Activity modelling in crowded environments : a soft decision approach

Probabilistic topic models have recently been used for activity analysis in video processing, due to their strong capacity to model both local activities and interactions in crowded scenes. In those applications, a video sequence is divided into a collection of uniform non-overlaping video clips, and the high dimensional continuous inputs are quantized into a bag of discrete visual words. The hard division of video clips, and hard assignment of visual words leads to problems when an activity is split over multiple clips, or the most appropriate visual word for quantization is unclear. In this paper, we propose a novel algorithm, which makes use of a soft histogram technique to compensate for the loss of information in the quantization process; and a soft cut technique in the temporal domain to overcome problems caused by separating an activity into two video clips. In the detection process, we also apply a soft decision strategy to detect unusual events.We show that the proposed soft decision approach outperforms its hard decision counterpart in both local and global activity modelling.

Assessing population limits : a carrying capacity approach to planning

While purporting to enhance Australia’s sustainability, the federal government’s Population Strategy rejects the assessment of the limiting factors to future population growth, thus avoiding urgent threshold issues such as resource depletion and environmental destruction. A more forward-thinking and whole-system perspective would assess and incorporate critical biophysical limits into governance processes with suitable prioritisation. It would encourage communities to examine their individual and collective responsibilities in the context of these limits in order to most equitably optimise outcomes; and it would employ both a resource-based examination of minimum population requirements, and an impact-based assessment of maximum thresholds. This carrying capacity approach to planning could help guide society towards a more sustainable future.

Compressive sensing for gait recognition

Compressive Sensing (CS) is a popular signal processing technique, that can exactly reconstruct a signal given a small number of random projections of the original signal, provided that the signal is sufficiently sparse. We demonstrate the applicability of CS in the field of gait recognition as a very effective dimensionality reduction technique, using the gait energy image (GEI) as the feature extraction process. We compare the CS based approach to the principal component analysis (PCA) and show that the proposed method outperforms this baseline, particularly under situations where there are appearance changes in the subject. Applying CS to the gait features also avoids the need to train the models, by using a generalised random projection.

Visual voice activity detection using frontal versus profile views

Visual activity detection of lip movements can be used to overcome the poor performance of voice activity detection based solely in the audio domain, particularly in noisy acoustic conditions. However, most of the research conducted in visual voice activity detection (VVAD) has neglected addressing variabilities in the visual domain such as viewpoint variation. In this paper we investigate the effectiveness of the visual information from the speaker’s frontal and profile views (i.e left and right side views) for the task of VVAD. As far as we are aware, our work constitutes the first real attempt to study this problem. We describe our visual front end approach and the Gaussian mixture model (GMM) based VVAD framework, and report the experimental results using the freely available CUAVE database. The experimental results show that VVAD is indeed possible from profile views and we give a quantitative comparison of VVAD based on frontal and profile views The results presented are useful in the development of multi-modal Human Machine Interaction (HMI) using a single camera, where the speaker’s face may not always be frontal.

A multi-resolution image alignment technique based on direct methods for pose estimation of aerial vehicles

In this paper, we seek to expand the use of direct methods in real-time applications by proposing a vision-based strategy for pose estimation of aerial vehicles. The vast majority of approaches make use of features to estimate motion. Conversely, the strategy we propose is based on a MR (Multi- Resolution) implementation of an image registration technique (Inverse Compositional Image Alignment ICIA) using direct methods. An on-board camera in a downwards-looking configuration, and the assumption of planar scenes, are the bases of the algorithm. The motion between frames (rotation and translation) is recovered by decomposing the frame-to-frame homography obtained by the ICIA algorithm applied to a patch that covers around the 80% of the image. When the visual estimation is required (e.g. GPS drop-out), this motion is integrated with the previous known estimation of the vehicles’ state, obtained from the on-board sensors (GPS/IMU), and the subsequent estimations are based only on the vision-based motion estimations. The proposed strategy is tested with real flight data in representative stages of a flight: cruise, landing, and take-off, being two of those stages considered critical: take-off and landing. The performance of the pose estimation strategy is analyzed by comparing it with the GPS/IMU estimations. Results show correlation between the visual estimation obtained with the MR-ICIA and the GPS/IMU data, that demonstrate that the visual estimation can be used to provide a good approximation of the vehicle’s state when it is required (e.g. GPS drop-outs). In terms of performance, the proposed strategy is able to maintain an estimation of the vehicle’s state for more than one minute, at real-time frame rates based, only on visual information.

Practical improvements to simultaneous computation of multi-view geometry and radial lens distortion

This paper discusses practical issues related to the use of the division model for lens distortion in multi-view geometry computation. A data normalisation strategy is presented, which has been absent from previous discussions on the topic. The convergence properties of the Rectangular Quadric Eigenvalue Problem solution for computing division model distortion are examined. It is shown that the existing method can require more than 1000 iterations when dealing with severe distortion. A method is presented for accelerating convergence to less than 10 iterations for any amount of distortion. The new method is shown to produce equivalent or better results than the existing method with up to two orders of magnitude reduction in iterations. Through detailed simulation it is found that the number of data points used to compute geometry and lens distortion has a strong influence on convergence speed and solution accuracy. It is recommended that more than the minimal number of data points be used when computing geometry using a robust estimator such as RANSAC. Adding two to four extra samples improves the convergence rate and accuracy sufficiently to compensate for the increased number of samples required by the RANSAC process.

Negative determinant of Hessian features

Local image feature extractors that select local maxima of the determinant of Hessian function have been shown to perform well and are widely used. This paper introduces the negative local minima of the determinant of Hessian function for local feature extraction. The properties and scale-space behaviour of these features are examined and found to be desirable for feature extraction. It is shown how this new feature type can be implemented along with the existing local maxima approach at negligible extra processing cost. Applications to affine covariant feature extraction and sub-pixel precise corner extraction are demonstrated. Experimental results indicate that the new corner detector is more robust to image blur and noise than existing methods. It is also accurate for a broader range of corner geometries. An affine covariant feature extractor is implemented by combining the minima of the determinant of Hessian with existing scale and shape adaptation methods. This extractor can be implemented along side the existing Hessian maxima extractor simply by finding both minima and maxima during the initial extraction stage. The minima features increase the number of correspondences by two to four fold. The additional minima features are very distinct from the maxima features in descriptor space and do not make the matching process more ambiguous.

Drink driving after the first offence: Characteristics of offenders who continue to drink and drive

Drink driving remains a significant problem on Australian roads, with about a quarter to a third of fatal crashes involving drivers or riders who have a BAC of 0.05 or greater. Last available data in the state of Queensland (2003) of the major factors involved in road fatalities and injuries indicated that alcohol and drugs were noted as one of the contributing factors in 38% of fatalities and 11% of all crashes, making it the highest single contributing factor to road fatalities. Until this point, there has been little information about first time offenders as a group, but it is known that offenders typically are not first time drink drivers but rather ‘first time apprehended’, in that most have engaged in drink driving in the years leading to the first offence. This paper follows 89 first time drink driving offenders who were interviewed at the time of court mention and followed up around 6 months following the court hearing. Of the offenders, 27% reported to have driven over the limit in the time between initial contact and follow up. The paper demonstrates the characteristics and offending patterns of first offenders who engaged in drink driving following conviction and those who didn’t, providing suggestions on how to target those at high risk for the behaviour and subsequent offending.

Sociopathic attitudes to road safety

Injuries and deaths due to unsafe driving practices are a substantial health and socioeconomic burden to the community. Young socially disadvantaged males who are involved in a lifestyle of risky behaviour, crime and motor vehicle accidents seem unaffected by educational campaigns to improve safer driving. The aim is to develop a driving and social behavioural profile that may explain the lack of effectiveness of road safety advertising and suggest ways to refine educational strategies to reduce the risky lifestyle and associated harms among those most vulnerable, the 15-25 year olds. The procedure involved a quantitative and qualitative analysis through questionnaires, surveys and focus groups involving a comparison of populations (n = 668) by age, gender and socioeconomic status in three discrete Australian sites. Information gathered included issues related to road safety awareness, knowledge of advertising, personal and peer group attitudes as well as driving and life style history. The results indicate that within the community a highly visible profile of strong anti-social road safety activities by an educationally and economically disadvantaged sub-culture exists and this group seem impervious to road safety advertising and education initiatives. As the overall unsafe driving and risky antisocial behaviour is significant among 15-25 year olds within the community the solution is seen to be community based. A long-term (five to ten year) program has been posited; promoting community partnerships through consultative and local action committees at all levels creating locally designed formal and informal educational and mutual support programs.

Women, drinking and aggression on a night out: Do girls just wanna have fun?

Alcohol misuse and violence is a major public safety concern. Although the extent and nature of alcohol-related violence has been examined there is a paucity of research surrounding the ongoing construction and re-construction of gender identity and its relationship to aggression and alcohol consumption. A social constructionist perspective was used to explore women’s perceptions and experiences of drinking alcohol and incidents of public violence and aggression. Two methods were used. Firstly, an exploratory study consisting of three in-depth interviews and three focus groups to examine the ideas women constructed in relation to their experiences; and further, an online survey to explore self-reported drinking patterns among men and women. The main themes emerging from the qualitative material were ‘planned drinking to excess’ (incorporating the rituals of a ‘pre-drink’ routine), and perceptions of appropriate feminine behaviour (particularly in relation to excessive drinking and alcohol related aggression in and around licensed venues). The survey data indicated that men continue to consume more alcohol and at higher levels than women, while women’s involvement in aggressive incidents on a night out being similar to that of men. Both genders considered that women’s involvement in aggressive incidents in and around licensed venues as ‘unfeminine’. Understanding drinking as a socially constructed activity adds to our understanding of the meaning of drinking for women, and in particular, young women. This perspective may allow more focussed initiatives to address the social and health related harms associated with drinking in and around licensed venues.

Saving bitrate vs. pleasing users : where is the break-even point in mobile video quality?

This paper presents a comprehensive study to find the most efficient bitrate requirement to deliver mobile video that optimizes bandwidth, while at the same time maintains good user viewing experience. In the study, forty participants were asked to choose the lowest quality video that would still provide for a comfortable and long-term viewing experience, knowing that higher video quality is more expensive and bandwidth intensive. This paper proposes the lowest pleasing bitrates and corresponding encoding parameters for five different content types: cartoon, movie, music, news and sports. It also explores how the lowest pleasing quality is influenced by content type, image resolution, bitrate, and user gender, prior viewing experience, and preference. In addition, it analyzes the trajectory of users’ progression while selecting the lowest pleasing quality. The findings reveal that the lowest bitrate requirement for a pleasing viewing experience is much higher than that of the lowest acceptable quality. Users’ criteria for the lowest pleasing video quality are related to the video’s content features, as well as its usage purpose and the user’s personal preferences. These findings can provide video providers guidance on what quality they should offer to please mobile users.

Evaluating automatic road detection across a large aerial imagery collection

The automated extraction of roads from aerial imagery can be of value for tasks including mapping, surveillance and change detection. Unfortunately, there are no public databases or standard evaluation protocols for evaluating these techniques. Many techniques are further hindered by a reliance on manual initialisation, making large scale application of the techniques impractical. In this paper, we present a public database and evaluation protocol for the evaluation of road extraction algorithms, and propose an improved automatic seed finding technique to initialise road extraction, based on a combination of geometric and colour features.

An exploration of feature detector performance in the thermal-infrared modality

Thermal-infrared images have superior statistical properties compared with visible-spectrum images in many low-light or no-light scenarios. However, a detailed understanding of feature detector performance in the thermal modality lags behind that of the visible modality. To address this, the first comprehensive study on feature detector performance on thermal-infrared images is conducted. A dataset is presented which explores a total of ten different environments with a range of statistical properties. An investigation is conducted into the effects of several digital and physical image transformations on detector repeatability in these environments. The effect of non-uniformity noise, unique to the thermal modality, is analyzed. The accumulation of sensor non-uniformities beyond the minimum possible level was found to have only a small negative effect. A limiting of feature counts was found to improve the repeatability performance of several detectors. Most other image transformations had predictable effects on feature stability. The best-performing detector varied considerably depending on the nature of the scene and the test.

Wilkins Hill : on the cusp of meaning

If contemporary artworks are often considered to be puzzles or riddles, then Wilkins Hill take this to a new level. Their recent exhibition Windows impersonating other windows, confronts viewers with an extremely ludic configuration: a spa bath full of almonds, towel racks placed before photos of Martin Heidegger distorted in neat grids, a video of a water tower in a Hamburg park, wooden cut-out speech bubbles and monitors that continuously play interviews with the artists themselves. What does it all mean?

Composite SaaS placement and resource optimization in Cloud computing using evolutionary algorithms

Software as a Service (SaaS) is gaining more and more attention from software users and providers recently. This has raised many new challenges to SaaS providers in providing better SaaSes that suit everyone needs at minimum costs. One of the emerging approaches in tackling this challenge is by delivering the SaaS as a composite SaaS. Delivering it in such an approach has a number of benefits, including flexible offering of the SaaS functions and decreased cost of subscription for users. However, this approach also introduces new problems for SaaS resource management in a Cloud data centre. We present the problem of composite SaaS resource management in Cloud data centre, specifically on its initial placement and resource optimization problems aiming at improving the SaaS performance based on its execution time as well as minimizing the resource usage. Our approach differs from existing literature because it addresses the problems resulting from composite SaaS characteristics, where we focus on the SaaS requirements, constraints and interdependencies. The problems are tackled using evolutionary algorithms. Experimental results demonstrate the efficiency and the scalability of the proposed algorithms.