Automatic image scaling for place recognition in changing environments

Robustness to variations in environmental conditions and camera viewpoint is essential for long-term place recognition, navigation and SLAM. Existing systems typically solve either of these problems, but invariance to both remains a challenge. This paper presents a training-free approach to lateral viewpoint- and condition-invariant, vision-based place recognition. Our successive frame patch-tracking technique infers average scene depth along traverses and automatically rescales views of the same place at different depths to increase their similarity. We combine our system with the condition-invariant SMART algorithm and demonstrate place recognition between day and night, across entire 4-lane-plus-median-strip roads, where current algorithms fail.

Applications of real-time machine vision to the control of mining equipment

The mining industry presents us with a number of ideal applications for sensor based machine control because of the unstructured environment that exists within each mine. The aim of the research presented here is to increase the productivity of existing large compliant mining machines by retrofitting with enhanced sensing and control technology. The current research focusses on the automatic control of the swing motion cycle of a dragline and an automated roof bolting system. We have achieved: * closed-loop swing control of an one-tenth scale model dragline; * single degree of freedom closed-loop visual control of an electro-hydraulic manipulator in the lab developed from standard components.

Design and evaluation of decision and control strategies for autonomous vision-based see and avoid systems

This paper details the design and performance assessment of a unique collision avoidance decision and control strategy for autonomous vision-based See and Avoid systems. The general approach revolves around re-positioning a collision object in the image using image-based visual servoing, without estimating range or time to collision. The decision strategy thus involves determining where to move the collision object, to induce a safe avoidance manuever, and when to cease the avoidance behaviour. These tasks are accomplished by exploiting human navigation models, spiral motion properties, expected image feature uncertainty and the rules of the air. The result is a simple threshold based system that can be tuned and statistically evaluated by extending performance assessment techniques derived for alerting systems. Our results demonstrate how autonomous vision-only See and Avoid systems may be designed under realistic problem constraints, and then evaluated in a manner consistent to aviation expectations.

Analysis of solar desalination system using heat pump

This paper investigates a pilot desalination system which consists of a direct expansion solar assisted heat pump (DXSAHP) coupled to a single-effect evaporator unit. The working fluid used is R134a and distillate is obtained via falling film evaporation and flashing in the unit. Experiments have been conducted in both day and night meteorological conditions in Singapore and the effects of solar irradiation and compressor speed have been studied against the system performance. From the experiments, the Performance Ratio (PR) obtained ranges from 0.43 to 0.88, the average Coefficient of Performance (COP) was 8 and the highest distillate production recorded was 1.38 kg/h

Countering disablism: An alternative universal income support system based on egalitarianism

The long-term vision of economic security and social participation for people with a disability held by disability activists and policy-makers has not been realised on a global scale. This is despite the implementation of various poverty alleviation initiatives by international and national governments. Indeed within advanced Western liberal democracies, the inequalities and poverty gaps have widened rather than closed. This article is based on findings from a historical-comparative policy and discourse analysis of disability income support system in Australia and the Basic Income model. The findings suggest that a model such as Basic Income, grounded in principles of social citizenship, goes some way to maintaining an adequate level of subsistence for people with a disability. The article concludes by presenting some challenges and a commitment to transforming income support policy.

Characteristics of on-road driving by persons with central vision loss: Learning to drive with a bioptic telescope

There is limited research on the driving performance and safety of bioptic drivers and even less regarding the driving skills that are most challenging for those learning to drive with bioptic telescopes. This research consisted of case studies of five trainee bioptic drivers whose driving skills were compared with those of a group of licensed bioptic drivers (n = 23) while they drove along city, suburban, and controlled-access highways in an instrumented dual-brake vehicle. A certified driver rehabilitation specialist was positioned in the front passenger seat to monitor safety and two backseat evaluators independently rated driving using a standardized scoring system. Other aspects of performance were assessed through vehicle instrumentation and video recordings. Results demonstrate that while sign recognition, lane keeping, steering steadiness, gap judgments and speed choices were significantly worse in trainees, some driving behaviors and skills, including pedestrian detection and traffic light recognition were not significantly different to those of the licensed drivers. These data provide useful insights into the skill challenges encountered by a small sample of trainee bioptic drivers which, while not generalizable because of the small sample size, provide valuable insights beyond that of previous studies and can be used as a basis to guide training strategies.

From vision to actions: Towards adaptive and autonomous humanoid robots

Although robotics research has seen advances over the last decades robots are still not in widespread use outside industrial applications. Yet a range of proposed scenarios have robots working together, helping and coexisting with humans in daily life. In all these a clear need to deal with a more unstructured, changing environment arises. I herein present a system that aims to overcome the limitations of highly complex robotic systems, in terms of autonomy and adaptation. The main focus of research is to investigate the use of visual feedback for improving reaching and grasping capabilities of complex robots. To facilitate this a combined integration of computer vision and machine learning techniques is employed. From a robot vision point of view the combination of domain knowledge from both imaging processing and machine learning techniques, can expand the capabilities of robots. I present a novel framework called Cartesian Genetic Programming for Image Processing (CGP-IP). CGP-IP can be trained to detect objects in the incoming camera streams and successfully demonstrated on many different problem domains. The approach requires only a few training images (it was tested with 5 to 10 images per experiment) is fast, scalable and robust yet requires very small training sets. Additionally, it can generate human readable programs that can be further customized and tuned. While CGP-IP is a supervised-learning technique, I show an integration on the iCub, that allows for the autonomous learning of object detection and identification. Finally this dissertation includes two proof-of-concepts that integrate the motion and action sides. First, reactive reaching and grasping is shown. It allows the robot to avoid obstacles detected in the visual stream, while reaching for the intended target object. Furthermore the integration enables us to use the robot in non-static environments, i.e. the reaching is adapted on-the- fly from the visual feedback received, e.g. when an obstacle is moved into the trajectory. The second integration highlights the capabilities of these frameworks, by improving the visual detection by performing object manipulation actions.

A Survey of autonomous vision-based See and Avoid for Unmanned Aircraft Systems

This paper provides a comprehensive review of the vision-based See and Avoid problem for unmanned aircraft. The unique problem environment and associated constraints are detailed, followed by an in-depth analysis of visual sensing limitations. In light of such detection and estimation constraints, relevant human, aircraft and robot collision avoidance concepts are then compared from a decision and control perspective. Remarks on system evaluation and certification are also included to provide a holistic review approach. The intention of this work is to clarify common misconceptions, realistically bound feasible design expectations and offer new research directions. It is hoped that this paper will help us to unify design efforts across the aerospace and robotics communities.

Repeatable Condition-Invariant Visual Odometry for Sequence-Based Place Recognition

This paper describes a vision-only system for place recognition in environments that are tra- versed at different times of day, when chang- ing conditions drastically affect visual appear- ance, and at different speeds, where places aren’t visited at a consistent linear rate. The ma- jor contribution is the removal of wheel-based odometry from the previously presented algo- rithm (SMART), allowing the technique to op- erate on any camera-based device; in our case a mobile phone. While we show that the di- rect application of visual odometry to our night- time datasets does not achieve a level of perfor- mance typically needed, the VO requirements of SMART are orthogonal to typical usage: firstly only the magnitude of the velocity is required, and secondly the calculated velocity signal only needs to be repeatable in any one part of the environment over day and night cycles, but not necessarily globally consistent. Our results show that the smoothing effect of motion constraints is highly beneficial for achieving a locally consis- tent, lighting-independent velocity estimate. We also show that the advantage of our patch-based technique used previously for frame recogni- tion, surprisingly, does not transfer to VO, where SIFT demonstrates equally good performance. Nevertheless, we present the SMART system us- ing only vision, which performs sequence-base place recognition in extreme low-light condi- tions where standard 6-DOF VO fails and that improves place recognition performance over odometry-less benchmarks, approaching that of wheel odometry.

Half-occlusion processing in stereoscopic vision

This study investigated questions related to half-occlusion processing in human stereoscopic vision: (1) How does the depth location of a half-occluding figure affect the depth localization of adjacent monocular objects? (2) Is three-dimensional slant around vertical axis (geometric effect) affected by half-occlusion constraints? and (3) How the half-occlusion constraints and surface formation processes are manifested in stereoscopic capture? Our results showed that the depth localization of binocular objects affects the depth localization of discrete monocular objects. We also showed that the visual system has a preference for a frontoparallel surface interpretation if the half-occlusion configuration allows multiple interpretation alternatives. When the surface formation was constrained by textures, our results showed that a process of rematching spreading determines the resulting perception and that the spreading can be limited by illusory contours that support the presence of binocularly unmatched figures. The unmatched figures could be present, if the inducing figures producing the illusory surface contained binocular image differences that provided cues for quantitative da Vinci stereopsis. These findings provide evidence of the significant role of half-occlusions in stereoscopic processing.

Feature integration in human vision

The earliest stages of human cortical visual processing can be conceived as extraction of local stimulus features. However, more complex visual functions, such as object recognition, require integration of multiple features. Recently, neural processes underlying feature integration in the visual system have been under intensive study. A specialized mid-level stage preceding the object recognition stage has been proposed to account for the processing of contours, surfaces and shapes as well as configuration. This thesis consists of four experimental, psychophysical studies on human visual feature integration. In two studies, classification image a recently developed psychophysical reverse correlation method was used. In this method visual noise is added to near-threshold stimuli. By investigating the relationship between random features in the noise and observer s perceptual decision in each trial, it is possible to estimate what features of the stimuli are critical for the task. The method allows visualizing the critical features that are used in a psychophysical task directly as a spatial correlation map, yielding an effective "behavioral receptive field". Visual context is known to modulate the perception of stimulus features. Some of these interactions are quite complex, and it is not known whether they reflect early or late stages of perceptual processing. The first study investigated the mechanisms of collinear facilitation, where nearby collinear Gabor flankers increase the detectability of a central Gabor. The behavioral receptive field of the mechanism mediating the detection of the central Gabor stimulus was measured by the classification image method. The results show that collinear flankers increase the extent of the behavioral receptive field for the central Gabor, in the direction of the flankers. The increased sensitivity at the ends of the receptive field suggests a low-level explanation for the facilitation. The second study investigated how visual features are integrated into percepts of surface brightness. A novel variant of the classification image method with brightness matching task was used. Many theories assume that perceived brightness is based on the analysis of luminance border features. Here, for the first time this assumption was directly tested. The classification images show that the perceived brightness of both an illusory Craik-O Brien-Cornsweet stimulus and a real uniform step stimulus depends solely on the border. Moreover, the spatial tuning of the features remains almost constant when the stimulus size is changed, suggesting that brightness perception is based on the output of a single spatial frequency channel. The third and fourth studies investigated global form integration in random-dot Glass patterns. In these patterns, a global form can be immediately perceived, if even a small proportion of random dots are paired to dipoles according to a geometrical rule. In the third study the discrimination of orientation structure in highly coherent concentric and Cartesian (straight) Glass patterns was measured. The results showed that the global form was more efficiently discriminated in concentric patterns. The fourth study investigated how form detectability depends on the global regularity of the Glass pattern. The local structure was either Cartesian or curved. It was shown that randomizing the local orientation deteriorated the performance only with the curved pattern. The results give support for the idea that curved and Cartesian patterns are processed in at least partially separate neural systems.

A bottom-up integration of vision and actions to create cognitive humanoids

In recent years more and more complex humanoid robots have been developed. On the other hand programming these systems has become more difficult. There is a clear need for such robots to be able to adapt and perform certain tasks autonomously, or even learn by themselves how to act. An important issue to tackle is the closing of the sensorimotor loop. Especially when talking about humanoids the tight integration of perception with actions will allow for improved behaviours, embedding adaptation on the lower-level of the system.

Feasibility of a stepped wedge cluster RCT and concurrent observational sub-study to evaluate the effects of modified ward night lighting on inpatient fall rates and sleep quality: A protocol for a pilot trial

Background: Falls among hospitalised patients impose a considerable burden on health systems globally and prevention is a priority. Some patient-level interventions have been effective in reducing falls, but others have not. An alternative and promising approach to reducing inpatient falls is through the modification of the hospital physical environment and the night lighting of hospital wards is a leading candidate for investigation. In this pilot trial, we will determine the feasibility of conducting a main trial to evaluate the effects of modified night lighting on inpatient ward level fall rates. We will test also the feasibility of collecting novel forms of patient level data through a concurrent observational sub-study. Methods/design: A stepped wedge, cluster randomised controlled trial will be conducted in six inpatient wards over 14 months in a metropolitan teaching hospital in Brisbane (Australia). The intervention will consist of supplementary night lighting installed across all patient rooms within study wards. The planned placement of luminaires, configurations and spectral characteristics are based on prior published research and pre-trial testing and modification. We will collect data on rates of falls on study wards (falls per 1000 patient days), the proportion of patients who fall once or more, and average length of stay. We will recruit two patients per ward per month to a concurrent observational sub-study aimed at understanding potential impacts on a range of patient sleep and mobility behaviour. The effect on the environment will be monitored with sensors to detect variation in light levels and night-time room activity. We will also collect data on possible patient-level confounders including demographics, pre-admission sleep quality, reported vision, hearing impairment and functional status. Discussion: This pragmatic pilot trial will assess the feasibility of conducting a main trial to investigate the effects of modified night lighting on inpatient fall rates using several new methods previously untested in the context of environmental modifications and patient safety. Pilot data collected through both parts of the trial will be utilised to inform sample size calculations, trial design and final data collection methods for a subsequent main trial.

Autonomous UAVs wildlife detection using thermal imaging, predictive navigation and computer vision

There is an increased interest on the use of Unmanned Aerial Vehicles (UAVs) for wildlife and feral animal monitoring around the world. This paper describes a novel system which uses a predictive dynamic application that places the UAV ahead of a user, with a low cost thermal camera, a small onboard computer that identifies heat signatures of a target animal from a predetermined altitude and transmits that target’s GPS coordinates. A map is generated and various data sets and graphs are displayed using a GUI designed for easy use. The paper describes the hardware and software architecture and the probabilistic model for downward facing camera for the detection of an animal. Behavioral dynamics of target movement for the design of a Kalman filter and Markov model based prediction algorithm are used to place the UAV ahead of the user. Geometrical concepts and Haversine formula are applied to the maximum likelihood case in order to make a prediction regarding a future state of the user, thus delivering a new way point for autonomous navigation. Results show that the system is capable of autonomously locating animals from a predetermined height and generate a map showing the location of the animals ahead of the user.

Towards vision-based deep reinforcement learning for robotic motion control

This paper introduces a machine learning based system for controlling a robotic manipulator with visual perception only. The capability to autonomously learn robot controllers solely from raw-pixel images and without any prior knowledge of configuration is shown for the first time. We build upon the success of recent deep reinforcement learning and develop a system for learning target reaching with a three-joint robot manipulator using external visual observation. A Deep Q Network (DQN) was demonstrated to perform target reaching after training in simulation. Transferring the network to real hardware and real observation in a naive approach failed, but experiments show that the network works when replacing camera images with synthetic images.