Face recognition robust to head pose from one sample image

Most face recognition systems only work well under quite constrained environments. In particular, the illumination conditions, facial expressions and head pose must be tightly controlled for good recognition performance. In 2004, we proposed a new face recognition algorithm, Adaptive Principal Component Analysis (APCA) [4], which performs well against both lighting variation and expression change. But like other eigenface-derived face recognition algorithms, APCA only performs well with frontal face images. The work presented in this paper is an extension of our previous work to also accommodate variations in head pose. Following the approach of Cootes et al, we develop a face model and a rotation model which can be used to interpret facial features and synthesize realistic frontal face images when given a single novel face image. We use a Viola-Jones based face detector to detect the face in real-time and thus solve the initialization problem for our Active Appearance Model search. Experiments show that our approach can achieve good recognition rates on face images across a wide range of head poses. Indeed recognition rates are improved by up to a factor of 5 compared to standard PCA.

Comparative performance of analytical techniques for polyhexamethylene biguanide (PHMB) in ophthalmic solutions

Purpose: The use of PHMB as a disinfectant in contact lens multipurpose solutions has been at the centre of much debate in recent times, particularly in relation to the issue of solution induced corneal staining. Clinical studies have been carried out which suggest different effects with individual contact lens materials used in combination with specific PHMB containing care regimes. There does not appear to be, however, a reliable analytical technique that would detect and quantify with any degree of accuracy the specific levels of PHMB that are taken up and released from individual solutions by the various contact lens materials. Methods: PHMB is a mixture of positively charged polymer units of varying molecular weight that has maximum absorbance wavelength of 236 nm. On the basis of these properties a range of assays including capillary electrophoresis, HPLC, a nickelnioxime colorimetric technique, mass spectrophotometry, UV spectroscopy and ion chromatography were assessed paying particular attention to each of their constraints and detection levels. Particular interest was focused on the relative advantage of contactless conductivity compared to UV and mass spectrometry detection in capillary electrophoresis (CE). This study provides an overview of the comparative performance of these techniques. Results: The UV absorbance of PHMB solutions, ranging from 0.0625 to 50 ppm was measured at 236 nm. Within this range the calibration curve appears to be linear however, absorption values below 1 ppm (0.0001%) were extremely difficult to reproduce. The concentration of PHMB in solutions is in the range of 0.0002–0.00005% and our investigations suggest that levels of PHMB below 0.0001% (levels encountered in uptake and release studies) can not be accurately estimated, in particular when analysing complex lens care solutions which can contain competitively absorbing, and thus interfering, species in the solution. The use of separative methodologies, such as CE using UV detection alone is similarly limited. Alternative techniques including contactless conductivity detection offer greater discrimination in complex solutions together with the opportunity for dual channel detection. Preliminary results achieved by TraceDec1 contactless conductivity detection, (Gain 150%, Offset 150) in conjunction with the Agilent capillary electrophoresis system using a bare fused silica capillary (extended light path, 50 mid, total length 64.5 cm, effective length 56 cm) and a cationic buffer at pH 3.2, exhibit great potential with reproducible PHMB split peaks. Conclusions: PHMB-based solutions are commonly associated with the potential to invoke corneal staining in combination with certain contact lens materials. However this terminology ‘PHMBbased solution’ is used primarily because PHMB itself has yet to be adequately implicated as the causative agent of the staining and compromised corneal cell integrity. The lack of well characterised adequately sensitive assays, coupled with the range of additional components that characterise individual care solutions pose a major barrier to the investigation of PHMB interactions in the lenswearing eye.

An adaptive motion model for person tracking with instantaneous head-pose features

This letter presents novel behaviour-based tracking of people in low-resolution using instantaneous priors mediated by head-pose. We extend the Kalman Filter to adaptively combine motion information with an instantaneous prior belief about where the person will go based on where they are currently looking. We apply this new method to pedestrian surveillance, using automatically-derived head pose estimates, although the theory is not limited to head-pose priors. We perform a statistical analysis of pedestrian gazing behaviour and demonstrate tracking performance on a set of simulated and real pedestrian observations. We show that by using instantaneous `intentional' priors our algorithm significantly outperforms a standard Kalman Filter on comprehensive test data.

Compared with specialist registrars, experienced staff nurses shorten the duration of weaning neonates from mechanical ventilation

OBJECTIVE: To compare the overall performance of specially trained neonatal nurses acting autonomously, unsupervised, and without a protocol with specialist registrars when weaning neonates from mechanical ventilation.

DESIGN: Prospective, randomized, controlled trial.

SETTING: A single neonatal intensive care unit.

PATIENTS: Neonates requiring conventional mechanical ventilation (n = 50).

INTERVENTIONS: Infants on conventional ventilation were randomly assigned to receive either nurse-led (n = 25) or registrar-led (n = 23) weaning. A total of 48 infants completed the study (two infants in the registrar group were excluded when their parents withdrew consent).

MEASUREMENTS AND MAIN RESULTS: The main outcome measure, median weaning time, was 1200 mins (95% confidence interval [CI], 621-1779 mins) in the nurse group and 3015 mins (95% CI, 2650-3380 mins) in the registrar group (p = .0458). The median time from treatment assignment to the first ventilator change was 60 mins (95% CI, 52-68 mins) in the nurse group and 120 mins (95% CI, 103-137 mins) in the registrar group (p = .35). On average, the nurses made ventilator changes every 4.5 hrs (95% CI, 2.9-6 hrs) and the registrars every 7.2 hrs (95% CI, 5.4-9 hrs; p = .003). The median number (range) of backward steps taken per infant was 0 (0-5 steps) in the nurse group and 1 (0-5 steps) in the registrar group (p = .019).

CONCLUSIONS: The findings of this study suggest that additional domains of neonatal critical care could be reviewed for their potential transfer to appropriately prepared nurses.

Fast and accurate hand pose detection for human-robot interaction

[EN]Enabling natural human-robot interaction using computer vision based applications requires fast and accurate hand detection. However, previous works in this field assume different constraints, like a limitation in the number of detected gestures, because hands are highly complex objects difficult to locate. This paper presents an approach which integrates temporal coherence cues and hand detection based on wrists using a cascade classifier. With this approach, we introduce three main contributions: (1) a transparent initialization mechanism without user participation for segmenting hands independently of their gesture, (2) a larger number of detected gestures as well as a faster training phase than previous cascade classifier based methods and (3) near real-time performance for hand pose detection in video streams.

Développement d'algorithmes d'estimation de la pose d'objets saisis par un préhenseur robotique

Les préhenseurs robotiques sont largement utilisés en industrie et leur déploiement pourrait être encore plus important si ces derniers étaient plus intelligents. En leur conférant des capacités tactiles et une intelligence leur permettant d’estimer la pose d’un objet saisi, une plus vaste gamme de tâches pourraient être accomplies par les robots. Ce mémoire présente le développement d’algorithmes d’estimation de la pose d’objets saisis par un préhenseur robotique. Des algorithmes ont été développés pour trois systèmes robotisés différents, mais pour les mêmes considérations. Effectivement, pour les trois systèmes la pose est estimée uniquement à partir d’une saisie d’objet, de données tactiles et de la configuration du préhenseur. Pour chaque système, la performance atteignable pour le système minimaliste étudié est évaluée. Dans ce mémoire, les concepts généraux sur l’estimation de la pose sont d’abord exposés. Ensuite, un préhenseur plan à deux doigts comprenant deux phalanges chacun est modélisé dans un environnement de simulation et un algorithme permettant d’estimer la pose d’un objet saisi par le préhenseur est décrit. Cet algorithme est basé sur les arbres d’interprétation et l’algorithme de RANSAC. Par la suite, un système expérimental plan comprenant une phalange supplémentaire par doigt est modélisé et étudié pour le développement d’un algorithme approprié d’estimation de la pose. Les principes de ce dernier sont similaires au premier algorithme, mais les capteurs compris dans le système sont moins précis et des adaptations et améliorations ont dû être appliquées. Entre autres, les mesures des capteurs ont été mieux exploitées. Finalement, un système expérimental spatial composé de trois doigts comprenant trois phalanges chacun est étudié. Suite à la modélisation, l’algorithme développé pour ce système complexe est présenté. Des hypothèses partiellement aléatoires sont générées, complétées, puis évaluées. L’étape d’évaluation fait notamment appel à l’algorithme de Levenberg-Marquardt.

L'utilité des données comptables dans les décisions de sélection et d'évaluation de performance de portefeuille

Dans la plupart des décisions à caractère économique, les données boursières jouent un rôle prépondérant. Pourtant, les données comptables dont le bénéfice comptable figurant aux états financiers, servent à fournir de l'information utile pour la prise de décision à caractère économique. Le débat sur l'utilité des données comptables publiées dans les états financiers continue à avoir lieu. Une des questions le plus souvent posée porte plus spécifiquement sur l'utilité de ces données dans les décisions de sélection et d'évaluation de performance de portefeuille. Les résultats de cette recherche nous ont permis de conclure que les décisions de sélection et d'évaluation de performance de portefeuille fondées sur des données comptables sont cohérentes avec les mêmes décisions basées sur des données boursières.

Vision-based tracking for sports performance analysis

With the world of professional sports shifting towards employing better sport analytics, the demand for vision-based performance analysis is growing increasingly in recent years. In addition, the nature of many sports does not allow the use of any kind of sensors or other wearable markers attached to players for monitoring their performances during competitions. This provides a potential application of systematic observations such as tracking information of the players to help coaches to develop their visual skills and perceptual awareness needed to make decisions about team strategy or training plans. My PhD project is part of a bigger ongoing project between sport scientists and computer scientists involving also industry partners and sports organisations. The overall idea is to investigate the contribution technology can make to the analysis of sports performance on the example of team sports such as rugby, football or hockey. A particular focus is on vision-based tracking, so that information about the location and dynamics of the players can be gained without any additional sensors on the players. To start with, prior approaches on visual tracking are extensively reviewed and analysed. In this thesis, methods to deal with the difficulties in visual tracking to handle the target appearance changes caused by intrinsic (e.g. pose variation) and extrinsic factors, such as occlusion, are proposed. This analysis highlights the importance of the proposed visual tracking algorithms, which reflect these challenges and suggest robust and accurate frameworks to estimate the target state in a complex tracking scenario such as a sports scene, thereby facilitating the tracking process. Next, a framework for continuously tracking multiple targets is proposed. Compared to single target tracking, multi-target tracking such as tracking the players on a sports field, poses additional difficulties, namely data association, which needs to be addressed. Here, the aim is to locate all targets of interest, inferring their trajectories and deciding which observation corresponds to which target trajectory is. In this thesis, an efficient framework is proposed to handle this particular problem, especially in sport scenes, where the players of the same team tend to look similar and exhibit complex interactions and unpredictable movements resulting in matching ambiguity between the players. The presented approach is also evaluated on different sports datasets and shows promising results. Finally, information from the proposed tracking system is utilised as the basic input for further higher level performance analysis such as tactics and team formations, which can help coaches to design a better training plan. Due to the continuous nature of many team sports (e.g. soccer, hockey), it is not straightforward to infer the high-level team behaviours, such as players’ interaction. The proposed framework relies on two distinct levels of performance analysis: low-level performance analysis, such as identifying players positions on the play field, as well as a high-level analysis, where the aim is to estimate the density of player locations or detecting their possible interaction group. The related experiments show the proposed approach can effectively explore this high-level information, which has many potential applications.

Performance and ruminal morphologic characteristics of Saanen kids fed ground, pelleted or extruded total ration

The aim of the present study was to determine feed intake and average weight gain and to evaluate the ruminal morphologic characteristics of Saanen kids slaughtered at 30, 45 and 60 days of age, according to a completely randomized design. Thirty-six non-castrated male Saanen kids were fed ground total ration, pelleted total ration, or extruded total ration. Feed intake and refusals were controlled daily and the animals were weighed at birth and then once a week. Newborn kids received a milk replacer and were weaned at 45 days. Immediately after slaughter, the animals were eviscerated, the entire digestive apparatus was removed from the carcass. The reticulo-rumen was separated, emptied, washed and weighed. Samples were collected from the dorsal sac, pillar area and ventral sac of the rumen, fixed for about 24h in Bouin's solution, dehydrated, embedded in Histosec and cut into 5 mu m sections. Results showed that dry matter intake (DMI) at weaning and post-weaning and weight gain were higher (P < 0.05) in animals that received the pelleted total ration. The weight of the reticulo-rumen accompanied body development and was heavier in these animals. Histologically, after weaning ruminal papillae were more developed in animals that received pelleted total ration. Length of papillae increased with increase of age. The ratio of papillary height to papillary width increased with age in the ventral sac and until weaning (P > 0.05). We conclude that the pelleting process of the total ration favored increased intake, with a 46.7% increase in weight gain and increase in rumen weight and papillae length, suggesting that best results are obtained with this processing. In general, no difference was observed between the results obtained with extruded and ground total ration, although animals fed extruded total ration showed an increase in rumen weight and papillae width. (c) 2004 Elsevier B.V All rights reserved.

A summative scoring system for evaluation of human kinematic performance

Evaluation of human kinematic performance is essential in rehabilitation and skill assessment. These services are in high demand where the improvements made due to exercises need to be regularly assessed. In some relevant industries there is a need to evaluate their employee capabilities quantitatively for accident compensation and insurance purposes. In particular, these assessments are preferred to be based on more quantifiable measures in a standardized form ensuring accuracy, reliability, ease of use and anywhere anytime information to the clinician. Therefore, it is necessary to have an efficient mechanism for evaluation and assessment of human kinematic movements as the current motion matching and recognition algorithms fall short due to characteristically strict specifications required in numerous health care applications. In this paper, we propose a summative approach using a double integral to define a closeness between two trajectories typically generated by human movement. This approach can be considered as a spatial scoring mechanism in the evaluation of human kinematic performance as well as in movement recognition applications. Several experiments based on computer simulations as well as real data were set up to examine the performance of the proposed approach as a scoring mechanism for the evaluation of human kinematic performances. The results demonstrated better characterization of the movement assessment and motion recognition ability, with a recognition rate of 86.19%, than the currently used methods such as Gaussian mixture models and pose normalization employed in motion recognition tasks. Finally, we use the scoring mechanism to analyze the proximity in human kinematic performance.

POSE ESTIMATION AND 3D RECONSTRUCTION USING SENSOR FUSION

A camera maps 3-dimensional (3D) world space to a 2-dimensional (2D) image space. In the process it loses the depth information, i.e., the distance from the camera focal point to the imaged objects. It is impossible to recover this information from a single image. However, by using two or more images from different viewing angles this information can be recovered, which in turn can be used to obtain the pose (position and orientation) of the camera. Using this pose, a 3D reconstruction of imaged objects in the world can be computed. Numerous algorithms have been proposed and implemented to solve the above problem; these algorithms are commonly called Structure from Motion (SfM). State-of-the-art SfM techniques have been shown to give promising results. However, unlike a Global Positioning System (GPS) or an Inertial Measurement Unit (IMU) which directly give the position and orientation respectively, the camera system estimates it after implementing SfM as mentioned above. This makes the pose obtained from a camera highly sensitive to the images captured and other effects, such as low lighting conditions, poor focus or improper viewing angles. In some applications, for example, an Unmanned Aerial Vehicle (UAV) inspecting a bridge or a robot mapping an environment using Simultaneous Localization and Mapping (SLAM), it is often difficult to capture images with ideal conditions. This report examines the use of SfM methods in such applications and the role of combining multiple sensors, viz., sensor fusion, to achieve more accurate and usable position and reconstruction information. This project investigates the role of sensor fusion in accurately estimating the pose of a camera for the application of 3D reconstruction of a scene. The first set of experiments is conducted in a motion capture room. These results are assumed as ground truth in order to evaluate the strengths and weaknesses of each sensor and to map their coordinate systems. Then a number of scenarios are targeted where SfM fails. The pose estimates obtained from SfM are replaced by those obtained from other sensors and the 3D reconstruction is completed. Quantitative and qualitative comparisons are made between the 3D reconstruction obtained by using only a camera versus that obtained by using the camera along with a LIDAR and/or an IMU. Additionally, the project also works towards the performance issue faced while handling large data sets of high-resolution images by implementing the system on the Superior high performance computing cluster at Michigan Technological University.