Driver distraction, defined as the diversion of attention away from activities critical for safe driving toward a competing activity, is increasingly recognized as a significant source of injuries and fatalities on the roadway. Additionally, the trend towards increasing the use of in-vehicle information systems is critical because they induce visual, biomechanical and cognitive distraction and may affect driving performance in qualitatively different ways. Non-intrusive methods are strongly preferred for monitoring distraction, and vision-based systems have appeared to be attractive for both drivers and researchers. Biomechanical, visual and cognitive distractions are the most commonly detected types in video-based algorithms. Many distraction detection systems only use a single visual cue and therefore, they may be easily disturbed when occlusion or illumination changes appear. Moreover, the combination of these visual cues is a key and challenging aspect in the development of robust distraction detection systems. These visual cues can be extracted mainly by using face monitoring systems but they should be completed with more visual cues (e.g., hands or body information) or even, distraction detection from specific actions (e.g., phone usage). Additionally, these algorithms should be included in an embedded device or system inside a car. This is not a trivial task and several requirements must be taken into account: reliability, real-time performance, low cost, small size, low power consumption, flexibility and short time-to-market. The key points for the development and implementation of sensors to carry out the detection of distraction will also be reviewed. This paper shows a review of the role of computer vision technology applied to the development of monitoring systems to detect distraction. Some key points considered as both future work and challenges ahead yet to be solved will also be addressed.

Summary Big Data encompasses large volume of complex structured, semi‐structured, and unstructured data, which is beyond the processing capabilities of conventional databases. The processing and analysis of Big Data now play a central role in decision making, forecasting, business analysis, product development, customer experience, and loyalty, to name but a few. In this paper, we examine the distinguishing characteristics of Big Data along the lines of the 3Vs: variety, volume, and velocity. Accordingly, the paper provides an insight into the main processing paradigms in relation to the 3Vs. It defines a lifecycle for Big Data processing and classifies various available tools and technologies in terms of the lifecycle phases of Big Data, which include data acquisition, data storage, data analysis, and data exploitation of the results. This paper is first of its kind that reviews and analyzes current trends and technologies in relation to the characteristics, evolution, and processing of Big Data. Copyright © 2014 John Wiley & Sons, Ltd.

Automatic glasses detection on real face images is a challenging problem due to different appearance variations. Nevertheless, glasses detection on face images has not been thoroughly investigated. In this paper, an innovative algorithm for automatic glasses detection based on Robust Local Binary Pattern and robust alignment is proposed. Firstly, images are preprocessed and normalized in order to deal with scale and rotation. Secondly, eye glasses region is detected considering that the nosepiece of the glasses is usually placed at the same level as the center of the eyes in both height and width. Thirdly, Robust Local Binary Pattern is built to describe the eyes region, and finally, support vector machine is used to classify the LBP features. This algorithm can be applied as the first step of a glasses removal algorithm due to its robustness and speed. The proposed algorithm has been tested over the Labeled Faces in the Wild database showing a 98.65 % recognition rate. Influences of the resolution, the alignment of the normalized images and the number of divisions in the LBP operator are also investigated.

No abstract

NoSQL databases provide high availability and efficiency in data processing but at the expense of weaker consistency. In this paper, we propose a new approach in order to test NoSQL key/value databases in general and their CRUD operations in particular. We design a new context-aware model that takes into account the contextual requirements of clients (users) and the NoSQL database system. Accordingly, we develop a transaction model and testing criteria in order to test NoSQL databases by taking into account transactional and nontransactional CRUD operations. Results from testing criteria are used to analyse the trade-off between availability and consistency of NoSQL databases. In addition, these are used to help NoSQL database users and developers to choose between transactional and non-transactional CRUD operations.