Functional activation during the Rapid Visual Information Processing task in a middle aged cohort: An fMRI study

The Rapid Visual Information Processing (RVIP) task, a serial discrimination task where task performance believed to reflect sustained attention capabilities, is widely used in behavioural research and increasingly in neuroimaging studies. To date, functional neuroimaging research into the RVIP has been undertaken using block analyses, reflecting the sustained processing involved in the task, but not necessarily the transient processes associated with individual trial performance. Furthermore, this research has been limited to young cohorts. This study assessed the behavioural and functional magnetic resonance imaging (fMRI) outcomes of the RVIP task using both block and event-related analyses in a healthy middle aged cohort (mean age = 53.56 years, n = 16). The results show that the version of the RVIP used here is sensitive to changes in attentional demand processes with participants achieving a 43% accuracy hit rate in the experimental task compared with 96% accuracy in the control task. As shown by previous research, the block analysis revealed an increase in activation in a network of frontal, parietal, occipital and cerebellar regions. The event related analysis showed a similar network of activation, seemingly omitting regions involved in the processing of the task (as shown in the block analysis), such as occipital areas and the thalamus, providing an indication of a network of regions involved in correct trial performance. Frontal (superior and inferior frontal gryi), parietal (precuenus, inferior parietal lobe) and cerebellar regions were shown to be active in both the block and event-related analyses, suggesting their importance in sustained attention/vigilance. These networks and the differences between them are discussed in detail, as well as implications for future research in middle aged cohorts.

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

At present, the most reliable method to obtain end-user perceived quality is through subjective tests. In this paper, the impact of automatic region-of-interest (ROI) coding on perceived quality of mobile video is investigated. The evidence, which is based on perceptual comparison analysis, shows that the coding strategy improves perceptual quality. This is particularly true in low bit rate situations. The ROI detection method used in this paper is based on two approaches: - (1) automatic ROI by analyzing the visual contents automatically, and; - (2) eye-tracking based ROI by aggregating eye-tracking data across many users, used to both evaluate the accuracy of automatic ROI detection and the subjective quality of automatic ROI encoded video. The perceptual comparison analysis is based on subjective assessments with 54 participants, across different content types, screen resolutions, and target bit rates while comparing the two ROI detection methods. The results from the user study demonstrate that ROI-based video encoding has higher perceived quality compared to normal video encoded at a similar bit rate, particularly in the lower bit rate range.

Learning Temporal Alignment Uncertainty for Efficient Event Detection

In this paper we tackle the problem of efficient video event detection. We argue that linear detection functions should be preferred in this regard due to their scalability and efficiency during estimation and evaluation. A popular approach in this regard is to represent a sequence using a bag of words (BOW) representation due to its: (i) fixed dimensionality irrespective of the sequence length, and (ii) its ability to compactly model the statistics in the sequence. A drawback to the BOW representation, however, is the intrinsic destruction of the temporal ordering information. In this paper we propose a new representation that leverages the uncertainty in relative temporal alignments between pairs of sequences while not destroying temporal ordering. Our representation, like BOW, is of a fixed dimensionality making it easily integrated with a linear detection function. Extensive experiments on CK+, 6DMG, and UvA-NEMO databases show significant performance improvements across both isolated and continuous event detection tasks.

Distributed Robotic Vision as a service

The vision sense of standalone robots is limited by line of sight and onboard camera capabilities, but processing video from remote cameras puts a high computational burden on robots. This paper describes the Distributed Robotic Vision Service, DRVS, which implements an on-demand distributed visual object detection service. Robots specify visual information requirements in terms of regions of interest and object detection algorithms. DRVS dynamically distributes the object detection computation to remote vision systems with processing capabilities, and the robots receive high-level object detection information. DRVS relieves robots of managing sensor discovery and reduces data transmission compared to image sharing models of distributed vision. Navigating a sensorless robot from remote vision systems is demonstrated in simulation as a proof of concept.

Enhancing human action recognition with region proposals

Deep convolutional network models have dominated recent work in human action recognition as well as image classification. However, these methods are often unduly influenced by the image background, learning and exploiting the presence of cues in typical computer vision datasets. For unbiased robotics applications, the degree of variation and novelty in action backgrounds is far greater than in computer vision datasets. To address this challenge, we propose an “action region proposal” method that, informed by optical flow, extracts image regions likely to contain actions for input into the network both during training and testing. In a range of experiments, we demonstrate that manually segmenting the background is not enough; but through active action region proposals during training and testing, state-of-the-art or better performance can be achieved on individual spatial and temporal video components. Finally, we show by focusing attention through action region proposals, we can further improve upon the existing state-of-the-art in spatio-temporally fused action recognition performance.

The influence of pre-processing on the estimation of readability of web documents

This paper investigates the effect that text pre-processing approaches have on the estimation of the readability of web pages. Readability has been highlighted as an important aspect of web search result personalisation in previous work. The most widely used text readability measures rely on surface level characteristics of text, such as the length of words and sentences. We demonstrate that different tools for extracting text from web pages lead to very different estimations of readability. This has an important implication for search engines because search result personalisation strategies that consider users reading ability may fail if incorrect text readability estimations are computed.

Indicators of wellbeing in recreational video game players

Video game play is a popular entertainment choice, yet we have a limited understanding of the potential wellbeing benefits associated with recreational play. An online survey (final sample, n = 297) addresses this by investigating how the player experience related to wellbeing. The impact of amount of play, game genre, mode of play (social or solitary play) and the psychological experience of play (flow and need satisfaction) on a multi-dimensional measure of wellbeing (emotional, psychological and social) was examined via hierarchical regression. Age, gender, the play of casual games compared to shooters, and in-game experiences of flow, autonomy and relatedness were associated with increases in dimensions of wellbeing.

Detecting rare events using Kullback-Leibler divergence: A weakly supervised approach

Video surveillance infrastructure has been widely installed in public places for security purposes. However, live video feeds are typically monitored by human staff, making the detection of important events as they occur difficult. As such, an expert system that can automatically detect events of interest in surveillance footage is highly desirable. Although a number of approaches have been proposed, they have significant limitations: supervised approaches, which can detect a specific event, ideally require a large number of samples with the event spatially and temporally localised; while unsupervised approaches, which do not require this demanding annotation, can only detect whether an event is abnormal and not specific event types. To overcome these problems, we formulate a weakly-supervised approach using Kullback-Leibler (KL) divergence to detect rare events. The proposed approach leverages the sparse nature of the target events to its advantage, and we show that this data imbalance guarantees the existence of a decision boundary to separate samples that contain the target event from those that do not. This trait, combined with the coarse annotation used by weakly supervised learning (that only indicates approximately when an event occurs), greatly reduces the annotation burden while retaining the ability to detect specific events. Furthermore, the proposed classifier requires only a decision threshold, simplifying its use compared to other weakly supervised approaches. We show that the proposed approach outperforms state-of-the-art methods on a popular real-world traffic surveillance dataset, while preserving real time performance.

Biofuels from food processing wastes

Food processing industry generates substantial high organic wastes along with high energy uses. The recovery of food processing wastes as renewable energy sources represents a sustainable option for the substitution of fossil energy, contributing to the transition of food sector towards a low-carbon economy. This article reviews the latest research progress on biofuel production using food processing wastes. While extensive work on laboratory and pilot-scale biosystems for energy production has been reported, this work presents a review of advances in metabolic pathways, key technical issues and bioengineering outcomes in biofuel production from food processing wastes. Research challenges and further prospects associated with the knowledge advances and technology development of biofuel production are discussed.

Activity recognition using binary tree SVM

This paper presents an effective classification method based on Support Vector Machines (SVM) in the context of activity recognition. Local features that capture both spatial and temporal information in activity videos have made significant progress recently. Efficient and effective features, feature representation and classification plays a crucial role in activity recognition. For classification, SVMs are popularly used because of their simplicity and efficiency; however the common multi-class SVM approaches applied suffer from limitations including having easily confused classes and been computationally inefficient. We propose using a binary tree SVM to address the shortcomings of multi-class SVMs in activity recognition. We proposed constructing a binary tree using Gaussian Mixture Models (GMM), where activities are repeatedly allocated to subnodes until every new created node contains only one activity. Then, for each internal node a separate SVM is learned to classify activities, which significantly reduces the training time and increases the speed of testing compared to popular the `one-against-the-rest' multi-class SVM classifier. Experiments carried out on the challenging and complex Hollywood dataset demonstrates comparable performance over the baseline bag-of-features method.

Insights into students' conceptual understanding using textual analysis: A case study in signal processing

Concept inventory tests are one method to evaluate conceptual understanding and identify possible misconceptions. The multiple-choice question format, offering a choice between a correct selection and common misconceptions, can provide an assessment of students' conceptual understanding in various dimensions. Misconceptions of some engineering concepts exist due to a lack of mental frameworks, or schemas, for these types of concepts or conceptual areas. This study incorporated an open textual response component in a multiple-choice concept inventory test to capture written explanations of students' selections. The study's goal was to identify, through text analysis of student responses, the types and categorizations of concepts in these explanations that had not been uncovered by the distractor selections. The analysis of the textual explanations of a subset of the discrete-time signals and systems concept inventory questions revealed that students have difficulty conceptually explaining several dimensions of signal processing. This contributed to their inability to provide a clear explanation of the underlying concepts, such as mathematical concepts. The methods used in this study evaluate students' understanding of signals and systems concepts through their ability to express understanding in written text. This may present a bias for students with strong written communication skills. This study presents a framework for extracting and identifying the types of concepts students use to express their reasoning when answering conceptual questions.

Understanding video based parent training intervention for children with autism

This paper investigates the challenges of delivering parent training intervention for autism over video. We conducted a qualitative field study of an intervention, which is based on a well-established training program for parents of children with autism, called Hanen More Than Words. The study was conducted with a Hanen Certified speech pathologist who delivered video based training to two mothers, each with a son having autism. We conducted observations of 14 sessions of the intervention spanning 3 months along with 3 semi-structured interviews with each participant. We identified different activities that participants performed across different sessions and analysed them based upon their implications on technology. We found that all the participants welcomed video based training but they also faced several difficulties, particularly in establishing rapport with other participants, inviting equal participation, and in observing and providing feedback on parent-child interactions. Finally, we reflect on our findings and motivate further investigations by defining three design sensitivities of Adaptation, Group Participation, and Physical Setup.

Implicit and explicit interactions in video mediated collaboration

In this paper we report the results of a study comparing implicit-only and explicit-only interactions in a collaborative, video-mediated task with shared content. Expanding on earlier work which has typically only evaluated how implicit interaction can augment primarily explicit systems, we report issues surrounding control, anxiousness and negotiation in the context of video mediated collaboration. We conclude that implicit interaction has the potential to improve collaborative work, but that there are a multitude of issues that must first be negotiated.

A Distributed Robotic Vision Service

Robotic vision is limited by line of sight and onboard camera capabilities. Robots can acquire video or images from remote cameras, but processing additional data has a computational burden. This paper applies the Distributed Robotic Vision Service, DRVS, to robot path planning using data outside line-of-sight of the robot. DRVS implements a distributed visual object detection service to distributes the computation to remote camera nodes with processing capabilities. Robots request task-specific object detection from DRVS by specifying a geographic region of interest and object type. The remote camera nodes perform the visual processing and send the high-level object information to the robot. Additionally, DRVS relieves robots of sensor discovery by dynamically distributing object detection requests to remote camera nodes. Tested over two different indoor path planning tasks DRVS showed dramatic reduction in mobile robot compute load and wireless network utilization.

Human action recognition from video sequences

This PhD research has proposed new machine learning techniques to improve human action recognition based on local features. Several novel video representation and classification techniques have been proposed to increase the performance with lower computational complexity. The major contributions are the construction of new feature representation techniques, based on advanced machine learning techniques such as multiple instance dictionary learning, Latent Dirichlet Allocation (LDA) and Sparse coding. A Binary-tree based classification technique was also proposed to deal with large amounts of action categories. These techniques are not only improving the classification accuracy with constrained computational resources but are also robust to challenging environmental conditions. These developed techniques can be easily extended to a wide range of video applications to provide near real-time performance.