We propose drowsiness detection in real-time surveillance videos by determining if a person’s eyes are open or closed. As a first step, the face of the subject is detected in the image. In the detected face, the eyes are localized and filtered with an extended Sobel operator to detect the curvature of the eyelids. Once the curves are detected, concavity is used to tell whether the eyelids are closed or open. Consequently, a concave upward curve means the eyelid is closed whereas a concave downwards curve means the eye is open. The proposed method is also implemented on hardware in order to be used in real-time scenarios, such as driver drowsiness detection. The evaluation of the proposed method used three image datasets, where images in the first dataset have a uniform background. The proposed method achieved classification accuracy of up to 95% on this dataset. Another benchmark dataset used has significant variations based on face deformations. With this dataset, our method achieved classification accuracy of 70%. A real-time video dataset of people driving the car was also used, where the proposed method achieved 95% accuracy, thus showing its feasibility for use in real-time scenarios.

This paper presents two radio frequency (RF) sensors with different directivities designed and tested for device-free localization (DFL) in an indoor environment. Mostly, in smart homes and smart offices, peoples may be irritated by wearing the device on them all the time. As compared with device-based localization, the proposed sensors can localize both cooperative and non-cooperative targets (intruders and guests etc.) without privacy leakages. Both sensors are tested to detect the change in received signal strength (ΔRSS) due to the presence of an obstacle. RF sensors, i.e., antennas are designed to operate in the ISM band of 2.4–2.5 GHz. Experimental results show that the sensor with higher directivity provides better ΔRSS that helps in improved accuracy to detect a device-free target.

The demand for wireless mobile communication is growing exponentially with expectations that in the near future mobile device or user will be available in every corner of the globe. Alternatively, it increases the importance of antenna arrays which are responsible for transmission and reception of information. Every antenna array is projected to generate a desired pattern and, hence, failure of any antenna causes misrepresentation of the overall pattern in terms of increased side lobe levels and displacement of nulls from their original position. The aim of the study is to present viable, simple, and accurate stochastic solver based on backtracking search optimization algorithm (BSA) for the pattern correction of faulty antenna array in mobile communication systems. A fitness function is developed to optimize the weights of the remaining healthy antenna elements in the array. The fitness function consists of two parts: the first part is based on mean square error approach for the reduction of sidelobes level, while, in the second part, steering vectors are used for the repositioning of nulls. Simulation results establish the validity of the BSA from its counterparts based on genetic algorithm and its memetic combination with pattern search technique.

A novel two stage data association technique for multi-target tracking is proposed which assigns multiple measurements to a target to mitigate information loss. At the first stage a variational Bayesian (VB) clustering technique is used which groups the measurements automatically into a determined number of clusters. In the second stage a belief propagation (BP) based cluster to target association method is proposed to assign multiple clusters to a target. This is achieved by exploiting the inter-cluster dependency information. The proposed technique is suitable to accommodate non-rigid targets such as humans. Both location and features of clusters are used to re-identify the targets when they emerge from occlusions. The proposed technique is compared with state of the art method due to Laet et al. and evaluations are presented on a real data set.

Source separation algorithms that utilize only audio data can perform poorly if multiple sources or reverberation are present. In this paper we therefore propose a video-aided model-based source separation algorithm for a two-channel reverberant recording in which the sources are assumed static. By exploiting cues from video, we first localize individual speech sources in the enclosure and then estimate their directions. The interaural spatial cues, the interaural phase difference and the interaural level difference, as well as the mixing vectors are probabilistically modeled. The models make use of the source direction information and are evaluated at discrete time-frequency points. The model parameters are refined with the well-known expectation-maximization (EM) algorithm. The algorithm outputs time-frequency masks that are used to reconstruct the individual sources. Simulation results show that by utilizing the visual modality the proposed algorithm can produce better time-frequency masks thereby giving improved source estimates. We provide experimental results to test the proposed algorithm in different scenarios and provide comparisons with both other audio-only and audio-visual algorithms and achieve improved performance both on synthetic and real data. We also include dereverberation based pre-processing in our algorithm in order to suppress the late reverberant components from the observed stereo mixture and further enhance the overall output of the algorithm. This advantage makes our algorithm a suitable candidate for use in under-determined highly reverberant settings where the performance of other audio-only and audio-visual methods is limited.