Image segmentation and pose estimation of humans in video

This thesis introduces improved techniques towards automatically estimating the pose of humans from video. It examines a complete workflow to estimating pose, from the segmentation of the raw video stream to extract silhouettes, to using the silhouettes in order to determine the relative orientation of parts of the human body. The proposed segmentation algorithms have improved performance and reduced complexity, while the pose estimation shows superior accuracy during difficult cases of self occlusion.

Odometry-driven inference to link multiple exemplars of a location

A major challenge for robot localization and mapping systems is maintaining reliable operation in a changing environment. Vision-based systems in particular are susceptible to changes in illumination and weather, and the same location at another time of day may appear radically different to a system using a feature-based visual localization system. One approach for mapping changing environments is to create and maintain maps that contain multiple representations of each physical location in a topological framework or manifold. However, this requires the system to be able to correctly link two or more appearance representations to the same spatial location, even though the representations may appear quite dissimilar. This paper proposes a method of linking visual representations from the same location without requiring a visual match, thereby allowing vision-based localization systems to create multiple appearance representations of physical locations. The most likely position on the robot path is determined using particle filter methods based on dead reckoning data and recent visual loop closures. In order to avoid erroneous loop closures, the odometry-based inferences are only accepted when the inferred path's end point is confirmed as correct by the visual matching system. Algorithm performance is demonstrated using an indoor robot dataset and a large outdoor camera dataset.

Effectiveness of MED for Fault Diagnosis in Roller Bearings

Diagnostics of rolling element bearings is usually performed by means of vibration signals measured by accelerometers placed in the proximity of the bearing under investigation. The aim is to monitor the integrity of the bearing components, in order to avoid catastrophic failures, or to implement condition based maintenance strategies. In particular, the trend in this field is to combine in a single algorithm different signal-enhancement and signal-analysis techniques. Among the first ones, Minimum Entropy Deconvolution (MED) has been pointed out as a key tool able to highlight the effect of a possible damage in one of the bearing components within the vibration signal. This paper presents the application of this technique to signals collected on a simple test-rig, able to test damaged industrial roller bearings in different working conditions. The effectiveness of the technique has been tested, comparing the results of one undamaged bearing with three bearings artificially damaged in different locations, namely on the inner race, outer race and rollers. Since MED performances are dependent on the filter length, the most suitable value of this parameter is defined on the basis of both the application and measured signals. This represents an original contribution of the paper.

Traffic state estimation from partial Bluetooth and volume observations : case study in the Brisbane metropolitan area

The application of the Bluetooth (BT) technology to transportation has been enabling researchers to make accurate travel time observations, in freeway and arterial roads. The Bluetooth traffic data are generally incomplete, for they only relate to those vehicles that are equipped with Bluetooth devices, and that are detected by the Bluetooth sensors of the road network. The fraction of detected vehicles versus the total number of transiting vehicles is often referred to as Bluetooth Penetration Rate (BTPR). The aim of this study is to precisely define the spatio-temporal relationship between the quantities that become available through the partial, noisy BT observations; and the hidden variables that describe the actual dynamics of vehicular traffic. To do so, we propose to incorporate a multi- class traffic model into a Sequential Montecarlo Estimation algorithm. Our framework has been applied for the empirical travel time investigations into the Brisbane Metropolitan region.

Slicing big data - Twitter, gambling and time sensitive information

Big Data presents many challenges related to volume, whether one is interested in studying past datasets or, even more problematically, attempting to work with live streams of data. The most obvious challenge, in a ‘noisy’ environment such as contemporary social media, is to collect the pertinent information; be that information for a specific study, tweets which can inform emergency services or other responders to an ongoing crisis, or give an advantage to those involved in prediction markets. Often, such a process is iterative, with keywords and hashtags changing with the passage of time, and both collection and analytic methodologies need to be continually adapted to respond to this changing information. While many of the data sets collected and analyzed are preformed, that is they are built around a particular keyword, hashtag, or set of authors, they still contain a large volume of information, much of which is unnecessary for the current purpose and/or potentially useful for future projects. Accordingly, this panel considers methods for separating and combining data to optimize big data research and report findings to stakeholders. The first paper considers possible coding mechanisms for incoming tweets during a crisis, taking a large stream of incoming tweets and selecting which of those need to be immediately placed in front of responders, for manual filtering and possible action. The paper suggests two solutions for this, content analysis and user profiling. In the former case, aspects of the tweet are assigned a score to assess its likely relationship to the topic at hand, and the urgency of the information, whilst the latter attempts to identify those users who are either serving as amplifiers of information or are known as an authoritative source. Through these techniques, the information contained in a large dataset could be filtered down to match the expected capacity of emergency responders, and knowledge as to the core keywords or hashtags relating to the current event is constantly refined for future data collection. The second paper is also concerned with identifying significant tweets, but in this case tweets relevant to particular prediction market; tennis betting. As increasing numbers of professional sports men and women create Twitter accounts to communicate with their fans, information is being shared regarding injuries, form and emotions which have the potential to impact on future results. As has already been demonstrated with leading US sports, such information is extremely valuable. Tennis, as with American Football (NFL) and Baseball (MLB) has paid subscription services which manually filter incoming news sources, including tweets, for information valuable to gamblers, gambling operators, and fantasy sports players. However, whilst such services are still niche operations, much of the value of information is lost by the time it reaches one of these services. The paper thus considers how information could be filtered from twitter user lists and hash tag or keyword monitoring, assessing the value of the source, information, and the prediction markets to which it may relate. The third paper examines methods for collecting Twitter data and following changes in an ongoing, dynamic social movement, such as the Occupy Wall Street movement. It involves the development of technical infrastructure to collect and make the tweets available for exploration and analysis. A strategy to respond to changes in the social movement is also required or the resulting tweets will only reflect the discussions and strategies the movement used at the time the keyword list is created — in a way, keyword creation is part strategy and part art. In this paper we describe strategies for the creation of a social media archive, specifically tweets related to the Occupy Wall Street movement, and methods for continuing to adapt data collection strategies as the movement’s presence in Twitter changes over time. We also discuss the opportunities and methods to extract data smaller slices of data from an archive of social media data to support a multitude of research projects in multiple fields of study. The common theme amongst these papers is that of constructing a data set, filtering it for a specific purpose, and then using the resulting information to aid in future data collection. The intention is that through the papers presented, and subsequent discussion, the panel will inform the wider research community not only on the objectives and limitations of data collection, live analytics, and filtering, but also on current and in-development methodologies that could be adopted by those working with such datasets, and how such approaches could be customized depending on the project stakeholders.

Short-term traffic volume forecasting : a k-nearest neighbor approach enhanced by constrained linearly sewing principle component algorithm

To enhance the performance of the k-nearest neighbors approach in forecasting short-term traffic volume, this paper proposed and tested a two-step approach with the ability of forecasting multiple steps. In selecting k-nearest neighbors, a time constraint window is introduced, and then local minima of the distances between the state vectors are ranked to avoid overlappings among candidates. Moreover, to control extreme values’ undesirable impact, a novel algorithm with attractive analytical features is developed based on the principle component. The enhanced KNN method has been evaluated using the field data, and our comparison analysis shows that it outperformed the competing algorithms in most cases.

Pattern-based topics for document modelling in information filtering

Many mature term-based or pattern-based approaches have been used in the field of information filtering to generate users’ information needs from a collection of documents. A fundamental assumption for these approaches is that the documents in the collection are all about one topic. However, in reality users’ interests can be diverse and the documents in the collection often involve multiple topics. Topic modelling, such as Latent Dirichlet Allocation (LDA), was proposed to generate statistical models to represent multiple topics in a collection of documents, and this has been widely utilized in the fields of machine learning and information retrieval, etc. But its effectiveness in information filtering has not been so well explored. Patterns are always thought to be more discriminative than single terms for describing documents. However, the enormous amount of discovered patterns hinder them from being effectively and efficiently used in real applications, therefore, selection of the most discriminative and representative patterns from the huge amount of discovered patterns becomes crucial. To deal with the above mentioned limitations and problems, in this paper, a novel information filtering model, Maximum matched Pattern-based Topic Model (MPBTM), is proposed. The main distinctive features of the proposed model include: (1) user information needs are generated in terms of multiple topics; (2) each topic is represented by patterns; (3) patterns are generated from topic models and are organized in terms of their statistical and taxonomic features, and; (4) the most discriminative and representative patterns, called Maximum Matched Patterns, are proposed to estimate the document relevance to the user’s information needs in order to filter out irrelevant documents. Extensive experiments are conducted to evaluate the effectiveness of the proposed model by using the TREC data collection Reuters Corpus Volume 1. The results show that the proposed model significantly outperforms both state-of-the-art term-based models and pattern-based models

Mawson the astrobiologist rover : towards automatic recognition of stromatolites

This work aims at developing a planetary rover capable of acting as an assistant astrobiologist: making a preliminary analysis of the collected visual images that will help to make better use of the scientists time by pointing out the most interesting pieces of data. This paper focuses on the problem of detecting and recognising particular types of stromatolites. Inspired by the processes actual astrobiologists go through in the field when identifying stromatolites, the processes we investigate focus on recognising characteristics associated with biogenicity. The extraction of these characteristics is based on the analysis of geometrical structure enhanced by passing the images of stromatolites into an edge-detection filter and its Fourier Transform, revealing typical spatial frequency patterns. The proposed analysis is performed on both simulated images of stromatolite structures and images of real stromatolites taken in the field by astrobiologists.

Decentralized voltage support in a Low Voltage feeder by droop based voltage controlled PVs

Voltage drop at network peak hours is a significant power quality problem in Low Voltage (LV) distribution feeders. Recently, voltage rise due to high penetration of Photovoltaic cells (PVs) has been creating a new power quality problem during noon periods. In this paper, a voltage control strategy is proposed for the household installed PVs to regulate the voltage along the LV feeder. For this purpose, each PV is controlled to exchange reactive power with the grid. A droop control method is utilized to coordinate the reactive power exchange of each PV. The proposed method is a decentralized local voltage support since it is based on only local measurements and does not require any communication with other PVs. The required converter and filter structure and control algorithms are proposed to ensure the dynamic performance of the system. The study focuses on 3-phase PVs. The network is studied at network peak and off-peak periods, separately. The efficacy of the proposed voltage support concept is verified through numerical and dynamic analyses with MATLAB and PSCAD/EMTDC.

Management [5th Asia-Pacific Edition]

The fifth edition of this text has been thoroughly updated, continuing its strong emphasis on the importance of the Asian region to contemporary Australian and New Zealand organisations. Many Asian case examples are featured to illustrate key management concepts, and these provide a useful basis for comparison with management practices in Australia and New Zealand. Numerous practical examples throughout the text highlight contemporary management issues, such as: •workplace diversity •sustainability •ethics/corporate social responsibility •the impact of technology •innovation in the workplace •globalisation •employee engagement •flexible working arrangements •work-life balance •generational issues in the workplace •skills shortages in various industries •the importance of effective employee recruitment and training •organisational culture •workforce flexibility and casualisation •the ‘24/7’ nature of contemporary communication technology, including social media •outsourcing Management, 5th Asia Pacific edition, has also retained the features that have made previous editions so popular with students and lecturers, including the Career Readiness Workbook activities at the end of the book, and the accompanying Interactive Study Guide with its vast array of multimedia resources.

Sensor Network Based AUV Localisation

The operation of Autonomous Underwater Vehicles (AUVs) within underwater sensor network fields provides an opportunity to reuse the network infrastructure for long baseline localisation of the AUV. Computationally efficient localisation can be accomplished using off-the-shelf hardware that is comparatively inexpensive and which could already be deployed in the environment for monitoring purposes. This paper describes the development of a particle filter based localisation system which is implemented onboard an AUV in real-time using ranging information obtained from an ad-hoc underwater sensor network. An experimental demonstration of this approach was conducted in a lake with results presented illustrating network communication and localisation performance.

GNSS ambiguity resolution with controllable failure rate for long baseline network RTK

Many large-scale GNSS CORS networks have been deployed around the world to support various commercial and scientific applications. To make use of these networks for real-time kinematic positioning services, one of the major challenges is the ambiguity resolution (AR) over long inter-station baselines in the presence of considerable atmosphere biases. Usually, the widelane ambiguities are fixed first, followed by the procedure of determination of the narrowlane ambiguity integers based on the ionosphere-free model in which the widelane integers are introduced as known quantities. This paper seeks to improve the AR performance over long baseline through efficient procedures for improved float solutions and ambiguity fixing. The contribution is threefold: (1) instead of using the ionosphere-free measurements, the absolute and/or relative ionospheric constraints are introduced in the ionosphere-constrained model to enhance the model strength, thus resulting in the better float solutions; (2) the realistic widelane ambiguity precision is estimated by capturing the multipath effects due to the observation complexity, leading to improvement of reliability of widelane AR; (3) for the narrowlane AR, the partial AR for a subset of ambiguities selected according to the successively increased elevation is applied. For fixing the scalar ambiguity, an error probability controllable rounding method is proposed. The established ionosphere-constrained model can be efficiently solved based on the sequential Kalman filter. It can be either reduced to some special models simply by adjusting the variances of ionospheric constraints, or extended with more parameters and constraints. The presented methodology is tested over seven baselines of around 100 km from USA CORS network. The results show that the new widelane AR scheme can obtain the 99.4 % successful fixing rate with 0.6 % failure rate; while the new rounding method of narrowlane AR can obtain the fix rate of 89 % with failure rate of 0.8 %. In summary, the AR reliability can be efficiently improved with rigorous controllable probability of incorrectly fixed ambiguities.

Outdoor flight testing of a pole inspection UAV incorporating high-speed vision

We present a pole inspection system for outdoor environments comprising a high-speed camera on a vertical take-off and landing (VTOL) aerial platform. The pole inspection task requires a vehicle to fly close to a structure while maintaining a fixed stand-off distance from it. Typical GPS errors make GPS-based navigation unsuitable for this task however. When flying outdoors a vehicle is also affected by aerodynamics disturbances such as wind gusts, so the onboard controller must be robust to these disturbances in order to maintain the stand-off distance. Two problems must therefor be addressed: fast and accurate state estimation without GPS, and the design of a robust controller. We resolve these problems by a) performing visual + inertial relative state estimation and b) using a robust line tracker and a nested controller design. Our state estimation exploits high-speed camera images (100Hz) and 70Hz IMU data fused in an Extended Kalman Filter (EKF). We demonstrate results from outdoor experiments for pole-relative hovering, and pole circumnavigation where the operator provides only yaw commands. Lastly, we show results for image-based 3D reconstruction and texture mapping of a pole to demonstrate the usefulness for inspection tasks.

Indexing without spam

The presence of spam in a document ranking is a major issue for Web search engines. Common approaches that cope with spam remove from the document rankings those pages that are likely to contain spam. These approaches are implemented as post-retrieval processes, that filter out spam pages only after documents have been retrieved with respect to a user’s query. In this paper we suggest to remove spam pages at indexing time, therefore obtaining a pruned index that is virtually “spam-free”. We investigate the benefits of this approach from three points of view: indexing time, index size, and retrieval performances. Not surprisingly, we found that the strategy decreases both the time required by the indexing process and the space required for storing the index. Surprisingly instead, we found that by considering a spam-pruned version of a collection’s index, no difference in retrieval performance is found when compared to that obtained by traditional post-retrieval spam filtering approaches.

Security evaluation of Rakaposhi Stream Cipher

Rakaposhi is a synchronous stream cipher, which uses three main components: a non-linear feedback shift register (NLFSR), a dynamic linear feedback shift register (DLFSR) and a non-linear filtering function (NLF). NLFSR consists of 128 bits and is initialised by the secret key K. DLFSR holds 192 bits and is initialised by an initial vector (IV). NLF takes 8-bit inputs and returns a single output bit. The work identifies weaknesses and properties of the cipher. The main observation is that the initialisation procedure has the so-called sliding property. The property can be used to launch distinguishing and key recovery attacks. The distinguisher needs four observations of the related (K,IV) pairs. The key recovery algorithm allows to discover the secret key K after observing 29 pairs of (K,IV). Based on the proposed related-key attack, the number of related (K,IV) pairs is 2(128 + 192)/4 pairs. Further the cipher is studied when the registers enter short cycles. When NLFSR is set to all ones, then the cipher degenerates to a linear feedback shift register with a non-linear filter. Consequently, the initial state (and Secret Key and IV) can be recovered with complexity 263.87. If DLFSR is set to all zeros, then NLF reduces to a low non-linearity filter function. As the result, the cipher is insecure allowing the adversary to distinguish it from a random cipher after 217 observations of keystream bits. There is also the key recovery algorithm that allows to find the secret key with complexity 2 54.