The use of high dynamic range luminance mapping in the assessment, understanding and defining of visual issues in post occupancy building assessment

The international focus on embracing daylighting for energy efficient lighting purposes and the corporate sector’s indulgence in the perception of workplace and work practice “transparency” has spurned an increase in highly glazed commercial buildings. This in turn has renewed issues of visual comfort and daylight-derived glare for occupants. In order to ascertain evidence, or predict risk, of these events; appraisals of these complex visual environments require detailed information on the luminances present in an occupant’s field of view. Conventional luminance meters are an expensive and time consuming method of achieving these results. To create a luminance map of an occupant’s visual field using such a meter requires too many individual measurements to be a practical measurement technique. The application of digital cameras as luminance measurement devices has solved this problem. With high dynamic range imaging, a single digital image can be created to provide luminances on a pixel-by-pixel level within the broad field of view afforded by a fish-eye lens: virtually replicating an occupant’s visual field and providing rapid yet detailed luminance information for the entire scene. With proper calibration, relatively inexpensive digital cameras can be successfully applied to the task of luminance measurements, placing them in the realm of tools that any lighting professional should own. This paper discusses how a digital camera can become a luminance measurement device and then presents an analysis of results obtained from post occupancy measurements from building assessments conducted by the Mobile Architecture Built Environment Laboratory (MABEL) project. This discussion leads to the important realisation that the placement of such tools in the hands of lighting professionals internationally will provide new opportunities for the lighting community in terms of research on critical issues in lighting such as daylight glare and visual quality and comfort.

Extraction of road lanes from high-resolution stereo aerial imagery based on maximum likelihood segmentation and texture enhancement

Accurate road lane information is crucial for advanced vehicle navigation and safety applications. With the increasing of very high resolution (VHR) imagery of astonishing quality provided by digital airborne sources, it will greatly facilitate the data acquisition and also significantly reduce the cost of data collection and updates if the road details can be automatically extracted from the aerial images. In this paper, we proposed an effective approach to detect road lanes from aerial images with employment of the image analysis procedures. This algorithm starts with constructing the (Digital Surface Model) DSM and true orthophotos from the stereo images. Next, a maximum likelihood clustering algorithm is used to separate road from other ground objects. After the detection of road surface, the road traffic and lane lines are further detected using texture enhancement and morphological operations. Finally, the generated road network is evaluated to test the performance of the proposed approach, in which the datasets provided by Queensland department of Main Roads are used. The experiment result proves the effectiveness of our approach.

Automatic tracking, super-resolution and recognition of human faces from surveillance video

Identifying an individual from surveillance video is a difficult, time consuming and labour intensive process. The proposed system aims to streamline this process by filtering out unwanted scenes and enhancing an individual's face through super-resolution. An automatic face recognition system is then used to identify the subject or present the human operator with likely matches from a database. A person tracker is used to speed up the subject detection and super-resolution process by tracking moving subjects and cropping a region of interest around the subject's face to reduce the number and size of the image frames to be super-resolved respectively. In this paper, experiments have been conducted to demonstrate how the optical flow super-resolution method used improves surveillance imagery for visual inspection as well as automatic face recognition on an Eigenface and Elastic Bunch Graph Matching system. The optical flow based method has also been benchmarked against the ``hallucination'' algorithm, interpolation methods and the original low-resolution images. Results show that both super-resolution algorithms improved recognition rates significantly. Although the hallucination method resulted in slightly higher recognition rates, the optical flow method produced less artifacts and more visually correct images suitable for human consumption.

Vision-based topological mapping and localisation

Competent navigation in an environment is a major requirement for an autonomous mobile robot to accomplish its mission. Nowadays, many successful systems for navigating a mobile robot use an internal map which represents the environment in a detailed geometric manner. However, building, maintaining and using such environment maps for navigation is difficult because of perceptual aliasing and measurement noise. Moreover, geometric maps require the processing of huge amounts of data which is computationally expensive. This thesis addresses the problem of vision-based topological mapping and localisation for mobile robot navigation. Topological maps are concise and graphical representations of environments that are scalable and amenable to symbolic manipulation. Thus, they are well-suited for basic robot navigation applications, and also provide a representational basis for the procedural and semantic information needed for higher-level robotic tasks. In order to make vision-based topological navigation suitable for inexpensive mobile robots for the mass market we propose to characterise key places of the environment based on their visual appearance through colour histograms. The approach for representing places using visual appearance is based on the fact that colour histograms change slowly as the field of vision sweeps the scene when a robot moves through an environment. Hence, a place represents a region of the environment rather than a single position. We demonstrate in experiments using an indoor data set, that a topological map in which places are characterised using visual appearance augmented with metric clues provides sufficient information to perform continuous metric localisation which is robust to the kidnapped robot problem. Many topological mapping methods build a topological map by clustering visual observations to places. However, due to perceptual aliasing observations from different places may be mapped to the same place representative in the topological map. A main contribution of this thesis is a novel approach for dealing with the perceptual aliasing problem in topological mapping. We propose to incorporate neighbourhood relations for disambiguating places which otherwise are indistinguishable. We present a constraint based stochastic local search method which integrates the approach for place disambiguation in order to induce a topological map. Experiments show that the proposed method is capable of mapping environments with a high degree of perceptual aliasing, and that a small map is found quickly. Moreover, the method of using neighbourhood information for place disambiguation is integrated into a framework for topological off-line simultaneous localisation and mapping which does not require an initial categorisation of visual observations. Experiments on an indoor data set demonstrate the suitability of our method to reliably localise the robot while building a topological map.

Omnidirectional visual odometry for a planetary rover

Position estimation for planetary rovers has been typically limited to odometry based on proprioceptive measurements such as the integration of distance traveled and measurement of heading change. Here we present and compare two methods of online visual odometry suited for planetary rovers. Both methods use omnidirectional imagery to estimate motion of the rover. One method is based on robust estimation of optical flow and subsequent integration of the flow. The second method is a full structure-from-motion solution. To make the comparison meaningful we use the same set of raw corresponding visual features for each method. The dataset is an sequence of 2000 images taken during a field experiment in the Atacama desert, for which high resolution GPS ground truth is available.

Vision-based detection and tracking of aerial targets for UAV collision avoidance

Machine vision represents a particularly attractive solution for sensing and detecting potential collision-course targets due to the relatively low cost, size, weight, and power requirements of the sensors involved (as opposed to radar). This paper describes the development and evaluation of a vision-based collision detection algorithm suitable for fixed-wing aerial robotics. The system was evaluated using highly realistic vision data of the moments leading up to a collision. Based on the collected data, our detection approaches were able to detect targets at distances ranging from 400m to about 900m. These distances (with some assumptions about closing speeds and aircraft trajectories) translate to an advanced warning of between 8-10 seconds ahead of impact, which approaches the 12.5 second response time recommended for human pilots. We make use of the enormous potential of graphic processing units to achieve processing rates of 30Hz (for images of size 1024-by- 768). Currently, integration in the final platform is under way.

Airborne vision-based collision-detection system

Machine vision represents a particularly attractive solution for sensing and detecting potential collision-course targets due to the relatively low cost, size, weight, and power requirements of vision sensors (as opposed to radar and TCAS). This paper describes the development and evaluation of a real-time vision-based collision detection system suitable for fixed-wing aerial robotics. Using two fixed-wing UAVs to recreate various collision-course scenarios, we were able to capture highly realistic vision (from an onboard camera perspective) of the moments leading up to a collision. This type of image data is extremely scarce and was invaluable in evaluating the detection performance of two candidate target detection approaches. Based on the collected data, our detection approaches were able to detect targets at distances ranging from 400m to about 900m. These distances (with some assumptions about closing speeds and aircraft trajectories) translate to an advanced warning of between 8-10 seconds ahead of impact, which approaches the 12.5 second response time recommended for human pilots. We overcame the challenge of achieving real-time computational speeds by exploiting the parallel processing architectures of graphics processing units found on commercially-off-the-shelf graphics devices. Our chosen GPU device suitable for integration onto UAV platforms can be expected to handle real-time processing of 1024 by 768 pixel image frames at a rate of approximately 30Hz. Flight trials using manned Cessna aircraft where all processing is performed onboard will be conducted in the near future, followed by further experiments with fully autonomous UAV platforms.

Robust outdoor visual localization using a three-dimensional-edge map

Visual localization systems that are practical for autonomous vehicles in outdoor industrial applications must perform reliably in a wide range of conditions. Changing outdoor conditions cause difficulty by drastically altering the information available in the camera images. To confront the problem, we have developed a visual localization system that uses a surveyed three-dimensional (3D)-edge map of permanent structures in the environment. The map has the invariant properties necessary to achieve long-term robust operation. Previous 3D-edge map localization systems usually maintain a single pose hypothesis, making it difficult to initialize without an accurate prior pose estimate and also making them susceptible to misalignment with unmapped edges detected in the camera image. A multihypothesis particle filter is employed here to perform the initialization procedure with significant uncertainty in the vehicle's initial pose. A novel observation function for the particle filter is developed and evaluated against two existing functions. The new function is shown to further improve the abilities of the particle filter to converge given a very coarse estimate of the vehicle's initial pose. An intelligent exposure control algorithm is also developed that improves the quality of the pertinent information in the image. Results gathered over an entire sunny day and also during rainy weather illustrate that the localization system can operate in a wide range of outdoor conditions. The conclusion is that an invariant map, a robust multihypothesis localization algorithm, and an intelligent exposure control algorithm all combine to enable reliable visual localization through challenging outdoor conditions.

Representation and learning of visual information for pose recognition

Recovering position from sensor information is an important problem in mobile robotics, known as localisation. Localisation requires a map or some other description of the environment to provide the robot with a context to interpret sensor data. The mobile robot system under discussion is using an artificial neural representation of position. Building a geometrical map of the environment with a single camera and artificial neural networks is difficult. Instead it would be simpler to learn position as a function of the visual input. Usually when learning images, an intermediate representation is employed. An appropriate starting point for biologically plausible image representation is the complex cells of the visual cortex, which have invariance properties that appear useful for localisation. The effectiveness for localisation of two different complex cell models are evaluated. Finally the ability of a simple neural network with single shot learning to recognise these representations and localise a robot is examined.

Toward robust image detection of crown-of-thorns starfish for autonomous population monitoring

Robust texture recognition in underwater image sequences for marine pest population control such as Crown-Of-Thorns Starfish (COTS) is a relatively unexplored area of research. Typically, humans count COTS by laboriously processing individual images taken during surveys. Being able to autonomously collect and process images of reef habitat and segment out the various marine biota holds the promise of allowing researchers to gain a greater understanding of the marine ecosystem and evaluate the impact of different environmental variables. This research applies and extends the use of Local Binary Patterns (LBP) as a method for texture-based identification of COTS from survey images. The performance and accuracy of the algorithms are evaluated on a image data set taken on the Great Barrier Reef.

Effect of representation size and visual ambiguity on RatSLAM system performance

RatSLAM is a vision-based SLAM system based on extended models of the rodent hippocampus. RatSLAM creates environment representations that can be processed by the experience mapping algorithm to produce maps suitable for goal recall. The experience mapping algorithm also allows RatSLAM to map environments many times larger than could be achieved with a one to one correspondence between the map and environment, by reusing the RatSLAM maps to represent multiple sections of the environment. This paper describes experiments investigating the effects of the environment-representation size ratio and visual ambiguity on mapping and goal navigation performance. The experiments demonstrate that system performance is weakly dependent on either parameter in isolation, but strongly dependent on their joint values.

Lip detection for audio-visual speech recognition in-car environment

Acoustically, car cabins are extremely noisy and as a consequence audio-only, in-car voice recognition systems perform poorly. As the visual modality is immune to acoustic noise, using the visual lip information from the driver is seen as a viable strategy in circumventing this problem by using audio visual automatic speech recognition (AVASR). However, implementing AVASR requires a system being able to accurately locate and track the drivers face and lip area in real-time. In this paper we present such an approach using the Viola-Jones algorithm. Using the AVICAR [1] in-car database, we show that the Viola- Jones approach is a suitable method of locating and tracking the driver’s lips despite the visual variability of illumination and head pose for audio-visual speech recognition system.

Biologically inspired visual landmark processing for simultaneous localization and mapping

This paper illustrates a method for finding useful visual landmarks for performing simultaneous localization and mapping (SLAM). The method is based loosely on biological principles, using layers of filtering and pooling to create learned templates that correspond to different views of the environment. Rather than using a set of landmarks and reporting range and bearing to the landmark, this system maps views to poses. The challenge is to produce a system that produces the same view for small changes in robot pose, but provides different views for larger changes in pose. The method has been developed to interface with the RatSLAM system, a biologically inspired method of SLAM. The paper describes the method of learning and recalling visual landmarks in detail, and shows the performance of the visual system in real robot tests.

Audio visual automatic speech recognition in vehicles

Acoustically, car cabins are extremely noisy and as a consequence, existing audio-only speech recognition systems, for voice-based control of vehicle functions such as the GPS based navigator, perform poorly. Audio-only speech recognition systems fail to make use of the visual modality of speech (eg: lip movements). As the visual modality is immune to acoustic noise, utilising this visual information in conjunction with an audio only speech recognition system has the potential to improve the accuracy of the system. The field of recognising speech using both auditory and visual inputs is known as Audio Visual Speech Recognition (AVSR). Continuous research in AVASR field has been ongoing for the past twenty-five years with notable progress being made. However, the practical deployment of AVASR systems for use in a variety of real-world applications has not yet emerged. The main reason is due to most research to date neglecting to address variabilities in the visual domain such as illumination and viewpoint in the design of the visual front-end of the AVSR system. In this paper we present an AVASR system in a real-world car environment using the AVICAR database [1], which is publicly available in-car database and we show that the use of visual speech conjunction with the audio modality is a better approach to improve the robustness and effectiveness of voice-only recognition systems in car cabin environments.

Typical accuracy and quality control of a process for creating CT-Based virtual bone models

A pragmatic method for assessing the accuracy and precision of a given processing pipeline required for converting computed tomography (CT) image data of bones into representative three dimensional (3D) models of bone shapes is proposed. The method is based on coprocessing a control object with known geometry which enables the assessment of the quality of resulting 3D models. At three stages of the conversion process, distance measurements were obtained and statistically evaluated. For this study, 31 CT datasets were processed. The final 3D model of the control object contained an average deviation from reference values of −1.07±0.52 mm standard deviation (SD) for edge distances and −0.647±0.43 mm SD for parallel side distances of the control object. Coprocessing a reference object enables the assessment of the accuracy and precision of a given processing pipeline for creating CTbased 3D bone models and is suitable for detecting most systematic or human errors when processing a CT-scan. Typical errors have about the same size as the scan resolution.