A tutorial on visual servo control

This article provides a tutorial introduction to visual servo control of robotic manipulators. Since the topic spans many disciplines our goal is limited to providing a basic conceptual framework. We begin by reviewing the prerequisite topics from robotics and computer vision, including a brief review of coordinate transformations, velocity representation, and a description of the geometric aspects of the image formation process. We then present a taxonomy of visual servo control systems. The two major classes of systems, position-based and image-based systems, are then discussed in detail. Since any visual servo system must be capable of tracking image features in a sequence of images, we also include an overview of feature-based and correlation-based methods for tracking. We conclude the tutorial with a number of observations on the current directions of the research field of visual servo control.

Visual acuity is not what it seems : on Ian Burn's 'Late' reflections

A whole tradition is said to be based on the hierarchical distinction between the perceptual and conceptual. In art, Niklas Luhmann argues, this schism is played out and repeated in conceptual art. This paper complicates this depiction by examining Ian Burn's last writings in which I argue the artist-writer reviews the challenge of minimal-conceptual art in terms of its perceptual pre-occupations. Burn revisits his own work and the legacy of minimal-conceptual by moving away from the kind of ideology critique he is best known for internationally in order to reassert the long overlooked visual-perceptual preoccupations of the conceptual in art.

Rapid prototyping framework for visual control of autonomous micro aerial vehicles

Rapid prototyping environments can speed up the research of visual control algorithms. We have designed and implemented a software framework for fast prototyping of visual control algorithms for Micro Aerial Vehicles (MAV). We have applied a combination of a proxy-based network communication architecture and a custom Application Programming Interface. This allows multiple experimental configurations, like drone swarms or distributed processing of a drone's video stream. Currently, the framework supports a low-cost MAV: the Parrot AR.Drone. Real tests have been performed on this platform and the results show comparatively low figures of the extra communication delay introduced by the framework, while adding new functionalities and flexibility to the selected drone. This implementation is open-source and can be downloaded from www.vision4uav.com/?q=VC4MAV-FW

Visual support for work assignment in process-aware information systems : framework formalisation and implementation

Process-aware information systems, ranging from generic workflow systems to dedicated enterprise information systems, use work-lists to offer so-called work items to users. In real scenarios, users can be confronted with a very large number of work items that stem from multiple cases of different processes. In this jungle of work items, users may find it hard to choose the right item to work on next. The system cannot autonomously decide which is the right work item, since the decision is also dependent on conditions that are somehow outside the system. For instance, what is “best” for an organisation should be mediated with what is “best” for its employees. Current work-list handlers show work items as a simple sorted list and therefore do not provide much decision support for choosing the right work item. Since the work-list handler is the dominant interface between the system and its users, it is worthwhile to provide an intuitive graphical interface that uses contextual information about work items and users to provide suggestions about prioritisation of work items. This paper uses the so-called map metaphor to visualise work items and resources (e.g., users) in a sophisticated manner. Moreover, based on distance notions, the work-list handler can suggest the next work item by considering different perspectives. For example, urgent work items of a type that suits the user may be highlighted. The underlying map and distance notions may be of a geographical nature (e.g., a map of a city or office building), but may also be based on process designs, organisational structures, social networks, due dates, calendars, etc. The framework proposed in this paper is generic and can be applied to any process-aware information system. Moreover, in order to show its practical feasibility, the paper discusses a full-fledged implementation developed in the context of the open-source workflow environment YAWL, together with two real examples stemming from two very different scenarios. The results of an initial usability evaluation of the implementation are also presented, which provide a first indication of the validity of the approach.

Image-based visual servoing for the super-orbital re-entry of Hayabusa spacecraft

This paper presents an image-based visual servoing system that was used to track the atmospheric Earth re-entry of Hayabusa. The primary aim of this ground based tracking platform was to record the emission spectrum radiating from the superheated gas of the shock layer and the surface of the heat shield during re-entry. To the author's knowledge, this is the first time that a visual servoing system has successfully tracked a super-orbital re-entry of a spacecraft and recorded its pectral signature. Furthermore, we improved the system by including a simplified dynamic model for feed-forward control and demonstrate improved tracking performance on the International Space Station (ISS). We present comparisons between simulation and experimental results on different target trajectories including tracking results from Hayabusa and ISS. The required performance for tracking both spacecraft is demanding when combined with a narrow field of view (FOV). We also briefly discuss the preliminary results obtained from the spectroscopy of the Hayabusa's heat shield during re-entry.

Modified texture menu analysis

Lower energy and protein intakes are well documented in patients on texture modified diets. In acute hospital settings, the provision of appropriate texture modified foods to meet industry standards is essential for patient safety and nutrition outcomes. The texture modified menu at an acute private hospital was evaluated in accordance with their own nutritional standards (NS) and Australian National Standards (Dietitians Association of Australia and Speech Pathology Australia, 2007). The NS documents portion sizes and nutritional requirements for each menu. Texture B and C menus were analysed qualitatively and quantitatively over 9 days of a 6 day cyclic menu for breakfast (n=4), lunch (n=34) and dinner (n=34). Results indicated a lack of portion control, as specified by the NS, across all meals including breakfast (65–140%), soup (55–115%), meat (45–165%), vegetables (55–185%) and desserts (30–300%). Dilution factors and portion sizes influenced the protein and energy availability of Texture B & C menus. While the Texture B menu provided more energy, neither menu met the NS. Limited dessert options on the Texture C menu restricted the ability of this menu to meet protein NS. A lack of portion control and menu items incorrectly modified can compromise protein and energy intakes. Strategies to correct serving sizes and provision of alternate protein sources were recommended. Suggestions included cost-effectively increasing the variety of foods to assist protein and energy intake and the procurement of standardised equipment and visual aids to assist food preparation and presentation in accordance with texture modified guidelines and the NS.

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.

Coupling of energy from quantum emitters to the plasmonic mode of V groove waveguides: A numerical study

This work is a theoretical investigation into the coupling of a single excited quantum emitter to the plasmon mode of a V groove waveguide. The V groove waveguide consists of a triangular channel milled in gold and the emitter is modeled as a dipole emitter, and could represent a quantum dot, nitrogen vacancy in diamond, or similar. In this work the dependence of coupling efficiency of emitter to plasmon mode is determined for various geometrical parameters of the emitter-waveguide system. Using the finite element method, the effect on coupling efficiency of the emitter position and orientation, groove angle, groove depth, and tip radius, is studied in detail. We demonstrate that all parameters, with the exception of groove depth, have a significant impact on the attainable coupling efficiency. Understanding the effect of various geometrical parameters on the coupling between emitters and the plasmonic mode of the waveguide is essential for the design and optimization of quantum dot–V groove devices.

SeqSLAM : visual route-based navigation for sunny summer days and stormy winter nights

Learning and then recognizing a route, whether travelled during the day or at night, in clear or inclement weather, and in summer or winter is a challenging task for state of the art algorithms in computer vision and robotics. In this paper, we present a new approach to visual navigation under changing conditions dubbed SeqSLAM. Instead of calculating the single location most likely given a current image, our approach calculates the best candidate matching location within every local navigation sequence. Localization is then achieved by recognizing coherent sequences of these “local best matches”. This approach removes the need for global matching performance by the vision front-end - instead it must only pick the best match within any short sequence of images. The approach is applicable over environment changes that render traditional feature-based techniques ineffective. Using two car-mounted camera datasets we demonstrate the effectiveness of the algorithm and compare it to one of the most successful feature-based SLAM algorithms, FAB-MAP. The perceptual change in the datasets is extreme; repeated traverses through environments during the day and then in the middle of the night, at times separated by months or years and in opposite seasons, and in clear weather and extremely heavy rain. While the feature-based method fails, the sequence-based algorithm is able to match trajectory segments at 100% precision with recall rates of up to 60%.

Integrated vision-based attitude estimation

For many years, computer vision has lured researchers with promises of a low-cost, passive, lightweight and information-rich sensor suitable for navigation purposes. The prime difficulty in vision-based navigation is that the navigation solution will continually drift with time unless external information is available, whether it be cues from the appearance of the scene, a map of features (whether built online or known a priori), or from an externally-referenced sensor. It is not merely position that is of interest in the navigation problem. Attitude (i.e. the angular orientation of a body with respect to a reference frame) is integral to a visionbased navigation solution and is often of interest in its own right (e.g. flight control). This thesis examines vision-based attitude estimation in an aerospace environment, and two methods are proposed for constraining drift in the attitude solution; one through a novel integration of optical flow and the detection of the sky horizon, and the other through a loosely-coupled integration of Visual Odometry and GPS position measurements. In the first method, roll angle, pitch angle and the three aircraft body rates are recovered though a novel method of tracking the horizon over time and integrating the horizonderived attitude information with optical flow. An image processing front-end is used to select several candidate lines in a image that may or may not correspond to the true horizon, and the optical flow is calculated for each candidate line. Using an Extended Kalman Filter (EKF), the previously estimated aircraft state is propagated using a motion model and a candidate horizon line is associated using a statistical test based on the optical flow measurements and location of the horizon in the image. Once associated, the selected horizon line, along with the associated optical flow, is used as a measurement to the EKF. To evaluate the accuracy of the algorithm, two flights were conducted, one using a highly dynamic Uninhabited Airborne Vehicle (UAV) in clear flight conditions and the other in a human-piloted Cessna 172 in conditions where the horizon was partially obscured by terrain, haze and smoke. The UAV flight resulted in pitch and roll error standard deviations of 0.42° and 0.71° respectively when compared with a truth attitude source. The Cessna 172 flight resulted in pitch and roll error standard deviations of 1.79° and 1.75° respectively. In the second method for estimating attitude, a novel integrated GPS/Visual Odometry (GPS/VO) navigation filter is proposed, using a structure similar to a classic looselycoupled GPS/INS error-state navigation filter. Under such an arrangement, the error dynamics of the system are derived and a Kalman Filter is developed for estimating the errors in position and attitude. Through similar analysis to the GPS/INS problem, it is shown that the proposed filter is capable of recovering the complete attitude (i.e. pitch, roll and yaw) of the platform when subjected to acceleration not parallel to velocity for both the monocular and stereo variants of the filter. Furthermore, it is shown that under general straight line motion (e.g. constant velocity), only the component of attitude in the direction of motion is unobservable. Numerical simulations are performed to demonstrate the observability properties of the GPS/VO filter in both the monocular and stereo camera configurations. Furthermore, the proposed filter is tested on imagery collected using a Cessna 172 to demonstrate the observability properties on real-world data. The proposed GPS/VO filter does not require additional restrictions or assumptions such as platform-specific dynamics, map-matching, feature-tracking, visual loop-closing, gravity vector or additional sensors such as an IMU or magnetic compass. Since no platformspecific dynamics are required, the proposed filter is not limited to the aerospace domain and has the potential to be deployed in other platforms such as ground robots or mobile phones.

Vertical vegetation design decisions and their impact on energy consumption in subtropical cities

Vertical vegetation is vegetation growing on, or adjacent to, the unused sunlit exterior surfaces of buildings in cities. Vertical vegetation can improve the energy efficiency of the building on which it is installed mainly by insulating, shading and transpiring moisture from foliage and substrate. Several design parameters may affect the extent of the vertical vegetation's improvement of energy performance. Examples are choice of vegetation, growing medium geometry, north/south aspect and others. The purpose of this study is to quantitatively map out the contribution of several parameters to energy savings in a subtropical setting. The method is thermal simulation based on EnergyPlus configured to reflect the special characteristics of vertical vegetation. Thermal simulation results show that yearly cooling energy savings can reach 25% with realistic design choices in subtropical environments. Heating energy savings are negligible. The most important parameter is the aspect of walls covered by vegetation. Vertical vegetation covering walls facing north (south for the northern hemisphere) will result in the highest energy savings. In making plant selections, the most significant parameter is Leaf Area Index (LAI). Plants with larger LAI, preferably LAI>4, contribute to greater savings whereas vertical vegetation with LAI<2 can actually consume energy. The choice of growing media and its thickness influence both heating and cooling energy consumption. Change of growing medium thickness from 6cm to 8cm causes dramatic increase in energy savings from 2% to 18%. For cooling, it is best to use a growing material with high water retention, due to the importance of evapotranspiration for cooling. Similarly, for increased savings in cooling energy, sufficient irrigation is required. Insufficient irrigation results in the vertical vegetation requiring more energy to cool the building. To conclude, the choice of design parameters for vertical vegetation is crucial in making sure that it contributes to energy savings rather than energy consumption. Optimal design decisions can create a dramatic sustainability enhancement for the built environment in subtropical climates.

An improved method to detect damage using modal strain energy based damage index

This paper presents two novel concepts to enhance the accuracy of damage detection using the Modal Strain Energy based Damage Index (MSEDI) with the presence of noise in the mode shape data. Firstly, the paper presents a sequential curve fitting technique that reduces the effect of noise on the calculation process of the MSEDI, more effectively than the two commonly used curve fitting techniques; namely, polynomial and Fourier’s series. Secondly, a probability based Generalized Damage Localization Index (GDLI) is proposed as a viable improvement to the damage detection process. The study uses a validated ABAQUS finite-element model of a reinforced concrete beam to obtain mode shape data in the undamaged and damaged states. Noise is simulated by adding three levels of random noise (1%, 3%, and 5%) to the mode shape data. Results show that damage detection is enhanced with increased number of modes and samples used with the GDLI.

Multiple cameras for audio-visual speech recognition in an automotive environment

Audio-visualspeechrecognition, or the combination of visual lip-reading with traditional acoustic speechrecognition, has been previously shown to provide a considerable improvement over acoustic-only approaches in noisy environments, such as that present in an automotive cabin. The research presented in this paper will extend upon the established audio-visualspeechrecognition literature to show that further improvements in speechrecognition accuracy can be obtained when multiple frontal or near-frontal views of a speaker's face are available. A series of visualspeechrecognition experiments using a four-stream visual synchronous hidden Markov model (SHMM) are conducted on the four-camera AVICAR automotiveaudio-visualspeech database. We study the relative contribution between the side and central orientated cameras in improving visualspeechrecognition accuracy. Finally combination of the four visual streams with a single audio stream in a five-stream SHMM demonstrates a relative improvement of over 56% in word recognition accuracy when compared to the acoustic-only approach in the noisiest conditions of the AVICAR database.

Turbulence and suspended sediment measurements in an urban environment during the Brisbane River flood of January 2011

In urbanised areas, the flood flows constitute a hazard to populations and infrastructure as illustrated during major floods in 2011. During the 2011 Brisbane River flood, some turbulent velocity data were collected using acoustic Doppler velocimetry in an inundated street. The field deployment showed some unusual features of flood flow in the urban environment. That is, the water elevations and velocities fluctuated with distinctive periods between 50 and 100 s linked with some local topographic effects. The instantaneous velocity data were analysed using a triple decomposition. The velocity fluctuations included a large energy component in the slow fluctuation range, while the turbulent motion components were much smaller. The suspended sediment data showed some significant longitudinal flux. Altogether the results highlighted that the triple decomposition approach originally developed for period flows is well suited to complicated flows in an inundated urban environment.