Efficient road detection and tracking for unmanned aerial vehicle

Abstract - An unmanned aerial vehicle (UAV) has many applications in a variety of fields. Detection and tracking of a specific road in UAV videos play an important role in automatic UAV navigation, traffic monitoring, and ground–vehicle tracking, and also is very helpful for constructing road networks for modeling and simulation. In this paper, an efficient road detection and tracking framework in UAV videos is proposed. In particular, a graph-cut–based detection approach is given to accurately extract a specified road region during the initialization stage and in the middle of tracking process, and a fast homography-based road-tracking scheme is developed to automatically track road areas. The high efficiency of our framework is attributed to two aspects: the road detection is performed only when it is necessary and most work in locating the road is rapidly done via very fast homography-based tracking. Experiments are conducted on UAV videos of real road scenes we captured and downloaded from the Internet. The promising results indicate the effectiveness of our proposed framework, with the precision of 98.4% and processing 34 frames per second for 1046 x 595 videos on average.

Efficient and accurate set-based registration of time-separated aerial images

This paper addresses the task of time-separated aerial image registration. The ability to solve this problem accurately and reliably is important for a variety of subsequent image understanding applications. The principal challenge lies in the extent and nature of transient appearance variation that a land area can undergo, such as that caused by the change under illumination conditions, seasonal variations, or the occlusion by non-persistent objects (people, cars). Our work introduces several major novelties (i) unlike previous work on aerial image registration, we approach the problem using a set-based paradigm; (ii) we show how image space local, pair-wise constraints can be used to enforce a globally good registration using a constraints graph structure; (iii) we show how a simple holistic representation derived from raw aerial images can be used as a basic building block of the constraints graph in a manner which achieves both high registration accuracy and speed; (iv) lastly, we introduce a new and, to the best of our knowledge, the only data corpus suitable for the evaluation of set-based aerial image registration algorithms. Using this data set, we demonstrate (i) that the proposed method outperforms the state-of-the-art for pair-wise registration already, achieving greater accuracy and reliability, while at the same time reducing the computational cost of the task and (ii) that the increase in the number of available images in a set consistently reduces the average registration error, with a major difference already for a single additional image.

Stillness and movement: a bodily approach to photography

My paper will address both Duration and temporality of the ‘still’ imageand Sensorial and bodily experience of photography through a discussion of a recent body of work ‘Fly Rhythm’, a series of photographs and video works exhibited in a gallery context.By acknowledging the inter-relationship between the body and the camera my project seeks to challenge a perceived separation between performance and photography. Fly Rhythm was conceived through a performative somatic process. Through using a custom made camera I was able to negotiate time and space to create a visual drawing of movement and stillness together in photography. The resultant images are discussed as a notation of body movement – a record of bodily history enabled through a self imposed discipline of learning to read light.I initially constructed a human size camera to understand how photography works. Spending time inside observing the way light moves and affects the formation of sight is also a way of embodying the act of photography. I responded by making a bespoke camera that enabled light to be captured during extended periods while moving. My project is dependent upon a self-imposed discipline of intuiting light’s strength and erratic changes, a skill developed by making analogue prints while inside a camera obscura. Once I had developed an ability to read light’s changes and gain an understanding of camera mechanics I made durational recordings moving through the landscape on Bruny Island Tasmania and industrial sites in Melbourne, photographs exhibited as part of Fly Rhythm. I will discuss these prints in context with the idea that light is a conduit through which past and present fuse together in a bodily act of photographing and processing images.I will explore durational aspects of photography by discussing light’s relative motion while taking photographs without using the viewfinder or composing images in the traditional way. Rather, the camera at the end of my arm is directed through how I read light therefore a choreography notated in the prints – a kind of body signatureMy practice enables a new the way of seeing, in a spontaneous hand held process creating a sense of embodiment. By analyzing process my paper will consider how the body together with analogue and 21st century digital technology coalesce cross-disciplinary practice combining visual art, performance and photographic disciplines.I also explored limitations of digital light in contrast with ‘natural’ light by a making a gamut of dissolving colour determined by the software based on two pixels. Projected into the ambient light ‘Glide’ is an 11minute durational work installed at the Substation Contemporary Art Space in Melbourne Australia.

Adaptive robust control of 6-DOF autonomous aerial vehicles

The thesis focused on development of an auto-pilot system for UAV’s and small fixed wing aircraft for use in hazardous flight conditions, such as severe weather. This led to development of a mathematical algorithm that unbinds the flight systems from coupling effects which can adaptively changed to the environment.

Groupwise registration of aerial images

This paper addresses the task of time separated aerial image registration. The ability to solve this problem accurately and reliably is important for a variety of subsequent image understanding applications. The principal challenge lies in the extent and nature of transient appearance variation that a land area can undergo, such as that caused by the change in illumination conditions, seasonal variations, or the occlusion by non-persistent objects (people, cars). Our work introduces several novelties: (i) unlike all previous work on aerial image registration, we approach the problem using a set-based paradigm; (ii) we show how local, pairwise constraints can be used to enforce a globally good registration using a constraints graph structure; (iii) we show how a simple holistic representation derived from raw aerial images can be used as a basic building block of the constraints graph in a manner which achieves both high registration accuracy and speed. We demonstrate: (i) that the proposed method outperforms the state-of-the-art for pair-wise registration already, achieving greater accuracy and reliability, while at the same time reducing the computational cost of the task; and (ii) that the increase in the number of available images in a set consistently reduces the average registration error.

Conceptual design for fully autonomous aerial and ground system for precision agriculture

There are few regulatory restrictions involving the use of fully autonomous unmanned aerial systems in unpopulated, farming areas of Australia. The combination of a fully autonomous aerial and ground systems would provide efficient and cost effective retrieval of soil and vegetation data for use in precision agriculture. The aerial system will survey the site and collect spectral imagery to analyse plant density, stress and nutrition. The ground sensors will collect soil moisture content readings throughout the site. The data from both systems will be collated at a central base station. The base station will also provide housing and interface with the aerial system.

Chamber music in painting photography film

This exhibition expands upon the history, approaches of experimental film and image making. Through speculative and abstract approaches the artists appropriate images to deal with trauma, confusion and nostalgia. The artists in this exhibition use personal imagery to demonstrate abstract ideals and idiosyncratic perspectives. Work in the show will be made up of photographic prints, collage, 16mm film and video work. Through physical manipulations of the image surface, retrenching of forgotten archives and poetic layerings of time and place, this exhibition aims to examine the de-linear and personal ways artists can experiment with the image.Through incorporating work of long standing artists Dirk De Bruyn and Luigi Fusinato in contrast with the work of young artists Anna Higgins and Beth Caird, the exhibition will examine the relationship between experimental film from a pre-digital context and how it influences, echoes and evolves in a post-digital environment.

The body in photography: an improvised performance with light

Considering the way light is integral to photography I draw on its paradoxical nature at sub atomic levels that describe how, when observed it changes. Taking a biocentric approach ; ‘A radical new view of reality: Life creates time, space, and the cosmos itself The farther we peer into space, the more we realize that the nature of the universe cannot be understood fully by inspecting spiral galaxies or watching distant supernovas. It lies deeper. It involves our very selves.’ (Lanza, 2009), I aim to clarify how embodied photographic practice can be explored through improvisational and performative discourse.

The training load of aerial skiing

This study quantified the training load experienced by elite aerial skiers. Nine elite female aerial skiers were monitored during 16 training sessions over a 13 day period. Time-motion, landing impact and heart rate (HR) data were measured from 688 jumps using integrated GPS, accelerometer and HR transmitters while rating of perceived exertion (RPE) was taken using Borg's scale. Each jump was delineated into five components from the GPS time-motion data to determine the work to rest ratios. Participants completed 16 ± 3 jumps per session with a work to rest ratio of 1.9:1 Heart rates averaged 65 ± 3.1% HRmax and peaked at 85 ± 4.4% HRmax while and an RPE score of 12 ± 1 was evoked. Landing impacts were significantly higher (p ≤ 0.001) when participants jumped off ramps with a larger take-off angle or when they completed jumps with a mid-air rotation. The training load experienced by elite aerial skiers may be causative of the high incidence of injuries reported. Significantly differing levels of impact load during the study suggest training load for these athletes can be easily modified and periodised allowing optimised performance and minimised injury.