An integrated approach for precise road reconstruction from aerial imagery and LiDAR data

Accurate and detailed road models play an important role in a number of geospatial applications, such as infrastructure planning, traffic monitoring, and driver assistance systems. In this thesis, an integrated approach for the automatic extraction of precise road features from high resolution aerial images and LiDAR point clouds is presented. A framework of road information modeling has been proposed, for rural and urban scenarios respectively, and an integrated system has been developed to deal with road feature extraction using image and LiDAR analysis. For road extraction in rural regions, a hierarchical image analysis is first performed to maximize the exploitation of road characteristics in different resolutions. The rough locations and directions of roads are provided by the road centerlines detected in low resolution images, both of which can be further employed to facilitate the road information generation in high resolution images. The histogram thresholding method is then chosen to classify road details in high resolution images, where color space transformation is used for data preparation. After the road surface detection, anisotropic Gaussian and Gabor filters are employed to enhance road pavement markings while constraining other ground objects, such as vegetation and houses. Afterwards, pavement markings are obtained from the filtered image using the Otsu's clustering method. The final road model is generated by superimposing the lane markings on the road surfaces, where the digital terrain model (DTM) produced by LiDAR data can also be combined to obtain the 3D road model. As the extraction of roads in urban areas is greatly affected by buildings, shadows, vehicles, and parking lots, we combine high resolution aerial images and dense LiDAR data to fully exploit the precise spectral and horizontal spatial resolution of aerial images and the accurate vertical information provided by airborne LiDAR. Objectoriented image analysis methods are employed to process the feature classiffcation and road detection in aerial images. In this process, we first utilize an adaptive mean shift (MS) segmentation algorithm to segment the original images into meaningful object-oriented clusters. Then the support vector machine (SVM) algorithm is further applied on the MS segmented image to extract road objects. Road surface detected in LiDAR intensity images is taken as a mask to remove the effects of shadows and trees. In addition, normalized DSM (nDSM) obtained from LiDAR is employed to filter out other above-ground objects, such as buildings and vehicles. The proposed road extraction approaches are tested using rural and urban datasets respectively. The rural road extraction method is performed using pan-sharpened aerial images of the Bruce Highway, Gympie, Queensland. The road extraction algorithm for urban regions is tested using the datasets of Bundaberg, which combine aerial imagery and LiDAR data. Quantitative evaluation of the extracted road information for both datasets has been carried out. The experiments and the evaluation results using Gympie datasets show that more than 96% of the road surfaces and over 90% of the lane markings are accurately reconstructed, and the false alarm rates for road surfaces and lane markings are below 3% and 2% respectively. For the urban test sites of Bundaberg, more than 93% of the road surface is correctly reconstructed, and the mis-detection rate is below 10%.

Pinteresque puppets and masters weave dark tales of a dystopic world

A HARBINGER is a messenger, foreshadowing what is to come. This adult fairytale, told with a cast of human actors and 22 puppets, foretells the story of a little girl found in the shadows of countless books in the library of a character known as the Old Man.

The Brisbane Line

A short 27 mins docudrama film. The Brisbane Line is a neo noir drama-documentary depicting the forgotten history surrounding the subtropical capital of Queensland, Australia. Set in the shadows of this sunshine city's unsolved crime, the film explores gaps between fact and fiction, memory and myth and excavates Brisbane's original sin [from DVD container]. The Brisbane Line is a film noir about the 1940s police force & corruption in Brisbane. The film is a creative research output, screened at Tribal Cinemas, Brisbane on the 8th November 2011.

One night stand : only you

Technical: This looped video work is made up from a number of still images animated in a sequence, not intended to be a smooth action, but syncopated. The gaps in real time suggest blinking, lapses in technology, warps in time and distance. The still images have been manipulated in photoshop and imported into an animation software program, showing subtle emphasis on various aspects of the features of the face and location from the screen shots. Content: Obsession is one of the most constant expressions of love, whether it is a negative attribute, such as stalking, or the need to see or stroke the beloved, or telling and re-telling the story of first meeting. “like the beat, beat, beat of the tom tom when the jungle shadows fall like the tick, tick, tock of the stately clock as it stands against the wall like the drip, drip drip of the rain drops when the summer shower’s through a voice within me keeps repeating you, you, you… only you...” (Cole Porter, Night and Day) My desire to immerse myself in my newly-met adult daughter as a reality is as obsessive as any new parent. The primary means of contact is video cam, which has become a kind of surveillance for me. I stare at her mouth as it moves, her ear as she moves her head, her smile, her grimaces, her high cheekbones, her eyes that are like mine, the shape of her head, her teeth that are like her father’s… hundreds of candid pictures screen shot over a year and a half were the source of the video images.

Parametric modelling for the efficient design of daylight strategies with complex geometries

Daylight devices are important components of any climate responsive façade system. But, the evolution of parametric CAD systems and digital fabrication has had an impact on architectural form so that regular forms are shifting to complex geometries. Architectural and engineering integration of daylight devices in envelopes with complex geometries is a challenge in terms of design and performance evaluation. The purpose of this paper is to assess daylight performance of a building with a climatic responsive envelope with complex geometry that integrates shading devices in the façade. The case study is based on the Esplanade buildings in Singapore. Climate-based day-light metrics such as Daylight Availability and Useful Daylight Illuminance are used. DIVA (daylight simulation), and Grasshopper (parametric analysis) plug-ins for Rhinoceros have been employed to examine the range of performance possibilities. Parameters such as dimension, inclination of the device, projected shadows and shape have been changed in order to maximize daylight availability and Useful Daylight Illuminance while minimizing glare probability. While orientation did not have a great impact on the results, aperture of the shading devices did, showing that shading devices with a projection of 1.75 m to 2.00 m performed best, achieving target lighting levels without issues of glare.

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.

Dark Cartographies

‘Dark Cartographies’ is a slowly evolving meditation upon seasonal change, life after light and the occluding shadows of human influence. Through creating experiences of the many ‘times of a night’ the work allows participants to experience deep engagement with rich spectras of hidden place and sound. By amplifying and shining light upon a myriad of lives lived in blackness, ‘Dark Cartographies’ tempts us to re-understand seasonal change as actively-embodied temporality, inflected by our climate-changing disturbances. ‘Dark Cartographies’ uses custom interactive systems, illusionary techniques and real time spatial audio that draw upon a rich array of media, including seasonal, nocturnal field recordings sourced in the Far North Queensland region and detailed observations of foliage & flowering phases. By drawing inspiration from the subtle transitions between what Europeans named ‘Summer’ and ‘Autumn’, and by including the body and its temporal disturbances within the work, ‘Dark Cartographies’ creates compellingly immersive environments that wrap us in atmospheres beyond sight and hearing. ‘Dark Cartographies’ is a dynamic new installation directed & choreographed by environmental cycles; alluding to a new framework for making works that we call ‘Seasonal’. This powerful, responsive & experiential work draws attention to that which will disappear when biodiverse worlds have descended into an era of permanent darkness – an ‘extinction of human experience’. By tapping into the deeply interlocking seasonal cycles of environments that are themselves intimately linked with social, geographical & political concerns, participating audiences are therefore challenged to see the night, their locality & ecologies in new ways through extending their personal limits of perception, imagery & comprehension.

Space within the surface : the patterned surfaces of Florence Broadhurst and Jim Thompson

The Woods Bagot 2007 refurbishment of the Qantas and British Airways Bangkok Business lounge in the Survarnabhumi Airport features wall finishes designed by wallpaper designer, Florence Broadhurst (1899-1977) and Thai Silk trader, Jim Thompson (1906-1967). This distinctive selection, which is proclaimed on the airport’s website, of patterned wall surfaces side by side draws attention to their striking similarities and their defining differences . Thompson and Broadhurst would appear to be worlds apart, but here in the airport their work brings them together. Thompson, the son of a wealthy cotton family in America, worked as an architect before joining the army. He moved to Bangkok to start The Thai Silk Company in 1948. Broadhurst was born on a farm in Mt. Perry, Queensland. She began her career as a performance artist, as part of an Australian troupe in Shanghai, moving onto pursue a career in fashion design, catering to the middle and upper classes in London. Upon her return to Australia, Broadhurst started a print design company in 1959. Both Broadhurst and Thompson pursued multiple careers, lived many lives, and died under mysterious circumstances. Broadhurst was murdered in 1977 at her Sydney print warehouse, which remains an unsolved crime. Thompson disappeared in Malaysia in 1967 and his body has never been found. This chapter investigates the parallels between Thompson and Broadhurst and what lead them to design such popular patterns for wall surfaces towards the end of their careers. While neither designer was a household name, their work is familiar to most, seen in the costume and set design of films, on the walls of restaurants and cafes and even in family homes. The reason for the popularity of their patterns has not previously been analysed. However, this chapter suggests that the patterns are intriguing because they contain something of their designers’ identities. It suggests that the coloured surface provides a way of camouflaging and hiding its subjects’ histories, such that Broadhurst and Thompson, consciously or unconsciously, used the patterned surface as a plane in which their past lives could be buried. The revealing nature of the stark white wall, compared with the forgiveness provided by the pattern in which to hide, is elaborated by painter and advocate for polychromatic architecture, Fernand Léger in his essay, “The Wall, The Architect, The Painter (1965).” Léger writes that, “the modern architect has gone too far in his magnificent attempts to cleanse through emptiness,” and that the resultant white walls of modernity create ‘an impalpability of air, of slick, brilliant new surfaces where nothing can be hidden any longer …even shadows don’t dare to enter’. To counter the exposure produced by the white wall, Thompson and Broadhurst designed patterned surfaces that could harbour their personal histories. Broadhurst and Thompson’s works share a number of commonalities in their design production, even though their work in print design commenced a decade apart. Both designers opted to work more with traditional methods of pattern making. Broadhurst used hand-operated screens, and Thompson outsourced work to local weavers and refrained from operating out of a factory. Despite humble beginnings, Broadhurst and Thompson enjoyed international success with their wall patterns being featured in a number of renowned international hotels in Bahrain, Singapore, Sydney, and London in the 1970s and 1980s. Their patterns were also transferred to fabric for soft furnishings and clothing. Thompson’s patterns were used for costumes in films including the King and I and Ben Hur. Broadhurst’s patterns were also widely used by fashion designers and artists, such as Akira Isogowa‘s costume design for Salome, a 1998 production by the Sydney Dance Company. Most recently her print designs have been used by skin illustrator Emma Hack, in a series of works painting female bodies into Broadhurst’s patterns. Hack’s works camouflage the models’ bodies into the patterned surface, assimilating subject and surface, hinting at there being something living within the patterned wall. More than four decades after Broadhurst’s murder and five decades since Thompson’s disappearance, their print designs persist as more than just a legacy. They are applied as surface finishes with the same fervour as when the designs were first released. This chapter argues that the reason for the ongoing celebration of their work is that there is the impalpable presence of the creator in the patterns. It suggests that the patterns blur the boundary between subject and surface.

City that enjoys life

A travel article about lifestyle and architecture in Vancouver, Canada. I arrived in Vancouver on a Sunday morning and followed the smell of crepes to a café that had opened early. It was warm, and the outside tables were filling up. The others had a last-night look about them, except a family that smiled as they took the table next to mine. There were no shoppers yet, but the mall was busy with walkers and cyclists. Here and there the down-and-out found seats in the sun; their shadows ran the length of shop fronts...

Lighting invariant urban street classification

In this paper we propose the hybrid use of illuminant invariant and RGB images to perform image classification of urban scenes despite challenging variation in lighting conditions. Coping with lighting change (and the shadows thereby invoked) is a non-negotiable requirement for long term autonomy using vision. One aspect of this is the ability to reliably classify scene components in the presence of marked and often sudden changes in lighting. This is the focus of this paper. Posed with the task of classifying all parts in a scene from a full colour image, we propose that lighting invariant transforms can reduce the variability of the scene, resulting in a more reliable classification. We leverage the ideas of “data transfer” for classification, beginning with full colour images for obtaining candidate scene-level matches using global image descriptors. This is commonly followed by superpixellevel matching with local features. However, we show that if the RGB images are subjected to an illuminant invariant transform before computing the superpixel-level features, classification is significantly more robust to scene illumination effects. The approach is evaluated using three datasets. The first being our own dataset and the second being the KITTI dataset using manually generated ground truth for quantitative analysis. We qualitatively evaluate the method on a third custom dataset over a 750m trajectory.

Is the sun too bright in Queensland? An approach to robust outdoor colour beacon detection

Using cameras onboard a robot for detecting a coloured stationary target outdoors is a difficult task. Apart from the complexity of separating the target from the background scenery over different ranges, there are also the inconsistencies with direct and reflected illumination from the sun,clouds, moving and stationary objects. They can vary both the illumination on the target and its colour as perceived by the camera. In this paper, we analyse the effect of environment conditions, range to target, camera settings and image processing on the reported colours of various targets. The analysis indicates the colour space and camera configuration that provide the most consistent colour values over varying environment conditions and ranges. This information is used to develop a detection system that provides range and bearing to detected targets. The system is evaluated over various lighting conditions from bright sunlight, shadows and overcast days and demonstrates robust performance. The accuracy of the system is compared against a laser beacon detector with preliminary results indicating it to be a valuable asset for long-range coloured target detection.

The radical in arts education research

Arts education research, as an interdisciplinary field, has developed in the shadows of a number of research traditions. However amid all the methodological innovation, I believe there is one particular, distinctive and radical research strategy which arts educators have created to research the practice of arts education: namely arts-based research. For many, and Elliot Eisner from Stanford University was among the first, arts education needed a research approach which could deal with the complex dynamics of arts education in the classroom. What was needed was ‘an approach to the conduct of educational research that was rooted in the arts and that used aesthetically crafted forms to reveal aspects of practice that mattered educationally’ (Eisner 2006: 11). While arts education researchers were crafting the principles and practices of arts-based research, fellow artist/researchers in the creative arts were addressing similar needs and fashioning their own exacting research strategies. This chapter aligns arts-based research with the complementary research practices established in creative arts studios and identifies the shared and truly radical nature of these moves. Finally, and in a contemporary turn many will find surprising, I will discuss how the radical aspects of these methodologies are now being held up as core elements of what is being called the fourth paradigm of scientific research, known as eScience. Could it be that the radical dynamics of arts-based research pre-figured the needs of eScience researchers who are currently struggling to manage the ‘deluge of Big Data’ which is disrupting their well-established scientific methods?

Automatic wildfire detection and simulation using optical information from unmanned aerial systems

In many parts of the world, uncontrolled fires in sparsely populated areas are a major concern as they can quickly grow into large and destructive conflagrations in short time spans. Detecting these fires has traditionally been a job for trained humans on the ground, or in the air. In many cases, these manned solutions are simply not able to survey the amount of area necessary to maintain sufficient vigilance and coverage. This paper investigates the use of unmanned aerial systems (UAS) for automated wildfire detection. The proposed system uses low-cost, consumer-grade electronics and sensors combined with various airframes to create a system suitable for automatic detection of wildfires. The system employs automatic image processing techniques to analyze captured images and autonomously detect fire-related features such as fire lines, burnt regions, and flammable material. This image recognition algorithm is designed to cope with environmental occlusions such as shadows, smoke and obstructions. Once the fire is identified and classified, it is used to initialize a spatial/temporal fire simulation. This simulation is based on occupancy maps whose fidelity can be varied to include stochastic elements, various types of vegetation, weather conditions, and unique terrain. The simulations can be used to predict the effects of optimized firefighting methods to prevent the future propagation of the fires and greatly reduce time to detection of wildfires, thereby greatly minimizing the ensuing damage. This paper also documents experimental flight tests using a SenseFly Swinglet UAS conducted in Brisbane, Australia as well as modifications for custom UAS.