This paper proposes a novel approach to automatic estimation of attention of students during lectures in the classroom. The approach uses 2D and 3D data obtained by the Kinect One sensor to build a feature set characterizing both facial and body properties of a student, including gaze point and body posture. Machine learning algorithms are used to train classifiers which estimate time-varying attention levels of individual students. Human observers’ estimation of attention level is used as a reference. The comparison of attention prediction accuracy of seven classifiers is done on a data set comprising 18 subjects. Our best person-independent three-level attention classifier achieved moderate accuracy of 0.753, comparable to results of other studies in the field of student engagement. The results indicate that Kinect-based attention monitoring system is able to predict both students’ attention over time as well as average attention levels and could be applied as a tool for non-intrusive automated analytics of the learning process.

In this paper, we report recent research activities under the integrated project, Live Staging of Media Events (LIVE), which is funded under European Framework-6 Programme, and illustrate how a new LIVE TV broadcasting and content production concept can be introduced to improve the existing TV broadcasting services. In comparison with existing TV content production technologies, we show case that LIVE TV broadcasting format could achieve a range of significant advantages, which can be highlighted as: (i) real-time interaction between TV content production team and viewers to ensure the best possible entertainment experiences and to allow viewers not only to view but also to participate, to influence and to control; (ii) the traditional concept of TV content director can be changed to a TV content conductor, where live TV broadcasting can be conducted on real-time bases and existing content materials can be conducted into multi-streams of TV broadcasting, providing variety of choices to allow the audience to make their own preferences in watching TV programs; (iii) introduction of significant intelligence in terms of content analysis and behavior analysis etc. to further improve the quality of services based on the fundamental concept of LIVE project. When tested under field trials for 2008 Olympic Games by ORF, the developed LIVE system has illustrated great potential as well as significant promises to improve the TV broadcasting services not only in terms of the interaction formats, but also in terms of viewing experiences as well as the style of content productions and preparations.

In response to the increasing need for fast satellite image processing SPACE-SI developed STORM—a fully automatic image processing chain that performs all processing steps from the input optical images to web-delivered map-ready products for various sensors. This paper focuses on the automatic geometric corrections module and its adaptation to very high resolution (VHR) multispectral images. In the automatic ground control points (GCPs) extraction sub-module a two-step algorithm that utilizes vector roads as a reference layer and delivers GCPs for high resolution RapidEye images with near pixel accuracy was initially implemented. Super-fine positioning of individual GCPs onto an aerial orthophoto was introduced for VHR images. The enhanced algorithm is capable of achieving accuracy of approximately 1.5 pixels on WorldView-2 data. In the case of RapidEye images the accuracies of the physical sensor model reach sub-pixel values at independent check points. When compared to the reference national aerial orthophoto the accuracies of WorldView-2 orthoimages automatically produced with the rational function model reach near-pixel values. On a heterogeneous set of 41 RapidEye images the rate of automatic processing reached 97.6%. Image processing times remained under one hour for standard-size images of both sensor types.

Efficient workspace awareness is critical for improved interaction in cooperative and collaborative robotic applications. In addition to safety and control aspects, quality-related tasks such as the monitoring of manual activities and the final quality assessment of the results are also required. In this context, a visual quality and safety monitoring system is developed and evaluated. The system integrates close-up observation of manual activities and posture monitoring. A compact single-camera stereo vision system and a time-of-flight depth camera are used to minimize the interference of the sensors with the operator and the workplace. Data processing is based on a deep learning to detect classes related to quality and safety aspects. The operation of the system is evaluated while monitoring a human-robot manual assembly task. The results show that the system ensures a high level of safety, provides reliable visual feedback to the operator on errors in the assembly process, and inspects the finished assembly with a low critical error rate.

This paper presents a novel approach to fully automatic satellite image registration to a local earth coordinate system based on the digital map of the road network. Automatic satellite image co-registration methods typically establish correspondences between points on the target and registered image using local image features such as SIFT, however they are not effective for multi-temporal and multi-sensor registration. As the road network is a prominent feature on the satellite images and is visible in most circumstances, we propose to map it directly to the digital road network topographic map, which is readily available in GIS databases. Our approach starts by detection of road segments in a satellite image, producing a road mask image. Small road mask patches are matched against rasterized road network map to find a set of probable patch locations. Following optimization of translation parameters, each satellite image tile is coarsely located on a road map. In a second fine optimization step, smaller road patches locations are further optimized. The algorithm produces a set of tie points, which include coordinates of satellite image pixels within local metric coordinate system. Experiments were performed on a set of 5 RapidEye images of Slovenia from different periods of the year. The results show that the average error of the points is below 1 pixel for all images, and that the reliability in terms of outlier pixels is very high.