Can you describe him for me? A technique for semantic person search in video

From a law enforcement standpoint, the ability to search for a person matching a semantic description (i.e. 1.8m tall, red shirt, jeans) is highly desirable. While a significant research effort has focused on person re-detection (the task of identifying a previously observed individual in surveillance video), these techniques require descriptors to be built from existing image or video observations. As such, person re-detection techniques are not suited to situations where footage of the person of interest is not readily available, such as a witness reporting a recent crime. In this paper, we present a novel framework that is able to search for a person based on a semantic description. The proposed approach uses size and colour cues, and does not require a person detection routine to locate people in the scene, improving utility in crowded conditions. The proposed approach is demonstrated with a new database that will be made available to the research community, and we show that the proposed technique is able to correctly localise a person in a video based on a simple semantic description.

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.

Neural network-based detection of virtual environment anomalies

The increasingly widespread use of large-scale 3D virtual environments has translated into an increasing effort required from designers, developers and testers. While considerable research has been conducted into assisting the design of virtual world content and mechanics, to date, only limited contributions have been made regarding the automatic testing of the underpinning graphics software and hardware. In the work presented in this paper, two novel neural network-based approaches are presented to predict the correct visualization of 3D content. Multilayer perceptrons and self-organizing maps are trained to learn the normal geometric and color appearance of objects from validated frames and then used to detect novel or anomalous renderings in new images. Our approach is general, for the appearance of the object is learned rather than explicitly represented. Experiments were conducted on a game engine to determine the applicability and effectiveness of our algorithms. The results show that the neural network technology can be effectively used to address the problem of automatic and reliable visual testing of 3D virtual environments.

Controlled emergency landing of an unpowered unmanned aerial system

The ability to perform autonomous emergency (forced) landings is one of the key technology enablers identified for UAS. This paper presents the flight test results of forced landings involving a UAS, in a controlled environment, and which was conducted to ascertain the performances of previously developed (and published) path planning and guidance algorithms. These novel 3-D nonlinear algorithms have been designed to control the vehicle in both the lateral and longitudinal planes of motion. These algorithms have hitherto been verified in simulation. A modified Boomerang 60 RC aircraft is used as the flight test platform, with associated onboard and ground support equipment sourced Off-the-Shelf or developed in-house at the Australian Research Centre for Aerospace Automation (ARCAA). HITL simulations were conducted prior to the flight tests and displayed good landing performance, however, due to certain identified interfacing errors, the flight results differed from that obtained in simulation. This paper details the lessons learnt and presents a plausible solution for the way forward.

Flight guardian: a common avionics architecture for collision avoidance and safe emergency landing for unmanned aerial systems

This paper presents an approach to derive requirements for an avionics architecture that provides onboard sense-and-avoid and autonomous emergency forced landing capabilities to a UAS. The approach is based on two design paradigms that (1) derive requirements analyzing the common functionality between these two functions to then derive requirements for sensors, computing capability, interfaces, etc. (2) consider the risk and safety mitigation associated with these functions to derive certification requirements for the system design. We propose to use the Aircraft Certification Matrix (ACM) approach to tailor the system Development Assurance Levels (DAL) and architecture requirements in accordance with acceptable risk criteria. This architecture is developed under the name “Flight Guardian”. Flight Guardian is an avionics architecture that integrates common sensory elements that are essential components of any UAS that is required to be dependable. The Flight Guardian concept is also applicable to conventionally piloted aircraft, where it will serve to reduce cockpit workload.

Smart grid-demand side response model for optimization air conditioning

The growing demand of air-conditioning is one of the largest contributors to Australia’s overall electricity consumption. This has started to create peak load supply problems for some electricity utilities particularly in Queensland. This research aimed to develop consumer demand side response model to assist electricity consumers to mitigate peak demand on the electrical network. The model developed demand side response model to allow consumers to manage and control air conditioning for every period, it is called intelligent control. This research investigates optimal response of end-user toward electricity price for several cases in the near future, such as: no spike, spike and probability spike price cases. The results indicate the potential of the scheme to achieve energy savings, reducing electricity bills (costs) to the consumer and targeting best economic performance for electrical generation distribution and transmission.

Performance analysis of PTP components for IEC 61850 process bus applications

New substation automation applications, such as sampled value process buses and synchrophasors, require sampling accuracy of 1 µs or better. The Precision Time Protocol (PTP), IEEE Std 1588, achieves this level of performance and integrates well into Ethernet based substation networks. This paper takes a systematic approach to the performance evaluation of commercially available PTP devices (grandmaster, slave, transparent and boundary clocks) from a variety of manufacturers. The ``error budget'' is set by the performance requirements of each application. The ``expenditure'' of this error budget by each component is valuable information for a system designer. The component information is used to design a synchronization system that meets the overall functional requirements. The quantitative performance data presented shows that this testing is effective and informative. Results from testing PTP performance in the presence of sampled value process bus traffic demonstrate the benefit of a ``bottom up'' component testing approach combined with ``top down'' system verification tests. A test method that uses a precision Ethernet capture card, rather than dedicated PTP test sets, to determine the Correction Field Error of transparent clocks is presented. This test is particularly relevant for highly loaded Ethernet networks with stringent timing requirements. The methods presented can be used for development purposes by manufacturers, or by system integrators for acceptance testing. A sampled value process bus was used as the test application for the systematic approach described in this paper. The test approach was applied, components were selected, and the system performance verified to meet the application's requirements. Systematic testing, as presented in this paper, is applicable to a range of industries that use, rather than develop, PTP for time transfer.

Context-aware multicast protocol for emergency message dissemination in vehicular networks

Road traffic accidents can be reduced by providing early warning to drivers through wireless ad hoc networks. When a vehicle detects an event that may lead to an imminent accident, the vehicle disseminates emergency messages to alert other vehicles that may be endangered by the accident. In many existing broadcast-based dissemination schemes, emergency messages may be sent to a large number of vehicles in the area and can be propagated to only one direction. This paper presents a more efficient context aware multicast protocol that disseminates messages only to endangered vehicles that may be affected by the emergency event. The endangered vehicles can be identified by calculating the interaction among vehicles based on their motion properties. To ensure fast delivery, the dissemination follows a routing path obtained by computing a minimum delay tree. The multicast protocol uses a generalized approach that can support any arbitrary road topology. The performance of the multicast protocol is compared with existing broadcast protocols by simulating chain collision accidents on a typical highway. Simulation results show that the multicast protocol outperforms the other protocols in terms of reliability, efficiency, and latency.

Context-aware rate-adaptive beaconing for efficient and scalable vehicular safety communication

Vehicular safety applications, such as cooperative collision warning systems, rely on beaconing to provide situational awareness that is needed to predict and therefore to avoid possible collisions. Beaconing is the continual exchange of vehicle motion-state information, such as position, speed, and heading, which enables each vehicle to track its neighboring vehicles in real time. This work presents a context-aware adaptive beaconing scheme that dynamically adapts the beaconing repetition rate based on an estimated channel load and the danger severity of the interactions among vehicles. The safety, efficiency, and scalability of the new scheme is evaluated by simulating vehicle collisions caused by inattentive drivers under various road traffic densities. Simulation results show that the new scheme is more efficient and scalable, and is able to improve safety better than the existing non-adaptive and adaptive rate schemes.

Practical stability of approximating discrete-time filters with respect to model mismatch

This paper establishes practical stability results for an important range of approximate discrete-time filtering problems involving mismatch between the true system and the approximating filter model. Practical stability is established in the sense of an asymptotic bound on the amount of bias introduced by the model approximation. Our analysis applies to a wide range of estimation problems and justifies the common practice of approximating intractable infinite dimensional nonlinear filters by simpler computationally tractable filters.

A penalty-based grouping genetic algorithm for multiple composite SaaS components clustering in Cloud

Software as a Service (SaaS) in Cloud is getting more and more significant among software users and providers recently. A SaaS that is delivered as composite application has many benefits including reduced delivery costs, flexible offers of the SaaS functions and decreased subscription cost for users. However, this approach has introduced a new problem in managing the resources allocated to the composite SaaS. The resource allocation that has been done at the initial stage may be overloaded or wasted due to the dynamic environment of a Cloud. A typical data center resource management usually triggers a placement reconfiguration for the SaaS in order to maintain its performance as well as to minimize the resource used. Existing approaches for this problem often ignore the underlying dependencies between SaaS components. In addition, the reconfiguration also has to comply with SaaS constraints in terms of its resource requirements, placement requirement as well as its SLA. To tackle the problem, this paper proposes a penalty-based Grouping Genetic Algorithm for multiple composite SaaS components clustering in Cloud. The main objective is to minimize the resource used by the SaaS by clustering its component without violating any constraint. Experimental results demonstrate the feasibility and the scalability of the proposed algorithm.

A simulated annealing algorithm for energy efficient virtual machine placement

Improving energy efficiency has become increasingly important in data centers in recent years to reduce the rapidly growing tremendous amounts of electricity consumption. The power dissipation of the physical servers is the root cause of power usage of other systems, such as cooling systems. Many efforts have been made to make data centers more energy efficient. One of them is to minimize the total power consumption of these servers in a data center through virtual machine consolidation, which is implemented by virtual machine placement. The placement problem is often modeled as a bin packing problem. Due to the NP-hard nature of the problem, heuristic solutions such as First Fit and Best Fit algorithms have been often used and have generally good results. However, their performance leaves room for further improvement. In this paper we propose a Simulated Annealing based algorithm, which aims at further improvement from any feasible placement. This is the first published attempt of using SA to solve the VM placement problem to optimize the power consumption. Experimental results show that this SA algorithm can generate better results, saving up to 25 percentage more energy than First Fit Decreasing in an acceptable time frame.

Energy-efficient virtual machine placement in data centers by genetic algorithm

Server consolidation using virtualization technology has become an important technology to improve the energy efficiency of data centers. Virtual machine placement is the key in the server consolidation. In the past few years, many approaches to the virtual machine placement have been proposed. However, existing virtual machine placement approaches to the virtual machine placement problem consider the energy consumption by physical machines in a data center only, but do not consider the energy consumption in communication network in the data center. However, the energy consumption in the communication network in a data center is not trivial, and therefore should be considered in the virtual machine placement in order to make the data center more energy-efficient. In this paper, we propose a genetic algorithm for a new virtual machine placement problem that considers the energy consumption in both the servers and the communication network in the data center. Experimental results show that the genetic algorithm performs well when tackling test problems of different kinds, and scales up well when the problem size increases.

Challenges in passenger terminal design : a conceptual model of passenger experience

In recent years, de-regulation in the airline industry and the introduction of low-cost carriers have conspired to produce significant changes in the airport landscape. From an airport operator’s perspective, one of the most notable has been the shift of capital revenue from traditional airline sources (through exclusive use, long term lease arrangements) to passengers (by way of fees collected from ticket sales). As a result of these developments, passengers have become recognized as major stakeholders who have the power to influence airport profitability. This link between passenger satisfaction and profitability has generated industry wide interest in the “passenger experience”. In this paper, we define the factors which influence passenger experience, namely (a) artifacts, (b) services and (c) the terminal building, and explore the challenges that exist in the current approaches to terminal design. On the basis of these insights, we propose a conceptual model of passenger experience, and motivate its use as a framework for further research into improving terminal design from a passenger oriented perspective.