Eight weeks of episodic visual navigation inside a non-stationary environment using adaptive spherical views

This paper presents a long-term experiment where a mobile robot uses adaptive spherical views to localize itself and navigate inside a non-stationary office environment. The office contains seven members of staff and experiences a continuous change in its appearance over time due to their daily activities. The experiment runs as an episodic navigation task in the office over a period of eight weeks. The spherical views are stored in the nodes of a pose graph and they are updated in response to the changes in the environment. The updating mechanism is inspired by the concepts of long- and short-term memories. The experimental evaluation is done using three performance metrics which evaluate the quality of both the adaptive spherical views and the navigation over time.

Useful field of view test

A test of the useful field of view was introduced more than two decades ago and was designed to reflect the visual difficulties that older adults experience with everyday tasks. Importantly, the useful field of view is one of the most extensively researched and promising predictor tests for a range of driving outcomes measures, including driving ability and crash risk, as well as other everyday tasks. Currently available commercial versions of the test can be administered using personal computers and measure speed of visual processing speed for rapid detection and localization of targets under conditions of divided visual attention and in the presence and absence of visual clutter. The test is believed to assess higher order cognitive abilities, but performance also relies on visual sensory function since targets must be visible in order to be attended to. The format of the useful field of view test has been modified over the years; the original version estimated the spatial extent of useful field of view, while the latest versions measures visual processing speed. While deficits in the useful field of view are associated with functional impairments in everyday activities in older adults, there is also emerging evidence from several research groups that improvements in visual processing speed can be achieved through training. These improvements have been shown to reduce crash risk, and have a positive impact on health and functional well being, with the potential to increase the mobility and hence independence of older adults.

Selective combination of visual and thermal imaging for resilient localization in adverse conditions : day and night, smoke and fire

Long-term autonomy in robotics requires perception systems that are resilient to unusual but realistic conditions that will eventually occur during extended missions. For example, unmanned ground vehicles (UGVs) need to be capable of operating safely in adverse and low-visibility conditions, such as at night or in the presence of smoke. The key to a resilient UGV perception system lies in the use of multiple sensor modalities, e.g., operating at different frequencies of the electromagnetic spectrum, to compensate for the limitations of a single sensor type. In this paper, visual and infrared imaging are combined in a Visual-SLAM algorithm to achieve localization. We propose to evaluate the quality of data provided by each sensor modality prior to data combination. This evaluation is used to discard low-quality data, i.e., data most likely to induce large localization errors. In this way, perceptual failures are anticipated and mitigated. An extensive experimental evaluation is conducted on data sets collected with a UGV in a range of environments and adverse conditions, including the presence of smoke (obstructing the visual camera), fire, extreme heat (saturating the infrared camera), low-light conditions (dusk), and at night with sudden variations of artificial light. A total of 240 trajectory estimates are obtained using five different variations of data sources and data combination strategies in the localization method. In particular, the proposed approach for selective data combination is compared to methods using a single sensor type or combining both modalities without preselection. We show that the proposed framework allows for camera-based localization resilient to a large range of low-visibility conditions.

Towards robotic visual and acoustic stealth for outdoor dynamic target tracking

Covertly tracking mobile targets, either animal or human, in previously unmapped outdoor natural environments using off-road robotic platforms requires both visual and acoustic stealth. Whilst the use of robots for stealthy surveillance is not new, the majority only consider navigation for visual covertness. However, most fielded robotic systems have a non-negligible acoustic footprint arising from the onboard sensors, motors, computers and cooling systems, and also from the wheels interacting with the terrain during motion. This time-varying acoustic signature can jeopardise any visual covertness and needs to be addressed in any stealthy navigation strategy. In previous work, we addressed the initial concepts for acoustically masking a tracking robot’s movements as it travels between observation locations selected to minimise its detectability by a dynamic natural target and ensuring con- tinuous visual tracking of the target. This work extends the overall concept by examining the utility of real-time acoustic signature self-assessment and exploiting shadows as hiding locations for use in a combined visual and acoustic stealth framework.

Novelty-based visual obstacle detection in agriculture

This paper describes a novel obstacle detection system for autonomous robots in agricultural field environments that uses a novelty detector to inform stereo matching. Stereo vision alone erroneously detects obstacles in environments with ambiguous appearance and ground plane such as in broad-acre crop fields with harvested crop residue. The novelty detector estimates the probability density in image descriptor space and incorporates image-space positional understanding to identify potential regions for obstacle detection using dense stereo matching. The results demonstrate that the system is able to detect obstacles typical to a farm at day and night. This system was successfully used as the sole means of obstacle detection for an autonomous robot performing a long term two hour coverage task travelling 8.5 km.

Directing experience : an exploration of active analysis and visual cognition theory in the training of contemporary directors

The focus of this research is the creation of a stage-directing training manual on the researcher's site at the National Institute of Dramatic Art. The directing procedures build on the work of Stanislavski's Active Analysis and findings from present-day visual cognition studies. Action research methodology and evidence-based data collection are employed to improve the efficacy of both the directing procedures and the pedagogical manual. The manual serves as a supplement to director training and a toolkit for the more experienced practitioner. The manual and research findings provide a unique and innovative contribution to the field of theatre directing.

A hierarchical model of goal directed navigation selects trajectories in a visual environment

We have developed a Hierarchical Look-Ahead Trajectory Model (HiLAM) that incorporates the firing pattern of medial entorhinal grid cells in a planning circuit that includes interactions with hippocampus and prefrontal cortex. We show the model’s flexibility in representing large real world environments using odometry information obtained from challenging video sequences. We acquire the visual data from a camera mounted on a small tele-operated vehicle. The camera has a panoramic field of view with its focal point approximately 5 cm above the ground level, similar to what would be expected from a rat’s point of view. Using established algorithms for calculating perceptual speed from the apparent rate of visual change over time, we generate raw dead reckoning information which loses spatial fidelity over time due to error accumulation. We rectify the loss of fidelity by exploiting the loop-closure detection ability of a biologically inspired, robot navigation model termed RatSLAM. The rectified motion information serves as a velocity input to the HiLAM to encode the environment in the form of grid cell and place cell maps. Finally, we show goal directed path planning results of HiLAM in two different environments, an indoor square maze used in rodent experiments and an outdoor arena more than two orders of magnitude larger than the indoor maze. Together these results bridge for the first time the gap between higher fidelity bio-inspired navigation models (HiLAM) and more abstracted but highly functional bio-inspired robotic mapping systems (RatSLAM), and move from simulated environments into real-world studies in rodent-sized arenas and beyond.

Seeing pedestrians at night : effect of driver age and visual abilities

Purpose To quantify the effects of driver age on night-time pedestrian conspicuity, and to determine whether individual differences in visual performance can predict drivers' ability to recognise pedestrians at night. Methods Participants were 32 visually normal drivers (20 younger: M = 24.4 years ± 6.4 years; 12 older: M = 72.0 years ± 5.0 years). Visual performance was measured in a laboratory-based testing session including visual acuity, contrast sensitivity, motion sensitivity and the useful field of view. Night-time pedestrian recognition distances were recorded while participants drove an instrumented vehicle along a closed road course at night; to increase the workload of drivers, auditory and visual distracter tasks were presented for some of the laps. Pedestrians walked in place, sideways to the oncoming vehicles, and wore either a standard high visibility reflective vest or reflective tape positioned on the movable joints (biological motion). Results Driver age and pedestrian clothing significantly (p < 0.05) affected the distance at which the drivers first responded to the pedestrians. Older drivers recognised pedestrians at approximately half the distance of the younger drivers and pedestrians were recognised more often and at longer distances when they wore a biological motion reflective clothing configuration than when they wore a reflective vest. Motion sensitivity was an independent predictor of pedestrian recognition distance, even when controlling for driver age. Conclusions The night-time pedestrian recognition capacity of older drivers was significantly worse than that of younger drivers. The distance at which drivers first recognised pedestrians at night was best predicted by a test of motion sensitivity.

Enhancing the teaching and learning of mathematical visual images

The literacy demands of mathematics are very different to those in other subjects (Gough, 2007; O'Halloran, 2005; Quinnell, 2011; Rubenstein, 2007) and much has been written on the challenges that literacy in mathematics poses to learners (Abedi and Lord, 2001; Lowrie and Diezmann, 2007, 2009; Rubenstein, 2007). In particular, a diverse selection of visuals typifies the field of mathematics (Carter, Hipwell and Quinnell, 2012), placing unique literacy demands on learners. Such visuals include varied tables, graphs, diagrams and other representations, all of which are used to communicate information.

From ImageNet to mining: Adapting visual object detection with minimal supervision

This paper presents visual detection and classification of light vehicles and personnel on a mine site.We capitalise on the rapid advances of ConvNet based object recognition but highlight that a naive black box approach results in a significant number of false positives. In particular, the lack of domain specific training data and the unique landscape in a mine site causes a high rate of errors. We exploit the abundance of background-only images to train a k-means classifier to complement the ConvNet. Furthermore, localisation of objects of interest and a reduction in computation is enabled through region proposals. Our system is tested on over 10km of real mine site data and we were able to detect both light vehicles and personnel. We show that the introduction of our background model can reduce the false positive rate by an order of magnitude.

Visual openness in urban environments: Measuring visual openness and visibility to natural landscapes in a changing urban landscape in Gold Coast, Australia

The visual characteristics of urban environments have been changing dramatically with the growth of cities around the world. Protection and enhancement of landscape character in urban environments have been one of the challenges for policy makers in addressing sustainable urban growth. Visual openness and enclosure in urban environments are important attributes in perception of visual space which affect the human interaction with physical space and which can be often modified by new developments. Measuring visual openness in urban areas results in more accurate, reliable, and systematic approach to manage and control visual qualities in growing cities. Recent advances in techniques in geographic information systems (GIS) and survey systems make it feasible to measure and quantify this attribute with a high degree of realism and precision. Previous studies in this field do not take full advantage of these improvements. This paper proposes a method to measure the visual openness and enclosure in a changing urban landscape in Australia, on the Gold Coast, by using the improved functionality in GIS. Using this method, visual openness is calculated and described for all publicly accessible areas in the selected study area. A final map is produced which shows the areas with highest visual openness and visibility to natural landscape resources. The output of this research can be used by planners and decision-makers in managing and controlling views in complex urban landscapes. Also, depending on the availability of GIS data, this method can be applied to any region including non-urban landscapes to help planners and policy-makers manage views and visual qualities.

“I understand. I am a participant”: Navigating the ‘fuzzy’ boundaries of visual methods in qualitative longitudinal research

In this chapter we discuss how utilising the participatory visual methodology, photovoice, in an aged care context with its unique communal setting raised several ‘fuzzy boundary’ ethical dilemmas. To illustrate these challenges, we draw on immersive field notes from an ongoing qualitative longitudinal research (QLR) exploring the lived experience of aged care from the perspective of older residents, and focus on interactions with one participant, 81 year old Cassie. We explore how the camera, which is integral to the photovoice method, altered the researcher/participant ethical dynamics by becoming a continual ‘connector’ to the researcher. The camera took on a distinct agency, acting as a non-threatening ‘portal’ that lengthened contact, provided informal opportunities to alter the relationship dynamics and enabled unplanned participant revelation.

Relationships between user experience and intuitiveness of visual and physical interactions

This paper investigates the effects of experience on the intuitiveness of physical and visual interactions performed by airport security screeners. Using portable eye tracking glasses, 40 security screeners were observed in the field as they performed search, examination and interface interactions during airport security x-ray screening. Data from semi structured interviews was used to further explore the nature of visual and physical interactions. Results show there are positive relationships between experience and the intuitiveness of visual and physical interactions performed by security screeners. As experience is gained, security screeners are found to perform search, examination and interface interactions more intuitively. In addition to experience, results suggest that intuitiveness is affected by the nature and modality of activities performed. This inference was made based on the dominant processing styles associated with search and examination activities. The paper concludes by discussing the implications that this research has for the design of visual and physical interfaces. We recommend designing interfaces that build on users’ already established intuitive processes, and that reduce the cognitive load incurred during transitions between visual and physical interactions.

On Visual Detection of Highly-occluded Objects for Harvesting Automation in Horticulture

Developing accurate and reliable crop detection algorithms is an important step for harvesting automation in horticulture. This paper presents a novel approach to visual detection of highly-occluded fruits. We use a conditional random field (CRF) on multi-spectral image data (colour and Near-Infrared Reflectance, NIR) to model two classes: crop and background. To describe these two classes, we explore a range of visual-texture features including local binary pattern, histogram of oriented gradients, and learn auto-encoder features. The pro-posed methods are evaluated using hand-labelled images from a dataset captured on a commercial capsicum farm. Experimental results are presented, and performance is evaluated in terms of the Area Under the Curve (AUC) of the precision-recall curves.Our current results achieve a maximum performance of 0.81AUC when combining all of the texture features in conjunction with colour information.

Visual detection of occluded crop: For automated harvesting

This paper presents a novel crop detection system applied to the challenging task of field sweet pepper (capsicum) detection. The field-grown sweet pepper crop presents several challenges for robotic systems such as the high degree of occlusion and the fact that the crop can have a similar colour to the background (green on green). To overcome these issues, we propose a two-stage system that performs per-pixel segmentation followed by region detection. The output of the segmentation is used to search for highly probable regions and declares these to be sweet pepper. We propose the novel use of the local binary pattern (LBP) to perform crop segmentation. This feature improves the accuracy of crop segmentation from an AUC of 0.10, for previously proposed features, to 0.56. Using the LBP feature as the basis for our two-stage algorithm, we are able to detect 69.2% of field grown sweet peppers in three sites. This is an impressive result given that the average detection accuracy of people viewing the same colour imagery is 66.8%.