Tracking people in 3D using position, size and shape

This paper presents a prototype tracking system for tracking people in enclosed indoor environments where there is a high rate of occlusions. The system uses a stereo camera for acquisition, and is capable of disambiguating occlusions using a combination of depth map analysis, a two step ellipse fitting people detection process, the use of motion models and Kalman filters and a novel fit metric, based on computationally simple object statistics. Testing shows that our fit metric outperforms commonly used position based metrics and histogram based metrics, resulting in more accurate tracking of people.

Person tracking using motion detection and optical flow

Person tracking systems to date have either relied on motion detection or optical flow as a basis for person detection and tracking. As yet, systems have not been developed that utilise both these techniques. We propose a person tracking system that uses both, made possible by a novel hybrid optical flow-motion detection technique that we have developed. This provides the system with two methods of person detection, helping to avoid missed detections and the need to predict position, which can lead to errors in tracking and mistakes when handling occlusion situations. Our results show that our system is able to track people accurately, with an average error less than four pixels, and that our system outperforms the current CAVIAR benchmark system.

Adaptive optical flow for person tracking

Person tracking systems are dependent on being able to locate a person accurately across a series of frames. Optical flow can be used to segment a moving object from a scene, provided the expected velocity of the moving object is known; but successful detection also relies on being able segment the background. A problem with existing optical flow techniques is that they don’t discriminate the foreground from the background, and so often detect motion (and thus the object) in the background. To overcome this problem, we propose a new optical flow technique, that is based upon an adaptive background segmentation technique, which only determines optical flow in regions of motion. This technique has been developed with a view to being used in surveillance systems, and our testing shows that for this application it is more effective than other standard optical flow techniques.

Advertising education in Australia: Looking back to the future

In Australia, advertising is a $13 billion industry which needs a supply of suitably skilled employees. Over the years, advertising education has developed from vocational based courses to degree courses across the country. This paper uses diffusion theory and various secondary sources and interviews to observe the development of advertising education in Australia from its early past, to its current day tertiary offerings, to discussing the issues that are arising in the near future. Six critical issues are identified, along with observations about the challenges and opportunities within Australia advertising education. By looking back to the future, it is hoped that this historical review provides lessons for other countries of similar educational structure or background, or even other marketing communication disciplines on a similar evolutionary path.

Wrong way, go back! Negotiating success in industry-based research

Literature addressing methodological issues in organisational research is extensive and multidisciplinary, encompassing debates about methodological choices, data-collection techniques, epistemological approaches and statistical procedures. However, little scholarship has tackled an important aspect of organisational research that precedes decisions about data collection and analysis – access to the organisations themselves, including the people, processes and documents within them. This chapter looks at organisational access through the experiences of three research fellows in the course of their work with their respective industry partners. In doing so, it reveals many of the challenges and changing opportunities associated with access to organisations, which are rarely explicitly addressed, but often assumed, in traditional methods texts and journal publications. Although the level of access granted varied somewhat across the projects at different points in time and according to different organisational contexts, we shared a number of core and consistent experiences in attempting to collect data and implement strategies.

Prevalence and correlates of low back pain among occupational therapy students in Northern Queensland

Background: Although low back pain (LBP) is an important issue for the health profession, few studies have examined LBP among occupational therapy students. Purpose. To investigate the prevalence and distribution of LBP, its adverse sequelae; and to identify potential risk factors.----------- Methods: In 2005, a self-reported questionnaire was administered to occupational therapy students in Northern Queensland.----------- Findings: The 12-month period-prevalence of LBP was 64.6%. Nearly half (46.9%) had experienced pain for over 2 days, 38.8% suffered LBP that affected their daily lives, and 24.5% had sought medical treatment. The prevalence of LBP ranged from 45.5 to 77.1% (p=0.004), while the prevalence of LBP symptoms persisting longer than two days was 34.1 to 62.5% (p=0.020). Logistic regression analysis indicated that year of study and weekly computer usage were statistically-significant LBP risk factors.----------- Implications: The occupational therapy profession will need to further investigate the high prevalence of student LBP identified in this study.

Wet potential

Water is so fundamental to everything that it is almost impossible to meaningfully conceptualise it, which is why it forms the basis of pretty much everything. To suggest that landscape architecture has some sort of privilege with it would be deluded. But, as alchemists of “the world”, we are both expected to deal with it professionally, as well as being forced to do so practically in making anything real, built in that same “world”. When people use words too much, that is the signifiers of things in sound, they become a kind of conceptual short hand to what they are referring to. You can hear this short hand when they use the word, as it gets grammatically dealt with differently – it becomes a conceptual object – a different type of noun. Water is one of these words, and as a supervisor I have almost universally seen students refer to it like this, by the end of their projects, and then have to force themselves to reconsider what it was about water that made them interested in water in the first place. This process is a transition of ideas and technology and technique, and will be the subject of this essay, tracking students responses to the weird substance in design subjects I have taught or projects I have supervised at RMIT since 1997, to and from and then again back to the qualities and issues of water for people generally, and landscape architecture in particular.

Evaluation of multiple sewage-associated bacteroides PCR markers for sewage pollution tracking

The host specificity of the five published sewage-associated Bacteroides markers (i.e., HF183, BacHum, HuBac, BacH and Human-Bac) was evaluated in Southeast Queensland, Australia by testing fecal DNA samples (n = 186) from 11 animal species including human fecal samples collected via influent to a sewage treatment plant (STP). All human fecal samples (n = 50) were positive for all five markers indicating 100% sensitivity of these markers. The overall specificity of the HF183 markers to differentiate between humans and animals was 99%. The specificities of the BacHum and BacH markers were > 94%, suggesting that these markers are suitable for sewage pollution in environmental waters in Australia. The BacHum (i.e., 63% specificity) and Human-Bac (i.e., 79% specificity) markers performed poorly in distinguishing between the sources of human and animal fecal samples. It is recommended that the specificity of the sewage-associated markers must be rigorously tested prior to its application to identify the sources of fecal pollution in environmental waters.

Improved detection and tracking of objects in surveillance video

Surveillance networks are typically monitored by a few people, viewing several monitors displaying the camera feeds. It is then very difficult for a human operator to effectively detect events as they happen. Recently, computer vision research has begun to address ways to automatically process some of this data, to assist human operators. Object tracking, event recognition, crowd analysis and human identification at a distance are being pursued as a means to aid human operators and improve the security of areas such as transport hubs. The task of object tracking is key to the effective use of more advanced technologies. To recognize an event people and objects must be tracked. Tracking also enhances the performance of tasks such as crowd analysis or human identification. Before an object can be tracked, it must be detected. Motion segmentation techniques, widely employed in tracking systems, produce a binary image in which objects can be located. However, these techniques are prone to errors caused by shadows and lighting changes. Detection routines often fail, either due to erroneous motion caused by noise and lighting effects, or due to the detection routines being unable to split occluded regions into their component objects. Particle filters can be used as a self contained tracking system, and make it unnecessary for the task of detection to be carried out separately except for an initial (often manual) detection to initialise the filter. Particle filters use one or more extracted features to evaluate the likelihood of an object existing at a given point each frame. Such systems however do not easily allow for multiple objects to be tracked robustly, and do not explicitly maintain the identity of tracked objects. This dissertation investigates improvements to the performance of object tracking algorithms through improved motion segmentation and the use of a particle filter. A novel hybrid motion segmentation / optical flow algorithm, capable of simultaneously extracting multiple layers of foreground and optical flow in surveillance video frames is proposed. The algorithm is shown to perform well in the presence of adverse lighting conditions, and the optical flow is capable of extracting a moving object. The proposed algorithm is integrated within a tracking system and evaluated using the ETISEO (Evaluation du Traitement et de lInterpretation de Sequences vidEO - Evaluation for video understanding) database, and significant improvement in detection and tracking performance is demonstrated when compared to a baseline system. A Scalable Condensation Filter (SCF), a particle filter designed to work within an existing tracking system, is also developed. The creation and deletion of modes and maintenance of identity is handled by the underlying tracking system; and the tracking system is able to benefit from the improved performance in uncertain conditions arising from occlusion and noise provided by a particle filter. The system is evaluated using the ETISEO database. The dissertation then investigates fusion schemes for multi-spectral tracking systems. Four fusion schemes for combining a thermal and visual colour modality are evaluated using the OTCBVS (Object Tracking and Classification in and Beyond the Visible Spectrum) database. It is shown that a middle fusion scheme yields the best results and demonstrates a significant improvement in performance when compared to a system using either mode individually. Findings from the thesis contribute to improve the performance of semi-automated video processing and therefore improve security in areas under surveillance.