Towards automatic object segmentation with sequential multiple views

Object segmentation is one of the fundamental steps for a number of robotic applications such as manipulation, object detection, and obstacle avoidance. This paper proposes a visual method for incorporating colour and depth information from sequential multiview stereo images to segment objects of interest from complex and cluttered environments. Rather than segmenting objects using information from a single frame in the sequence, we incorporate information from neighbouring views to increase the reliability of the information and improve the overall segmentation result. Specifically, dense depth information of a scene is computed using multiple view stereo. Depths from neighbouring views are reprojected into the reference frame to be segmented compensating for imperfect depth computations for individual frames. The multiple depth layers are then combined with color information from the reference frame to create a Markov random field to model the segmentation problem. Finally, graphcut optimisation is employed to infer pixels belonging to the object to be segmented. The segmentation accuracy is evaluated over images from an outdoor video sequence demonstrating the viability for automatic object segmentation for mobile robots using monocular cameras as a primary sensor.

Face recognition across pose on video using eigen light-fields

We propose an approach to employ eigen light-fields for face recognition across pose on video. Faces of a subject are collected from video frames and combined based on the pose to obtain a set of probe light-fields. These probe data are then projected to the principal subspace of the eigen light-fields within which the classification takes place. We modify the original light-field projection and found that it is more robust in the proposed system. Evaluation on VidTIMIT dataset has demonstrated that the eigen light-fields method is able to take advantage of multiple observations contained in the video.

Developing and enhancing independent learning skills : using video tutorials as a means of helping students help themselves

Purpose – The purpose of this paper is to examine the use of short video tutorials in a post-graduate accounting subject, as a means of helping students develop and enhance independent learning skills. Design/methodology/approach – In total, five short (approximately five to 10 minutes) video tutorials were introduced in an effort to shift the reliance for learning from the lecturer to the student. Data on students’ usage of online video tutorials, and comments by students in university questionnaires were collated over three semesters from 2008 to 2009. Interviews with students were then conducted in late 2009 to more comprehensively evaluate the use and perceived benefits of video tutorials. Findings – Findings reveal preliminary but positive outcomes in terms of both more efficient and effective teaching and learning. Research limitations/implications – The shift towards more independent learning through the use of video tutorials has positive implications for educators, employers, and professional accounting bodies; each of whom has identified the need for this skill in accounting graduates. Practical implications – The use of video tutorials has the potential for more rewarding teaching and more effective learning. Originality/value – This study is one of the first to examine the use and benefits of video tutorials as a means of developing independent learning skills in accountancy students – addressing a key concern within the profession.

Understanding user experience of mobile video : framework, measurement, and optimization

Since users have become the focus of product/service design in last decade, the term User eXperience (UX) has been frequently used in the field of Human-Computer-Interaction (HCI). Research on UX facilitates a better understanding of the various aspects of the user’s interaction with the product or service. Mobile video, as a new and promising service and research field, has attracted great attention. Due to the significance of UX in the success of mobile video (Jordan, 2002), many researchers have centered on this area, examining users’ expectations, motivations, requirements, and usage context. As a result, many influencing factors have been explored (Buchinger, Kriglstein, Brandt & Hlavacs, 2011; Buchinger, Kriglstein & Hlavacs, 2009). However, a general framework for specific mobile video service is lacking for structuring such a great number of factors. To measure user experience of multimedia services such as mobile video, quality of experience (QoE) has recently become a prominent concept. In contrast to the traditionally used concept quality of service (QoS), QoE not only involves objectively measuring the delivered service but also takes into account user’s needs and desires when using the service, emphasizing the user’s overall acceptability on the service. Many QoE metrics are able to estimate the user perceived quality or acceptability of mobile video, but may be not enough accurate for the overall UX prediction due to the complexity of UX. Only a few frameworks of QoE have addressed more aspects of UX for mobile multimedia applications but need be transformed into practical measures. The challenge of optimizing UX remains adaptations to the resource constrains (e.g., network conditions, mobile device capabilities, and heterogeneous usage contexts) as well as meeting complicated user requirements (e.g., usage purposes and personal preferences). In this chapter, we investigate the existing important UX frameworks, compare their similarities and discuss some important features that fit in the mobile video service. Based on the previous research, we propose a simple UX framework for mobile video application by mapping a variety of influencing factors of UX upon a typical mobile video delivery system. Each component and its factors are explored with comprehensive literature reviews. The proposed framework may benefit in user-centred design of mobile video through taking a complete consideration of UX influences and in improvement of mobile videoservice quality by adjusting the values of certain factors to produce a positive user experience. It may also facilitate relative research in the way of locating important issues to study, clarifying research scopes, and setting up proper study procedures. We then review a great deal of research on UX measurement, including QoE metrics and QoE frameworks of mobile multimedia. Finally, we discuss how to achieve an optimal quality of user experience by focusing on the issues of various aspects of UX of mobile video. In the conclusion, we suggest some open issues for future study.

Measuring bitrate and quality trade-off in a fast region-of-interest based video coding

Prevailing video adaptation solutions change the quality of the video uniformly throughout the whole frame in the bitrate adjustment process; while region-of-interest (ROI)-based solutions selectively retains the quality in the areas of the frame where the viewers are more likely to pay more attention to. ROI-based coding can improve perceptual quality and viewer satisfaction while trading off some bandwidth. However, there has been no comprehensive study to measure the bitrate vs. perceptual quality trade-off so far. The paper proposes an ROI detection scheme for videos, which is characterized with low computational complexity and robustness, and measures the bitrate vs. quality trade-off for ROI-based encoding using a state-of-the-art H.264/AVC encoder to justify the viability of this type of encoding method. The results from the subjective quality test reveal that ROI-based encoding achieves a significant perceptual quality improvement over the encoding with uniform quality at the cost of slightly more bits. Based on the bitrate measurements and subjective quality assessments, the bitrate and the perceptual quality estimation models for non-scalable ROI-based video coding (AVC) are developed, which are found to be similar to the models for scalable video coding (SVC).

Engaging bodily with video in design

Video is commonly used as a method for recording embodied interaction for purposes of analysis and design and has been proposed as a useful ‘material’ for interaction designers to engage with. But video is not a straight forward reproduction of embodied activity – in themselves video recordings ‘flatten’ the space of embodied interaction, they impose a perspective on unfolding action, and remove the embodied spatial and social context within which embodied interaction unfolds. This does not mean that video is not a useful medium with which to engage as part of a process of investigating and designing for embodied interaction – but crucially, it requires that as people attempting to engage with video, designers own bodies and bodily understandings must be engaged with and brought into play. This paper describes and reflects upon our experiences of engaging with video in two different activities as part of a larger research project investigating the design of gestural interfaces for a dental surgery context.

Probabilistic matching of image sets for video-based face recognition

We address the problem of face recognition on video by employing the recently proposed probabilistic linear discrimi-nant analysis (PLDA). The PLDA has been shown to be robust against pose and expression in image-based face recognition. In this research, the method is extended and applied to video where image set to image set matching is performed. We investigate two approaches of computing similarities between image sets using the PLDA: the closest pair approach and the holistic sets approach. To better model face appearances in video, we also propose the heteroscedastic version of the PLDA which learns the within-class covariance of each individual separately. Our experi-ments on the VidTIMIT and Honda datasets show that the combination of the heteroscedastic PLDA and the closest pair approach achieves the best performance.

The diagnostic accuracy of telegeriatrics for the diagnosis of dementia via video conferencing

Introduction The suitability of video conferencing (VC) technology for clinical purposes relevant to geriatric medicine is still being established. This project aimed to determine the validity of the diagnosis of dementia via VC. Methods This was a multisite, noninferiority, prospective cohort study. Patients, aged 50 years and older, referred by their primary care physician for cognitive assessment, were assessed at 4 memory disorder clinics. All patients were assessed independently by 2 specialist physicians. They were allocated one face-to-face (FTF) assessment (Reference standard – usual clinical practice) and an additional assessment (either usual FTF assessment or a VC assessment) on the same day. Each specialist physician had access to the patient chart and the results of a battery of standardized cognitive assessments administered FTF by the clinic nurse. Percentage agreement (P0) and the weighted kappa statistic with linear weight (Kw) were used to assess inter-rater reliability across the 2 study groups on the diagnosis of dementia (cognition normal, impaired, or demented). Results The 205 patients were allocated to group: Videoconference (n = 100) or Standard practice (n = 105); 106 were men. The average age was 76 (SD 9, 51–95) and the average Standardized Mini-Mental State Examination Score was 23.9 (SD 4.7, 9–30). Agreement for the Videoconference group (P0= 0.71; Kw = 0.52; P < .0001) and agreement for the Standard Practice group (P0= 0.70; Kw = 0.50; P < .0001) were both statistically significant (P < .05). The summary kappa statistic of 0.51 (P = .84) indicated that VC was not inferior to FTF assessment. Conclusions Previous studies have shown that preliminary standardized assessment tools can be reliably administered and scored via VC. This study focused on the geriatric assessment component of the interview (interpretation of standardized assessments, taking a history and formulating a diagnosis by medical specialist) and identified high levels of agreement for diagnosing dementia. A model of service incorporating either local or remote administered standardized assessments, and remote specialist assessment, is a reliable process for enabling the diagnosis of dementia for isolated older adults.

A mask-based approach for the geometric calibration of thermal-infrared cameras

Accurate and efficient thermal-infrared (IR) camera calibration is important for advancing computer vision research within the thermal modality. This paper presents an approach for geometrically calibrating individual and multiple cameras in both the thermal and visible modalities. The proposed technique can be used to correct for lens distortion and to simultaneously reference both visible and thermal-IR cameras to a single coordinate frame. The most popular existing approach for the geometric calibration of thermal cameras uses a printed chessboard heated by a flood lamp and is comparatively inaccurate and difficult to execute. Additionally, software toolkits provided for calibration either are unsuitable for this task or require substantial manual intervention. A new geometric mask with high thermal contrast and not requiring a flood lamp is presented as an alternative calibration pattern. Calibration points on the pattern are then accurately located using a clustering-based algorithm which utilizes the maximally stable extremal region detector. This algorithm is integrated into an automatic end-to-end system for calibrating single or multiple cameras. The evaluation shows that using the proposed mask achieves a mean reprojection error up to 78% lower than that using a heated chessboard. The effectiveness of the approach is further demonstrated by using it to calibrate two multiple-camera multiple-modality setups. Source code and binaries for the developed software are provided on the project Web site.

A Context Space Model for Detecting Anomalous Behaviour in Video Surveillance

Having a good automatic anomalous human behaviour detection is one of the goals of smart surveillance systems’ domain of research. The automatic detection addresses several human factor issues underlying the existing surveillance systems. To create such a detection system, contextual information needs to be considered. This is because context is required in order to correctly understand human behaviour. Unfortunately, the use of contextual information is still limited in the automatic anomalous human behaviour detection approaches. This paper proposes a context space model which has two benefits: (a) It provides guidelines for the system designers to select information which can be used to describe context; (b)It enables a system to distinguish between different contexts. A comparative analysis is conducted between a context-based system which employs the proposed context space model and a system which is implemented based on one of the existing approaches. The comparison is applied on a scenario constructed using video clips from CAVIAR dataset. The results show that the context-based system outperforms the other system. This is because the context space model allows the system to considering knowledge learned from the relevant context only.

Improved Subject Identification in Surveillance Video using Super Resolution

The time consuming and labour intensive task of identifying individuals in surveillance video is often challenged by poor resolution and the sheer volume of stored video. Faces or identifying marks such as tattoos are often too coarse for direct matching by machine or human vision. Object tracking and super-resolution can then be combined to facilitate the automated detection and enhancement of areas of interest. The object tracking process enables the automatic detection of people of interest, greatly reducing the amount of data for super-resolution. Smaller regions such as faces can also be tracked. A number of instances of such regions can then be utilized to obtain a super-resolved version for matching. Performance improvement from super-resolution is demonstrated using a face verification task. It is shown that there is a consistent improvement of approximately 7% in verification accuracy, using both Eigenface and Elastic Bunch Graph Matching approaches for automatic face verification, starting from faces with an eye to eye distance of 14 pixels. Visual improvement in image fidelity from super-resolved images over low-resolution and interpolated images is demonstrated on a small database. Current research and future directions in this area are also summarized.

Identifying customer behaviour and dwell time using soft biometrics

In a commercial environment, it is advantageous to know how long it takes customers to move between different regions, how long they spend in each region, and where they are likely to go as they move from one location to another. Presently, these measures can only be determined manually, or through the use of hardware tags (i.e. RFID). Soft biometrics are characteristics that can be used to describe, but not uniquely identify an individual. They include traits such as height, weight, gender, hair, skin and clothing colour. Unlike traditional biometrics, soft biometrics can be acquired by surveillance cameras at range without any user cooperation. While these traits cannot provide robust authentication, they can be used to provide identification at long range, and aid in object tracking and detection in disjoint camera networks. In this chapter we propose using colour, height and luggage soft biometrics to determine operational statistics relating to how people move through a space. A novel average soft biometric is used to locate people who look distinct, and these people are then detected at various locations within a disjoint camera network to gradually obtain operational statistics

Effectiveness of red light cameras on the right-angle crash involvement of motorcycles

Red light cameras (RLC) have been used to reduce right-angle collisions at signalized intersections. However, the effect of RLCs on motorcycle crashes has not been well investigated. The objective of this study is to evaluate the effectiveness of RLCs on motorcycle safety in Singapore. This is done by comparing their exposure, proneness of at-fault right-angle crashes as well as the resulting right-angle collisions at RLC with those at non-RLC sites. Estimating the crash vulnerability from not-at-fault crash involvements, the study shows that with a RLC, the relative crash vulnerability or crash-involved exposure of motorcycles at right-angle crashes is reduced. Furthermore, field investigation of motorcycle maneuvers reveal that at non-RLC arms, motorcyclists usually queue beyond the stop-line, facilitating an earlier discharge and hence become more exposed to the conflicting stream. However at arms with a RLC, motorcyclists are more restrained to avoid activating the RLC and hence become less exposed to conflicting traffic during the initial period of the green. The study also shows that in right-angle collisions, the proneness of at-fault crashes of motorcycles is lowest among all vehicle types. Hence motorcycles are more likely to be victims than the responsible parties in right-angle crashes. RLCs have also been found to be very effective in reducing at-fault crash involvements of other vehicle types which may implicate exposed motorcycles in the conflicting stream. Taking all these into account, the presence of RLCs should significantly reduce the vulnerability of motorcycles at signalized intersections.

Impact of region-of-interest video coding on perceived quality in mobile video

Effective streaming of video can be achieved by providing more bits to the most important region in the frame at the cost of reduced bits in the less important regions. This strategy can be beneficial for delivering high quality videos in mobile devices, especially when the availability of bandwidth is usually low and limited. While the state-of-the-art video codecs such as H.264 may have been optimised for perceived quality, it is hypothesised that users will give more attention to interesting region/object when watching videos. Therefore, giving a higher quality to region of interest (ROI)while reducing quality of other areas may result in improving the overall perceived quality without necessarily increasing the bitrate. In this paper, the impact of ROI-based encoded video on perceived quality is investigated by conducting a user study for varous target bitrates. The results from the user study demonstrate that ROI-based video coding has superior perceived quality compared to normal encoded video at the same bitrate in the lower bitrate range.