Evaluation of texture and geometry for dimensional facial expression recognition

Facial expression recognition (FER) algorithms mainly focus on classification into a small discrete set of emotions or representation of emotions using facial action units (AUs). Dimensional representation of emotions as continuous values in an arousal-valence space is relatively less investigated. It is not fully known whether fusion of geometric and texture features will result in better dimensional representation of spontaneous emotions. Moreover, the performance of many previously proposed approaches to dimensional representation has not been evaluated thoroughly on publicly available databases. To address these limitations, this paper presents an evaluation framework for dimensional representation of spontaneous facial expressions using texture and geometric features. SIFT, Gabor and LBP features are extracted around facial fiducial points and fused with FAP distance features. The CFS algorithm is adopted for discriminative texture feature selection. Experimental results evaluated on the publicly accessible NVIE database demonstrate that fusion of texture and geometry does not lead to a much better performance than using texture alone, but does result in a significant performance improvement over geometry alone. LBP features perform the best when fused with geometric features. Distributions of arousal and valence for different emotions obtained via the feature extraction process are compared with those obtained from subjective ground truth values assigned by viewers. Predicted valence is found to have a more similar distribution to ground truth than arousal in terms of covariance or Bhattacharya distance, but it shows a greater distance between the means.

Super-resolved faces for improved face recognition from surveillance video advances in biometrics

Characteristics of surveillance video generally include low resolution and poor quality due to environmental, storage and processing limitations. It is extremely difficult for computers and human operators to identify individuals from these videos. To overcome this problem, super-resolution can be used in conjunction with an automated face recognition system to enhance the spatial resolution of video frames containing the subject and narrow down the number of manual verifications performed by the human operator by presenting a list of most likely candidates from the database. As the super-resolution reconstruction process is ill-posed, visual artifacts are often generated as a result. These artifacts can be visually distracting to humans and/or affect machine recognition algorithms. While it is intuitive that higher resolution should lead to improved recognition accuracy, the effects of super-resolution and such artifacts on face recognition performance have not been systematically studied. This paper aims to address this gap while illustrating that super-resolution allows more accurate identification of individuals from low-resolution surveillance footage. The proposed optical flow-based super-resolution method is benchmarked against Baker et al.’s hallucination and Schultz et al.’s super-resolution techniques on images from the Terrascope and XM2VTS databases. Ground truth and interpolated images were also tested to provide a baseline for comparison. Results show that a suitable super-resolution system can improve the discriminability of surveillance video and enhance face recognition accuracy. The experiments also show that Schultz et al.’s method fails when dealing surveillance footage due to its assumption of rigid objects in the scene. The hallucination and optical flow-based methods performed comparably, with the optical flow-based method producing less visually distracting artifacts that interfered with human recognition.

Overview of the INEX 2009 Link the Wiki Track

In the third year of the Link the Wiki track, the focus has been shifted to anchor-to-bep link discovery. The participants were encouraged to utilize different technologies to resolve the issue of focused link discovery. Apart from the 2009 Wikipedia collection, the Te Ara collection was introduced for the first time in INEX. For the link the wiki tasks, 5000 file-to-file topics were randomly selected and 33 anchor-to-bep topics were nominated by the participants. The Te Ara collection does not contain hyperlinks and the task was to cross link the entire collection. A GUI tool for self-verification of the linking results was distributed. This helps participants verify the location of the anchor and bep. The assessment tool and the evaluation tool were revised to improve efficiency. Submission runs were evaluated against Wikipedia ground-truth and manual result set respectively. Focus-based evaluation was undertaken using a new metric. Evaluation results are presented and link discovery approaches are described

Topological map induction using neighbourhood information of places

In topological mapping, perceptual aliasing can cause different places to appear indistinguishable to the robot. In case of severely corrupted or non-available odometry information, topological mapping is difficult as the robot is challenged with the loop-closing problem; that is to determine whether it has visited a particular place before. In this article we propose to use neighbourhood information to disambiguate otherwise indistinguishable places. Using neighbourhood information for place disambiguation is an approach that neither depends on a specific choice of sensors nor requires geometric information such as odometry. Local neighbourhood information is extracted from a sequence of observations of visited places. In experiments using either sonar or visual observations from an indoor environment the benefits of using neighbourhood clues for the disambiguation of otherwise identical vertices are demonstrated. Over 90% of the maps we obtain are isomorphic with the ground truth. The choice of the robot’s sensors does not impact the results of the experiments much.

Rule-based approach for identifying assertions in clinical free-text data

A rule-based approach for classifying previously identified medical concepts in the clinical free text into an assertion category is presented. There are six different categories of assertions for the task: Present, Absent, Possible, Conditional, Hypothetical and Not associated with the patient. The assertion classification algorithms were largely based on extending the popular NegEx and Context algorithms. In addition, a health based clinical terminology called SNOMED CT and other publicly available dictionaries were used to classify assertions, which did not fit the NegEx/Context model. The data for this task includes discharge summaries from Partners HealthCare and from Beth Israel Deaconess Medical Centre, as well as discharge summaries and progress notes from University of Pittsburgh Medical Centre. The set consists of 349 discharge reports, each with pairs of ground truth concept and assertion files for system development, and 477 reports for evaluation. The system’s performance on the evaluation data set was 0.83, 0.83 and 0.83 for recall, precision and F1-measure, respectively. Although the rule-based system shows promise, further improvements can be made by incorporating machine learning approaches.

Unsupervised multi-label text classification using a world knowledge ontology

The development of text classification techniques has been largely promoted in the past decade due to the increasing availability and widespread use of digital documents. Usually, the performance of text classification relies on the quality of categories and the accuracy of classifiers learned from samples. When training samples are unavailable or categories are unqualified, text classification performance would be degraded. In this paper, we propose an unsupervised multi-label text classification method to classify documents using a large set of categories stored in a world ontology. The approach has been promisingly evaluated by compared with typical text classification methods, using a real-world document collection and based on the ground truth encoded by human experts.

System identification, estimation and control for a cost effective open-source quadcopter

This paper describes system identification, estimation and control of translational motion and heading angle for a cost effective open-source quadcopter — the MikroKopter. The dynamics of its built-in sensors, roll and pitch attitude controller, and system latencies are determined and used to design a computationally inexpensive multi-rate velocity estimator that fuses data from the built-in inertial sensors and a low-rate onboard laser range finder. Control is performed using a nested loop structure that is also computationally inexpensive and incorporates different sensors. Experimental results for the estimator and closed-loop positioning are presented and compared with ground truth from a motion capture system.

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.

A framework for a dense matching algorithm : Results using matching metrics and order statistic filters

An algorithm for computing dense correspondences between images of a stereo pair or image sequence is presented. The algorithm can make use of both standard matching metrics and the rank and census filters, two filters based on order statistics which have been applied to the image matching problem. Their advantages include robustness to radiometric distortion and amenability to hardware implementation. Results obtained using both real stereo pairs and a synthetic stereo pair with ground truth were compared. The rank and census filters were shown to significantly improve performance in the case of radiometric distortion. In all cases, the results obtained were comparable to, if not better than, those obtained using standard matching metrics. Furthermore, the rank and census have the additional advantage that their computational overhead is less than these metrics. For all techniques tested, the difference between the results obtained for the synthetic stereo pair, and the ground truth results was small.

Order statistic filters for image matching

The rank and census are two filters based on order statistics which have been applied to the image matching problem for stereo pairs. Advantages of these filters include their robustness to radiometric distortion and small amounts of random noise, and their amenability to hardware implementation. In this paper, a new matching algorithm is presented, which provides an overall framework for matching, and is used to compare the rank and census techniques with standard matching metrics. The algorithm was tested using both real stereo pairs and a synthetic pair with ground truth. The rank and census filters were shown to significantly improve performance in the case of radiometric distortion. In all cases, the results obtained were comparable to, if not better than, those obtained using standard matching metrics. Furthermore, the rank and census have the additional advantage that their computational overhead is less than these metrics. For all techniques tested, the difference between the results obtained for the synthetic stereo pair, and the ground truth results was small.

Automatic object segmentation of unstructured scenes using colour and depth maps

This study presents a segmentation pipeline that fuses colour and depth information to automatically separate objects of interest in video sequences captured from a quadcopter. Many approaches assume that cameras are static with known position, a condition which cannot be preserved in most outdoor robotic applications. In this study, the authors compute depth information and camera positions from a monocular video sequence using structure from motion and use this information as an additional cue to colour for accurate segmentation. The authors model the problem similarly to standard segmentation routines as a Markov random field and perform the segmentation using graph cuts optimisation. Manual intervention is minimised and is only required to determine pixel seeds in the first frame which are then automatically reprojected into the remaining frames of the sequence. The authors also describe an automated method to adjust the relative weights for colour and depth according to their discriminative properties in each frame. Experimental results are presented for two video sequences captured using a quadcopter. The quality of the segmentation is compared to a ground truth and other state-of-the-art methods with consistently accurate results.

Nonparametric semantic segmentation for 3D street scenes

In this paper we propose a method to generate a large scale and accurate dense 3D semantic map of street scenes. A dense 3D semantic model of the environment can significantly improve a number of robotic applications such as autonomous driving, navigation or localisation. Instead of using offline trained classifiers for semantic segmentation, our approach employs a data-driven, nonparametric method to parse scenes which easily scale to a large environment and generalise to different scenes. We use stereo image pairs collected from cameras mounted on a moving car to produce dense depth maps which are combined into a global 3D reconstruction using camera poses from stereo visual odometry. Simultaneously, 2D automatic semantic segmentation using a nonparametric scene parsing method is fused into the 3D model. Furthermore, the resultant 3D semantic model is improved with the consideration of moving objects in the scene. We demonstrate our method on the publicly available KITTI dataset and evaluate the performance against manually generated ground truth.

Mapping semantic knowledge for unsupervised text categorisation

Text categorisation is challenging, due to the complex structure with heterogeneous, changing topics in documents. The performance of text categorisation relies on the quality of samples, effectiveness of document features, and the topic coverage of categories, depending on the employing strategies; supervised or unsupervised; single labelled or multi-labelled. Attempting to deal with these reliability issues in text categorisation, we propose an unsupervised multi-labelled text categorisation approach that maps the local knowledge in documents to global knowledge in a world ontology to optimise categorisation result. The conceptual framework of the approach consists of three modules; pattern mining for feature extraction; feature-subject mapping for categorisation; concept generalisation for optimised categorisation. The approach has been promisingly evaluated by compared with typical text categorisation methods, based on the ground truth encoded by human experts.

Monocular vision based autonomous navigation for a cost-effective MAV in GPS-denied environments

In this paper, we present a monocular vision based autonomous navigation system for Micro Aerial Vehicles (MAVs) in GPS-denied environments. The major drawback of monocular systems is that the depth scale of the scene can not be determined without prior knowledge or other sensors. To address this problem, we minimize a cost function consisting of a drift-free altitude measurement and up-to-scale position estimate obtained using the visual sensor. We evaluate the scale estimator, state estimator and controller performance by comparing with ground truth data acquired using a motion capture system. All resources including source code, tutorial documentation and system models are available online.

Enabling aircraft emergency landings using active visual site detection

The ability to automate forced landings in an emergency such as engine failure is an essential ability to improve the safety of Unmanned Aerial Vehicles operating in General Aviation airspace. By using active vision to detect safe landing zones below the aircraft, the reliability and safety of such systems is vastly improved by gathering up-to-the-minute information about the ground environment. This paper presents the Site Detection System, a methodology utilising a downward facing camera to analyse the ground environment in both 2D and 3D, detect safe landing sites and characterise them according to size, shape, slope and nearby obstacles. A methodology is presented showing the fusion of landing site detection from 2D imagery with a coarse Digital Elevation Map and dense 3D reconstructions using INS-aided Structure-from-Motion to improve accuracy. Results are presented from an experimental flight showing the precision/recall of landing sites in comparison to a hand-classified ground truth, and improved performance with the integration of 3D analysis from visual Structure-from-Motion.