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.

Large scale monocular vision-only mapping from a fixed-wing sUAS

This paper presents the application of a monocular visual SLAMon a fixed-wing small Unmanned Aerial System (sUAS) capable of simultaneous estimation of aircraft pose and scene structure. We demonstrate the robustness of unconstrained vision alone in producing reliable pose estimates of a sUAS, at altitude. It is ultimately capable of online state estimation feedback for aircraft control and next-best-view estimation for complete map coverage without the use of additional sensors.We explore some of the challenges of visual SLAM from a sUAS including dealing with planar structure, distant scenes and noisy observations. The developed techniques are applied on vision data gathered from a fast-moving fixed-wing radio control aircraft flown over a 1×1km rural area at an altitude of 20-100m.We present both raw Structure from Motion results and a SLAM solution that includes FAB-MAP based loop-closures and graph-optimised pose. Timing information is also presented to demonstrate near online capabilities. We compare the accuracy of the 6-DOF pose estimates to an off-the-shelfGPS aided INS over a 1.7kmtrajectory.We also present output 3D reconstructions of the observed scene structure and texture that demonstrates future applications in autonomous monitoring and surveying.

Adaptive evolution of color vision as seen through the eyes of butterflies

Butterflies and primates are interesting for comparative color vision studies, because both have evolved middle- (M) and long-wavelength- (L) sensitive photopigments with overlapping absorbance spectrum maxima (lambda(max) values). Although positive selection is important for the maintenance of spectral variation within the primate pigments, it remains an open question whether it contributes similarly to the diversification of butterfly pigments. To examine this issue, we performed epimicrospectrophotometry on the eyes of five Limenitis butterfly species and found a 31-nm range of variation in the lambda(max) values of the L-sensitive photopigments (514-545 nm). We cloned partial Limenitis L opsin gene sequences and found a significant excess of replacement substitutions relative to polymorphisms among species. Mapping of these L photopigment lambda(max) values onto a phylogeny revealed two instances within Lepidoptera of convergently evolved L photopigment lineages whose lambda(max) values were blue-shifted. A codon-based maximum-likelihood analysis indicated that, associated with the two blue spectral shifts, four amino acid sites (Ile17Met, Ala64Ser, Asn70Ser, and Ser137Ala) have evolved substitutions in parallel and exhibit significant d(N)/d(S) >1. Homology modeling of the full-length Limenitis arthemis astyanax L opsin placed all four substitutions within the chromophore-binding pocket. Strikingly, the Ser137Ala substitution is in the same position as a site that in primates is responsible for a 5- to 7-nm blue spectral shift. Our data show that some of the same amino acid sites are under positive selection in the photopigments of both butterflies and primates, spanning an evolutionary distance >500 million years.

Quantitative evaluation of matching methods and validity measures for stereo vision

The authors present a qualitative and quantitative comparison of various similarity measures that form the kernel of common area-based stereo-matching systems. The authors compare classical difference and correlation measures as well as nonparametric measures based on the rank and census transforms for a number of outdoor images. For robotic applications, important considerations include robustness to image defects such as intensity variation and noise, the number of false matches, and computational complexity. In the absence of ground truth data, the authors compare the matching techniques based on the percentage of matches that pass the left-right consistency test. The authors also evaluate the discriminatory power of several match validity measures that are reported in the literature for eliminating false matches and for estimating match confidence. For guidance applications, it is essential to have and estimate of confidence in the three-dimensional points generated by stereo vision. Finally, a new validity measure, the rank constraint, is introduced that is capable of resolving ambiguous matches for rank transform-based matching.

Review of guidelines for children’s vision screenings

The aim of children's vision screenings is to detect visual problems that are common in this age category through valid and reliable tests. Nevertheless, the cost effectiveness of paediatric vision screenings, the nature of the tests included in the screening batteries and the ideal screening age has been the cause of much debate in Australia and worldwide. Therefore, the purpose of this review is to report on the current practice of children's vision screenings in Australia and other countries, as well as to evaluate the evidence for and against the provision of such screenings. This was undertaken through a detailed investigation of peer-reviewed publications on this topic. The current review demonstrates that there is no agreed vision screening protocol for children in Australia. This appears to be a result of the lack of strong evidence supporting the benefit of such screenings. While amblyopia, strabismus and, to a lesser extent refractive error, are targeted by many screening programs during pre-school and at school entry, there is less agreement regarding the value of screening for other visual conditions, such as binocular vision disorders, ocular health problems and refractive errors that are less likely to reduce distance visual acuity. In addition, in Australia, little agreement exists in the frequency and coverage of screening programs between states and territories and the screening programs that are offered are ad hoc and poorly documented. Australian children stand to benefit from improved cohesion and communication between jurisdictions and health professionals to enable an equitable provision of validated vision screening services that have the best chance of early detection and intervention for a range of paediatric visual problems.

From vision to reality : views of primary school principals on inclusive education in New South Wales, Australia

This paper discusses the findings of a research study that used semi-structured interviews to explore the views of primary school principals on inclusive education in New South Wales, Australia. Content analysis of the transcript data indicates that principals’ attitudes towards inclusive education and their success in engineering inclusive practices within their school are significantly affected by their own conception of what “inclusion” means, as well as the characteristics of the school community, and the attitudes and capacity of staff. In what follows, we present two parallel conversations that arose from the interview data to illustrate the main conceptual divisions existing between our participants’ conceptions of inclusion. First, we discuss the act of “being inclusive” which was perceived mainly as an issue of culture and pedagogy. Second, we consider the mechanics of “including,” which reflected a more instrumentalist position based on perceptions of individual student deficit, the level of support they may require and the amount of funding they can attract.

100Hz onboard vision for quadrotor state estimation

This paper introduces a high-speed, 100Hz, visionbased state estimator that is suitable for quadrotor control in close quarters manoeuvring applications. We describe the hardware and algorithms for estimating the state of the quadrotor. Experimental results for position, velocity and yaw angle estimators are presented and compared with motion capture data. Quantitative performance comparison with state-of-the-art achievements are also presented.

Airborne collision scenario flight tests : impact of angle measurement errors on reactive vision-based avoidance control

The future emergence of many types of airborne vehicles and unpiloted aircraft in the national airspace means collision avoidance is of primary concern in an uncooperative airspace environment. The ability to replicate a pilot’s see and avoid capability using cameras coupled with vision based avoidance control is an important part of an overall collision avoidance strategy. But unfortunately without range collision avoidance has no direct way to guarantee a level of safety. Collision scenario flight tests with two aircraft and a monocular camera threat detection and tracking system were used to study the accuracy of image-derived angle measurements. The effect of image-derived angle errors on reactive vision-based avoidance performance was then studied by simulation. The results show that whilst large angle measurement errors can significantly affect minimum ranging characteristics across a variety of initial conditions and closing speeds, the minimum range is always bounded and a collision never occurs.

Translating vision research into policy and practice to improve visibility, and hence safety, of road workers at night

This case study report describes the stages involved in the translation of research on night-time visibility into standards for the safety clothing worn by roadworkers. Vision research demonstrates that when lights are placed on the moveable joints of the body and the person moves in a dark setting, the phenomenon known as “biological motion or biomotion” occurs, enabling rapid and accurate recognition of the human form although only the lights can be seen. QUT was successful in gaining funding from the Australian Research Council for a Linkage grant due to the support of the predecessors of the Queensland Department of Transport and Main Roads (TMR) to research the biomotion effect in on-road settings using materials that feature in roadworker clothing. Although positive results were gained, the process of translating the research results into policy, practices and standards relied strongly on the supportive efforts of TMR staff engaged in the review and promulgation of national standards. The ultimate result was the incorporation of biomotion marking into AS/NZS 4602.1 2011. The experiences gained in this case provide insights into the processes involved in translating research into practice.

Vision based control for micro aerial vehicles : Application to sense and avoid

This work presents a collision avoidance approach based on omnidirectional cameras that does not require the estimation of range between two platforms to resolve a collision encounter. Our method achieves minimum separation between the two vehicles involved by maximising the view-angle given by the omnidirectional sensor. Only visual information is used to achieve avoidance under a bearing- only visual servoing approach. We provide theoretical problem formulation, as well as results from real flights using small quadrotors

Vision-only autonomous navigation using topometric maps

This paper presents a mapping and navigation system for a mobile robot, which uses vision as its sole sensor modality. The system enables the robot to navigate autonomously, plan paths and avoid obstacles using a vision based topometric map of its environment. The map consists of a globally-consistent pose-graph with a local 3D point cloud attached to each of its nodes. These point clouds are used for direction independent loop closure and to dynamically generate 2D metric maps for locally optimal path planning. Using this locally semi-continuous metric space, the robot performs shortest path planning instead of following the nodes of the graph --- as is done with most other vision-only navigation approaches. The system exploits the local accuracy of visual odometry in creating local metric maps, and uses pose graph SLAM, visual appearance-based place recognition and point clouds registration to create the topometric map. The ability of the framework to sustain vision-only navigation is validated experimentally, and the system is provided as open-source software.

Vision-based place recognition : how low can you go?

In this paper we use the algorithm SeqSLAM to address the question, how little and what quality of visual information is needed to localize along a familiar route? We conduct a comprehensive investigation of place recognition performance on seven datasets while varying image resolution (primarily 1 to 512 pixel images), pixel bit depth, field of view, motion blur, image compression and matching sequence length. Results confirm that place recognition using single images or short image sequences is poor, but improves to match or exceed current benchmarks as the matching sequence length increases. We then present place recognition results from two experiments where low-quality imagery is directly caused by sensor limitations; in one, place recognition is achieved along an unlit mountain road by using noisy, long-exposure blurred images, and in the other, two single pixel light sensors are used to localize in an indoor environment. We also show failure modes caused by pose variance and sequence aliasing, and discuss ways in which they may be overcome. By showing how place recognition along a route is feasible even with severely degraded image sequences, we hope to provoke a re-examination of how we develop and test future localization and mapping systems.