveillance (PETS) 2009 dataset was used for evaluation. Existing crowd event detection approaches used supervised approach, whereas we eschew semi-supervised approach.
-
ItemDetection of anomalous crowd behaviour using hyperspherical clustering(IEEE, 2015-01-12)Analysis of crowd behaviour in public places is an indispensable tool for video surveillance. Automated detection of anomalous crowd behaviour is a critical problem with the increase in human population. Anomalous events may include a person loitering about a place for unusual amounts of time; people running and causing panic; the size of a group of people growing over time etc. In this work, to detect anomalous events and objects, two types of feature coding has been proposed: spatial features and spatio-temporal features. Spatial features comprises of contrast, correlation, energy and homogeneity, which are derived from Gray Level Co-occurrence Matrix (GLCM). Spatio-temporal feature includes the time spent by an object at different locations in the scene. Hyperspherical clustering has been employed to detect the anomalies. Spatial features revealed the anomalous frames by using contrast and homogeneity measures. Loitering behaviour of the people were detected as anomalous objects using the spatio-temporal coding.
-
ItemClassification of Convulsive Psychogenic Non-epileptic Seizures Using Histogram of Oriented Motion of Accelerometry Signals(IEEE, 2015)A seizure is caused due to sudden surge of electrical activity within the brain. There is another class of seizures called psychogenic non-epileptic seizure (PNES) that mimics epilepsy, but is caused due to underlying psychology. The diagnosis of PNES is done using video-electroencephalography monitoring (VEM), which is a resource intensive process. Recently, accelerometers have been shown to be effective in classification of epileptic and non-epileptic seizures. In this work, we propose a novel feature called histogram of oriented motion (HOOM) extracted from accelerometer signals for classification of convulsive PNES. An automated algorithm based on HOOM is proposed. The algorithm showed a high sensitivity of (93.33%) and an overall accuracy of (80%) in classifying convulsive PNES.
-
ItemAn Improved Approach to Crowd Event Detection by Reducing Data Dimensions(SPRINGER-VERLAG BERLIN, 2016)Crowd monitoring is a critical application in video surveillance. Crowd events such as running, walking, merging, splitting, dispersion, and evacuation inform crowd management about the behavior of groups of people. For an effective crowd management, detection of crowd events provides an early sign of the behavior of the people. However, crowd event detection using videos is a highly challenging task because of several challenges such as non-rigid human body motions, occlusions, unavailability of distinguishing features due to occlusions, unpredictability in people movements, and other. In addition, the video itself is a high-dimensional data and analyzing to detect events becomes further complicated. One way of tackling the huge volume of video data is to represent a video using low-dimensional equivalent. However, reducing the video data size needs to consider the complex data structure and events embedded in a video. To this extent, we focus on detection of crowd events using the Isometric Mapping (ISOMAP) and Support Vector Machine (SVM). The ISOMAP is used to construct the low-dimensional representation of the feature vectors, and then an SVM is used for training and classification. The proposed approach uses Haar wavelets to extract Gray Level Coefficient Matrix (GLCM). Later, the approach extracts four statistical features (contrast, correlating, energy, and homogeneity) at different levels of Haar wavelet decomposition. Experiment results suggest that the proposed approach is shown to perform better when compared with existing approaches.
-
ItemAnomalous Crowd Event Analysis Using Isometric Mapping(SPRINGER-VERLAG BERLIN, 2016)Anomalous event detection is one of the important applications in crowd monitoring. The detection of anomalous crowd events requires featurematrix to capture the spatio-temporal information to localize the events and detect the outliers. However, feature matrices often become computationally expensive with large number of features becomes critical for large-scale and real-time video analytics. In this work, we present a fast approach to detect anomalous crowd events and frames. First, to detect anomalous crowd events, the motion features are captured using the optical flow and a feature matrix of motion information is constructed and then subjected to nonlinear dimensionality reduction (NDR) using the Isometric Mapping (ISOMAP). Next, to detect anomalous crowd frames, the method uses four statistical features by dividing the frames into blocks and then calculating the statistical features for the blocks where objects were present. The main focus of this study is to understand the effect of large feature matrix size on detecting the anomalies with respect to computational time. Experiments were conducted on two datasets: (1) Performance Evaluation of Tracking and Surveillance (PETS) 2009 and (2) Melbourne Cricket Ground (MCG) 2011. Experiment results suggest that the ISOMAP NDR reduces the computation time significantly, more than ten times, to detect anomalous crowd events and frames. In addition, the experiment revealed that the ISOMAP provided an upper bound on the computational time.