Search

Background This paper investigates the use of a light stage to capture high‐resolution, 3D facial surface textures and proposes novel methods to use the data for skin condition assessment. Materials and Methods We introduce new methods for analysing 3D surface texture using high‐resolution normal fields and apply these to the detection and assessment of skin conditions in human faces, specifically wrinkles, pores and acne. The use of high‐resolution normal maps as input to our texture measures enables us to investigate the 3D nature of texture, while retaining aspects of some well‐known 2D texture measures. The main contributions are as follows: the introduction of three novel methods for extracting texture descriptors from high‐resolution surface orientation fields; a comparative study of 2D and 3D skin texture analysis techniques; and an extensive data set of high‐resolution 3D facial scans presenting various skin conditions, with human ratings as “ground truth.” Results Our results demonstrate an improvement on state‐of‐the‐art methods for the analysis of pores and comparable results to the state of the art for wrinkles and acne using a considerably more compact model. Conclusions The use of high‐resolution normal maps, captured by a light stage, and the methods described, represent an important new set of tools in the analysis of skin texture.

With a keynote by Rebecca George OBE, the Lovelace Colloquium is an inspirational gather with a real focus: celebrating and inspiring women in IT.

The authors present a comprehensive overview of image processing and analysis work done to support research into the model flowering plant Arabidopsis thaliana. Beside the plant's importance in biological research, using image analysis to obtain experimental measurements of it is an interesting vision problem in its own right, involving the segmentation and analysis of sequences of images of objects whose shape varies between individual specimens and also changes over time. While useful measurements can be obtained by segmenting a whole plant from the background, they suggest that the increased range and precision of measurements made available by leaf-level segmentation makes this a problem well worth solving. A variety of approaches have been tried by biologists as well as computer vision researchers. This is an interdisciplinary area and the computer vision community has an important contribution to make. They suggest that there is a need for publicly available datasets with ground truth annotations to enable the evaluation of new approaches and to support the building of training data for modern data-driven computer vision approaches, which are those most likely to result in the kind of fully automated systems that will be of use to biologists.

In this paper, we bring together two divergent strands of research: photometric face capture and statistical 3D face appearance modelling. We propose a novel lightstage capture and processing pipeline for acquiring ear-to-ear, truly intrinsic diffuse and specular albedo maps that fully factor out the effects of illumination, camera and geometry. Using this pipeline, we capture a dataset of 50 scans and combine them with the only existing publicly available albedo dataset (3DRFE) of 23 scans. This allows us to build the first morphable face albedo model. We believe this is the first statistical analysis of the variability of facial specular albedo maps. This model can be used as a plug in replacement for the texture model of the Basel Face Model (BFM) or FLAME and we make the model publicly available. We ensure careful spectral calibration such that our model is built in a linear sRGB space, suitable for inverse rendering of images taken by typical cameras. We demonstrate our model in a state of the art analysis-by-synthesis 3DMM fitting pipeline, are the first to integrate specular map estimation and outperform the BFM in albedo reconstruction., Comment: CVPR 2020

Shadows have long been a challenging topic for computer vision. This challenge is made even harder when we assume that the camera is moving, as many existing shadow detection techniques require the creation and maintenance of a background model. This article explores the problem of shadow modelling from a moving viewpoint (assumed to be a robotic platform) through comparing shadow-variant and shadow-invariant image features — primarily color, texture and edge-based features. These features are then embedded in a segmentation pipeline that provides predictions on shadow status, using minimal temporal context. We also release a public dataset of shadow-related image sequences, to help other researchers further develop shadow detection methods and to enable benchmarking of techniques.

This paper describes a method for building semantic scene models from video data using observed motion. We do this through unsupervised clustering of simple yet novel motion descriptors, which provide a quantized representation of gross motion within scene regions. Using these we can characterise the dominant patterns of motion, and then group spatial regions based upon both proximity and local motion similarity to define areas or regions with particular motion characteristics. We are able to process scenes in which objects are difficult to detect and track due to variable frame-rate, video quality or occlusion, and we are able to identify regions which differ by usage but which do not differ by appearance (such as frequently used paths across open space). We demonstrate our method on 50 videos from very different scene types: indoor scenarios with unpredictable unconstrained motion, junction scenes, road and path scenes, and open squares or plazas. We show that these scenes can be clustered using our representation, and that the incorporation of learned spatial relations into the representation enables us to cluster more effectively. This method enables us to make meaningful statements about video scenes as a whole (such as ''this video is like that video'') and about regions within these scenes (such as ''this part of this scene is similar to that part of that scene'').

Recently, psychologists have turned their attention to the study of cast shadows and demonstrated that the human perceptual system values information from shadows very highly in the perception of spatial qualities, sometimes to the detriment of other cues. However with some notable and recent exceptions, computer vision systems treat cast shadows not as signal but as noise. This paper provides a concise yet comprehensive review of the literature on cast shadow perception from across the cognitive sciences, including the theoretical information available, the perception of shadows in human and machine vision, and the ways in which shadows can be used.

We propose a new method that treats visible human behaviour at the level of navigational strategies. By inferring intentions in terms of known goals, it is possible to explain the behaviour of people moving around within the field of view of a video camera. The approach presented here incorporates models of navigation from within psychology which are both simple and conceptually plausible, whilst providing good results in an event-detection application. The output is in the form of statements involving goals, such as ''Agent 25 went to exit 8 via sub-goals 34 and 21'' for a given navigational strategy, an image representing the path through the scene, and an overall score for each trajectory. The central algorithm generates all plausible paths through the scene to known goal sites and then compares each path to the agent's actual trajectory thus finding the most likely explanation for their behaviour. Two navigational strategies are examined, shortest path and simplest path. Experimental results are presented for an outdoor car-park and an indoor foyer scene, and our method is found to produce psychologically plausible explanations in the majority of cases. We propose a novel approach to determining the effectiveness of event detection systems, and evaluate the method presented here against this new ground truth. This evaluation method uses human observers to judge the behaviour shown in various video clips, then uses these judgements in correlation with those of the software. We compare the method with a standard machine learning approach based on nearest neighbour. Finally we consider the application of such a system in a binary event-detection or behaviour filtering system.

Spatial knowledge plays an essential role in human reasoning, permitting tasks such as locating objects in the world (including oneself), reasoning about everyday actions and describing perceptual information. This is also the case in the field of mobile robotics, where one of the most basic (and essential) tasks is the autonomous determination of the pose of a robot with respect to a map, given its perception of the environment. This is the problem of robot self-localisation (or simply the localisation problem). This paper presents a probabilistic algorithm for robot self-localisation that is based on a topological map constructed from the observation of spatial occlusion. Distinct locations on the map are defined by means of a classical formalism for qualitative spatial reasoning, whose base definitions are closer to the human categorisation of space than traditional, numerical, localisation procedures. The approach herein proposed was systematically evaluated through experiments using a mobile robot eq...

The problem of automated visual surveillance has spawned a lively research area, with 2005 seeing three conferences or workshops and special issues of two major journals devoted to the topic. These alone are responsible for somewhere in the region of 240 papers and posters on automated visual surveillance before we begin to count those presented in more general fora. Many of these systems and algorithms perform one small sub-part of the surveillance task, such as motion detection. But even with low level image processing tasks it is often difficult to compare systems on the basis of published results alone. This review paper aims to answer the difficult question “How close are we to developing surveillance related systems which are really useful?” The first section of this paper considers the question of surveillance in the real world: installations, systems and practises. The main body of the paper then considers existing computer vision techniques with an emphasis on higher level processes such as behaviour modelling and event detection. We conclude with a review of the evaluative mechanisms that have grown from within the computer vision community in an attempt to provide some form of robust evaluation and cross-system comparability.

This chapter introduces the domain of image analysis, both in general and as applied to the problem of plant phenotyping. Images can be thought of as a measurement tool, and the automated processing of images allows for greater throughput, reliability and repeatability, at all scales of measurement (from microscopic to field level). This domain should be of increasing interest to plant scientists, as the cost of image-based sensors is dropping, and photographing plants on a daily or even minute-by-minute basis is now cost-effective. With such systems there is a possibility of tens of thousands of photographs being recorded, and so the job of analysing these images must now fall to computational methods. In this chapter, we provide an overview of recent work in image analysis for plant science and highlight some of the key techniques from computer vision that have been applied to date to the problem of phenotyping plants. We conclude with a description of the four main challenges for image analysis and plant science: growth, occlusion, evaluation and low-cost sensor vision.

We compare skin texture classification using various 2D texture descriptors and their extensions to 3D surface orientation data. We perform a multi-resolution analysis on both the 2D and 3D data. Rotation-Invariant Local Binary Patterns, Multiple Orientations Gabor Filters and Center-Symetric Autocorrelation are used to extract 2D texture features from high resolution facial skin albedo patches. For extracting texture feature directly from the corresponding normal map patches, we propose extensions of these texture measures in both the slant/tilt and tangent spaces. We compare the results of classifying facial wrinkles and pores using the 2D-based and 3D-based texture features. We use the 3DRFE dataset which consists of high resolution 3D facial scans along with the corresponding photometric and albedo images. We notice a net improvement on classifying both wrinkle and pore using the 3D orientation based features over the 2D ones.

In this work, we present a system for the automated classiffication of seabed substrates in underwater video. Classiffication of seabed substrates traditionally requires manual analysis by a marine biologist, according to an established classiffication system. Accurate, consistent and robust classiffication is difficult in underwater video due to varying lighting conditions, turbidity and method of original recording. We have developed a system that uses ground truth data from marine biologists to train and test per-frame classiffiers. In this paper we present preliminary results of this using various feature representations (histograms, Gabor wavelets) and classiffiers (SVC, kNN) on both full-frame and patchedbased analysis, achieving up to 93% accuracy

This paper describes a novel image-based method for robot orientation estimation based on a single omnidirectional camera. The estimation of orientation is computed by finding the best pixel-wise match between images as a function of the rotation of the second image. This is done either using the first image as the reference image or with a moving reference image. Three datasets were collected in different scenarios along a “Gummy Bear” path in outdoor environments. This carefully designed path has the appearance of a gummy bear in profile, and provides many curves and sets of image pairs that are challenging for visual robot localisation. We compare our method to a feature-based method using SIFT and another appearance-based visual compass. Experimental results demonstrate that the appearance-based methods perform well and more consistently than the feature based method, especially when the compared images were grabbed at positions far apart.

Computer vision has addressed many problems in art, but has not yet looked in detail at the way artistic style can develop and evolve over the course of an artist's career. In this paper we take a computational approach to modelling stylistic change in the body of work amassed by Sir John “Kyffin” Williams, a nationally renowned and prolific Welsh artist. Using images gathered from catalogues and online sources, we use a leave-one-out methodology to classify paintings by year; despite the variation in image source, size, and quality we are able to obtain significant correlations between predicted year and actual year, and we are able to guess the age of the painting within 15 years, for around 70% of our dataset. We also investigate the incorporation of expert knowledge within this framework by consdering a subset of paintings chosen as exemplars by a scholar familiar with Williams' work.

This paper describes a logic-based formalism for qualitative spatial reasoning with cast shadows (Perceptual Qualitative Relations on Shadows, or PQRS) and presents results of a mobile robot qualitative self-localisation experiment using this formalism. Shadow detection was accomplished by mapping the images from the robot's monocular colour camera into a HSV colour space and then thresholding on the V dimension. We present results of self-localisation using two methods for obtaining the threshold automatically: in one method the images are segmented according to their grey-scale histograms, in the other, the threshold is set according to a prediction about the robot's location, based upon a qualitative spatial reasoning theory about shadows. This theory-driven threshold search and the qualitative self-localisation procedure are the main contributions of the present research. To the best of our knowledge this is the first work that uses qualitative spatial representations both to perform robot self-localisation and to calibrate a robot's interpretation of its perceptual input.

We describe a workshop designed for 11-19 year-olds that considers the nature of intelligence and introduces the Turing test in various ways.Chatbots as mimics of intelligence are considered at length. Pupils are invited to use our system Turi in which they can build and test their own chatbot.The materials are free, open source and available for all to download [1].

Technocamps is a 3-year EU funded project to bring an awareness of technical Informatics to the 11-19 age group in the 'Convergence zone' of Wales. The project is coordinated through four universities, with materials and activities being developed in each of the academic hubs. Projects of this scale are rare, both in terms of geographic area and financial backing, creating a new set of challenges and opportunities. We review the background to the project and its need, outline its activities during its first year and the challenges they have presented, and make observations about portability and derived good practice that might inform similar projects elsewhere. Longer term evaluation and longitudinal study will develop during the next two years of the work.

International audience; Real-world face recognition systems require careful balancing of three concerns: computational cost, robustness, and discriminative power. In this paper we describe a new descriptor, POEM (Patterns of Oriented Edge Magnitudes) by applying a self-similarity based structure on oriented magnitudes and prove that it addresses all three criteria. Experimental results on the FERET databases show that POEM outperforms other descriptors when used with nearest neighbour classifiers. With LFW by combining POEM with GMMs and with multi-kernel SVMs, we achieve comparable results to the state of the art. Impressively, POEM is around 20 times faster than Gabor-based methods

In this work we tackle the issue of visually recognising a place without any prior knowledge of its position, even in a world where the same place can look different or many places can look identical.

Estimation of attitude and orientation is a critically important technique for ground wheeled autonomous robots like driverless cars. By means of attitude estimation, robots can not only evaluate the risk of overturning the vehicle, but also correct many sensor errors caused by robot motion or vibration. Traditionally, odometry (wheel encoders) is widely used to provide speed information for localization in dead-reckoning systems, and GPS fulfills the same role when robots navigate in outdoor environments. Visual odometry determines the position and orientation of a vehicle based on analyzing a sequence of images only.

This paper describes the conception, motivation, organization, and evaluation of a national, one-day event for women students of computing: the BCSWomen Lovelace Colloquium. The aim of this paper is to demonstrate that such events have value for women students of computing. We hope to show that through introducing these undergraduate women to high profile role models we can inspire them, and that through providing the students with a forum for presenting their own work, we can be inspired by them ourselves. We believe this is a successful and economical model for an event which could be re-used in other countries or regions.

This paper describes a study into the attitudes and experiences of women at three distinct stages of the career pipeline: undergraduate, graduate student, and staff. Computing has often been likened to a "leaky pipeline" for women, so this work aims to consider various aspects of the student experience from the perspective of those who have in some sense succeeded and got at least as far as studying the subject at degree level. Through concentrating on the opinions and experiences of women who have persisted (and in some sense, done well) in computing, the authors hope to accentuate the positive: rather than work out what makes women drop out of computing, we instead consider what makes them stay.

Recently, cognitive psychologists and others have turned their attention to the formerly neglected study of shadows, and the information they purvey. These studies show that the human perceptual system values information from shadows very highly, particularly in the perception of depth, even to the detriment of other cues. However with a few notable exceptions, computer vision systems have treated shadows not as signal but as noise. This paper makes a step towards redressing this imbalance by considering the formal representation of shadows. We take one particular aspect of reasoning about shadows, developing the idea that shadows carry information about a fragment of the viewpoint of the light source. We start from the observation that the region on which the shadow is cast is occluded by the caster with respect to the light source and build a qualitative theory about shadows using a region-based spatial formalism about occlusion. Using this spatial formalism and a machine vision system we are able to draw simple conclusions about domain objects and egolocation for a mobile robot.

This paper describes a method for building visual scene models from video data using quantized descriptions of motion. This method enables us to make meaningful statements about video scenes as a whole (such as "this video is like that video") and about regions within these scenes (such as "this part of this scene is similar to this part of that scene"). We do this through unsupervised clustering of simple yet novel motion descriptors, which provide a quantized representation of gross motion within scene regions. Using these we can characterise the dominant patterns of motion, and then group spatial regions based upon both proximity and local motion similarity to define areas or regions with particular motion characteristics. We are able to process scenes in which objects are difficult to detect and track due to variable frame-rate, video quality or occlusion, and we are able to identify regions which differ by usage but which do not differ by appearance (such as frequently used paths across open space). We demonstrate our method on 50 videos making up very different scene types: indoor scenarios with unpredictable unconstrained motion, junction scenes, road and path scenes, and open squares or plazas. We show that these scenes can be clustered using our representation, and that the incorporation of learned spatial relations into the representation enables us to cluster more effectively.

This paper describes a method for building visual "maps" from video data using quantized descriptions of motion. This enables unsupervised classification of scene regions based upon the motion patterns observed within them. Our aim is to recognise generic places using a qualitative representation of the spatial layout of regions with common motion patterns. Such places are characterised by the distribution of these motion patterns as opposed to static appearance patterns, and could include locations such as train platforms, bus stops, and park benches. Motion descriptions are obtained by tracking image features over a temporal window, and are then subjected to normalisation and thresholding to provide a quantized representation of that feature's gross motion. Input video is quantized spatially into N×Npixel blocks, and a histogram of the frequency of occurrence of each vector is then built for each of these small areas of scene. Within these we can therefore characterise the dominant patterns of motion, and then group our spatial regions based upon both proximity and local motion similarity to define areas or regions with particular motion characteristics. Moving up a level we then consider the relationship between the motion in adjacent spatial areas, and can characterise the dominant patterns of motion expected in a particular part of the scene over time. The current paper differs from previous work which has largely been based on the pathsof moving agents, and therefore restricted to scenes in which such paths are identifiable. We demonstrate our method in three very different scenes: an indoor room scenario with multiple chairs and unpredictable unconstrained motion, an underground station featuring regions where motion is constrained (train tracks) and regions with complicated motion and difficult occlusion relationships (platform), and an outdoor scene with challenging camera motion and partially overlapping video streams.

This paper describes a novel approach to the problem of automated visual surveillance. The authors have extended an existing algorithm which uses a cognitive model of navigation to explain behaviour in a surveillance setting. We then take this cognitive model and apply it to the problem of filtering surveillance data: typically, a surveillance or CCTV installation will have a limited number of operatives monitoring a large number of cameras. The proposed system filters upon inexplicability scores, on the grounds that those trajectories which we can explain in terms of simple goals are exactly those trajectories which are uninteresting: it is only those we cannot simply explain which are worth attending to. Initial results are promising, with over 50% of uninteresting trajectories being excluded.

Image analysis is a field of research which, combined with novel methods of capturing images, can help to bridge the genotype–phenotype gap, where our understanding of the genotype has until now been leaps and bounds ahead of our ability to work with the phenotype. Methods of automating image capture in plant science research have increased in usage recently, as has the need to provide objective and highly accurate measures on large image datasets, thereby bringing the phenotype back to the centre of interest. In this special issue of Functional Plant Biology, we present some recent advances in the field of image analysis, and look at examples of different kinds of image processing and computer vision, which is occurring with increasing frequency in the plant sciences.

Hannah Dee, deputy chair of BCSWomen and research fellow at the University of Leeds, analyses some potential ways to support women in computing from school to the workplace.