Visual route recognition with a handful of bits

In this paper we use a sequence-based visual localization algorithm to reveal surprising answers to the question, how much visual information is actually needed to conduct effective navigation? The algorithm actively searches for the best local image matches within a sliding window of short route segments or 'sub-routes', and matches sub-routes by searching for coherent sequences of local image matches. In contract to many existing techniques, the technique requires no pre-training or camera parameter calibration. We compare the algorithm's performance to the state-of-the-art FAB-MAP 2.0 algorithm on a 70 km benchmark dataset. Performance matches or exceeds the state of the art feature-based localization technique using images as small as 4 pixels, fields of view reduced by a factor of 250, and pixel bit depths reduced to 2 bits. We present further results demonstrating the system localizing in an office environment with near 100% precision using two 7 bit Lego light sensors, as well as using 16 and 32 pixel images from a motorbike race and a mountain rally car stage. By demonstrating how little image information is required to achieve localization along a route, we hope to stimulate future 'low fidelity' approaches to visual navigation that complement probabilistic feature-based techniques.

Towards persistent localization and mapping with a continuous appearance-based topology

Appearance-based localization can provide loop closure detection at vast scales regardless of accumulated metric error. However, the computation time and memory requirements of current appearance-based methods scale not only with the size of the environment but also with the operation time of the platform. Additionally, repeated visits to locations will develop multiple competing representations, which will reduce recall performance over time. These properties impose severe restrictions on long-term autonomy for mobile robots, as loop closure performance will inevitably degrade with increased operation time. In this paper we present a graphical extension to CAT-SLAM, a particle filter-based algorithm for appearance-based localization and mapping, to provide constant computation and memory requirements over time and minimal degradation of recall performance during repeated visits to locations. We demonstrate loop closure detection in a large urban environment with capped computation time and memory requirements and performance exceeding previous appearance-based methods by a factor of 2. We discuss the limitations of the algorithm with respect to environment size, appearance change over time and applications in topological planning and navigation for long-term robot operation.

Clustering composite SaaS components in cloud computing using a grouping genetic algorithm

Recently, Software as a Service (SaaS) in Cloud computing, has become more and more significant among software users and providers. To offer a SaaS with flexible functions at a low cost, SaaS providers have focused on the decomposition of the SaaS functionalities, or known as composite SaaS. This approach has introduced new challenges in SaaS resource management in data centres. One of the challenges is managing the resources allocated to the composite SaaS. Due to the dynamic environment of a Cloud data centre, resources that have been initially allocated to SaaS components may be overloaded or wasted. As such, reconfiguration for the components’ placement is triggered to maintain the performance of the composite SaaS. However, existing approaches often ignore the communication or dependencies between SaaS components in their implementation. In a composite SaaS, it is important to include these elements, as they will directly affect the performance of the SaaS. This paper will propose a Grouping Genetic Algorithm (GGA) for multiple composite SaaS application component clustering in Cloud computing that will address this gap. To the best of our knowledge, this is the first attempt to handle multiple composite SaaS reconfiguration placement in a dynamic Cloud environment. The experimental results demonstrate the feasibility and the scalability of the GGA.

Relative entropy rate based model selection for linear hybrid system filters of uncertain nonlinear systems

Hybrid system representations have been exploited in a number of challenging modelling situations, including situations where the original nonlinear dynamics are too complex (or too imprecisely known) to be directly filtered. Unfortunately, the question of how to best design suitable hybrid system models has not yet been fully addressed, particularly in the situations involving model uncertainty. This paper proposes a novel joint state-measurement relative entropy rate based approach for design of hybrid system filters in the presence of (parameterised) model uncertainty. We also present a design approach suitable for suboptimal hybrid system filters. The benefits of our proposed approaches are illustrated through design examples and simulation studies.

In the pursuit of effective affective computing : the relationship between features and registration

For facial expression recognition systems to be applicable in the real world, they need to be able to detect and track a previously unseen person's face and its facial movements accurately in realistic environments. A highly plausible solution involves performing a "dense" form of alignment, where 60-70 fiducial facial points are tracked with high accuracy. The problem is that, in practice, this type of dense alignment had so far been impossible to achieve in a generic sense, mainly due to poor reliability and robustness. Instead, many expression detection methods have opted for a "coarse" form of face alignment, followed by an application of a biologically inspired appearance descriptor such as the histogram of oriented gradients or Gabor magnitudes. Encouragingly, recent advances to a number of dense alignment algorithms have demonstrated both high reliability and accuracy for unseen subjects [e.g., constrained local models (CLMs)]. This begs the question: Aside from countering against illumination variation, what do these appearance descriptors do that standard pixel representations do not? In this paper, we show that, when close to perfect alignment is obtained, there is no real benefit in employing these different appearance-based representations (under consistent illumination conditions). In fact, when misalignment does occur, we show that these appearance descriptors do work well by encoding robustness to alignment error. For this work, we compared two popular methods for dense alignment-subject-dependent active appearance models versus subject-independent CLMs-on the task of action-unit detection. These comparisons were conducted through a battery of experiments across various publicly available data sets (i.e., CK+, Pain, M3, and GEMEP-FERA). We also report our performance in the recent 2011 Facial Expression Recognition and Analysis Challenge for the subject-independent task.

Towards robust night and day place recognition using visible and thermal imaging

The chief challenge facing persistent robotic navigation using vision sensors is the recognition of previously visited locations under different lighting and illumination conditions. The majority of successful approaches to outdoor robot navigation use active sensors such as LIDAR, but the associated weight and power draw of these systems makes them unsuitable for widespread deployment on mobile robots. In this paper we investigate methods to combine representations for visible and long-wave infrared (LWIR) thermal images with time information to combat the time-of-day-based limitations of each sensing modality. We calculate appearance-based match likelihoods using the state-of-the-art FAB-MAP [1] algorithm to analyse loop closure detection reliability across different times of day. We present preliminary results on a dataset of 10 successive traverses of a combined urban-parkland environment, recorded in 2-hour intervals from before dawn to after dusk. Improved location recognition throughout an entire day is demonstrated using the combined system compared with methods which use visible or thermal sensing alone.

Granule mining and its application for network traffic characterization

Decision table and decision rules play an important role in rough set based data analysis, which compress databases into granules and describe the associations between granules. Granule mining was also proposed to interpret decision rules in terms of association rules and multi-tier structure. In this paper, we further extend granule mining to describe the relationships between granules not only by traditional support and confidence, but by diversity and condition diversity as well. Diversity measures how diverse of a granule associated with the other ganules, it provides a kind of novel knowledge in databases. Some experiments are conducted to test the proposed new concepts for describing the characteristics of a real network traffic data collection. The results show that the proposed concepts are promising.

A review of medical image watermarking requirements for teleradiology

Teleradiology allows medical images to be transmitted over electronic networks for clinical interpretation, and for improved healthcare access, delivery and standards. Although, such remote transmission of the images is raising various new and complex legal and ethical issues, including image retention and fraud, privacy, malpractice liability, etc., considerations of the security measures used in teleradiology remain unchanged. Addressing this problem naturally warrants investigations on the security measures for their relative functional limitations and for the scope of considering them further. In this paper, starting with various security and privacy standards, the security requirements of medical images as well as expected threats in teleradiology are reviewed. This will make it possible to determine the limitations of the conventional measures used against the expected threats. Further, we thoroughly study the utilization of digital watermarking for teleradiology. Following the key attributes and roles of various watermarking parameters, justification for watermarking over conventional security measures is made in terms of their various objectives, properties, and requirements. We also outline the main objectives of medical image watermarking for teleradiology, and provide recommendations on suitable watermarking techniques and their characterization. Finally, concluding remarks and directions for future research are presented.

A database for person re-identification in multi-camera surveillance networks

Person re-identification involves recognising individuals in different locations across a network of cameras and is a challenging task due to a large number of varying factors such as pose (both subject and camera) and ambient lighting conditions. Existing databases do not adequately capture these variations, making evaluations of proposed techniques difficult. In this paper, we present a new challenging multi-camera surveillance database designed for the task of person re-identification. This database consists of 150 unscripted sequences of subjects travelling in a building environment though up to eight camera views, appearing from various angles and in varying illumination conditions. A flexible XML-based evaluation protocol is provided to allow a highly configurable evaluation setup, enabling a variety of scenarios relating to pose and lighting conditions to be evaluated. A baseline person re-identification system consisting of colour, height and texture models is demonstrated on this database.

Hand-held monocular SLAM in thermal-infrared

Thermal-infrared imagery is relatively robust to many of the failure conditions of visual and laser-based SLAM systems, such as fog, dust and smoke. The ability to use thermal-infrared video for localization is therefore highly appealing for many applications. However, operating in thermal-infrared is beyond the capacity of existing SLAM implementations. This paper presents the first known monocular SLAM system designed and tested for hand-held use in the thermal-infrared modality. The implementation includes a flexible feature detection layer able to achieve robust feature tracking in high-noise, low-texture thermal images. A novel approach for structure initialization is also presented. The system is robust to irregular motion and capable of handling the unique mechanical shutter interruptions common to thermal-infrared cameras. The evaluation demonstrates promising performance of the algorithm in several environments.

Real-time power line extraction from unmanned aerial system video images

In this paper a real-time vision based power line extraction solution is investigated for active UAV guidance. The line extraction algorithm starts from ridge points detected by steerable filters. A collinear line segments fitting algorithm is followed up by considering global and local information together with multiple collinear measurements. GPU boosted algorithm implementation is also investigated in the experiment. The experimental result shows that the proposed algorithm outperforms two baseline line detection algorithms and is able to fitting long collinear line segments. The low computational cost of the algorithm make suitable for real-time applications.

A human-simulated immune evolutionary computation approach

Premature convergence to local optimal solutions is one of the main difficulties when using evolutionary algorithms in real-world optimization problems. To prevent premature convergence and degeneration phenomenon, this paper proposes a new optimization computation approach, human-simulated immune evolutionary algorithm (HSIEA). Considering that the premature convergence problem is due to the lack of diversity in the population, the HSIEA employs the clonal selection principle of artificial immune system theory to preserve the diversity of solutions for the search process. Mathematical descriptions and procedures of the HSIEA are given, and four new evolutionary operators are formulated which are clone, variation, recombination, and selection. Two benchmark optimization functions are investigated to demonstrate the effectiveness of the proposed HSIEA.

Quality based frame selection for video face recognition

Quality based frame selection is a crucial task in video face recognition, to both improve the recognition rate and to reduce the computational cost. In this paper we present a framework that uses a variety of cues (face symmetry, sharpness, contrast, closeness of mouth, brightness and openness of the eye) to select the highest quality facial images available in a video sequence for recognition. Normalized feature scores are fused using a neural network and frames with high quality scores are used in a Local Gabor Binary Pattern Histogram Sequence based face recognition system. Experiments on the Honda/UCSD database shows that the proposed method selects the best quality face images in the video sequence, resulting in improved recognition performance.

Understanding process behaviours in a large insurance company in Australia : a case study

Having a reliable understanding about the behaviours, problems, and performance of existing processes is important in enabling a targeted process improvement initiative. Recently, there has been an increase in the application of innovative process mining techniques to facilitate evidence-based understanding about organizations' business processes. Nevertheless, the application of these techniques in the domain of finance in Australia is, at best, scarce. This paper details a 6-month case study on the application of process mining in one of the largest insurance companies in Australia. In particular, the challenges encountered, the lessons learned, and the results obtained from this case study are detailed. Through this case study, we not only validated existing `lessons learned' from other similar case studies, but also added new insights that can be beneficial to other practitioners in applying process mining in their respective fields.