In the pursuit of effective affective computing : the relationship between features and registration

For facial expression recognition systems to be applicable in the real world, they need to be able to detect and track a previously unseen person's face and its facial movements accurately in realistic environments. A highly plausible solution involves performing a "dense" form of alignment, where 60-70 fiducial facial points are tracked with high accuracy. The problem is that, in practice, this type of dense alignment had so far been impossible to achieve in a generic sense, mainly due to poor reliability and robustness. Instead, many expression detection methods have opted for a "coarse" form of face alignment, followed by an application of a biologically inspired appearance descriptor such as the histogram of oriented gradients or Gabor magnitudes. Encouragingly, recent advances to a number of dense alignment algorithms have demonstrated both high reliability and accuracy for unseen subjects [e.g., constrained local models (CLMs)]. This begs the question: Aside from countering against illumination variation, what do these appearance descriptors do that standard pixel representations do not? In this paper, we show that, when close to perfect alignment is obtained, there is no real benefit in employing these different appearance-based representations (under consistent illumination conditions). In fact, when misalignment does occur, we show that these appearance descriptors do work well by encoding robustness to alignment error. For this work, we compared two popular methods for dense alignment-subject-dependent active appearance models versus subject-independent CLMs-on the task of action-unit detection. These comparisons were conducted through a battery of experiments across various publicly available data sets (i.e., CK+, Pain, M3, and GEMEP-FERA). We also report our performance in the recent 2011 Facial Expression Recognition and Analysis Challenge for the subject-independent task.

Robust facial feature extraction and matching

Automated feature extraction and correspondence determination is an extremely important problem in the face recognition community as it often forms the foundation of the normalisation and database construction phases of many recognition and verification systems. This paper presents a completely automatic feature extraction system based upon a modified volume descriptor. These features form a stable descriptor for faces and are utilised in a reversible jump Markov chain Monte Carlo correspondence algorithm to automatically determine correspondences which exist between faces. The developed system is invariant to changes in pose and occlusion and results indicate that it is also robust to minor face deformations which may be present with variations in expression.

Towards spontaneous facial expression recognition in real-world video

Facial expression is an important channel of human social communication. Facial expression recognition (FER) aims to perceive and understand emotional states of humans based on information in the face. Building robust and high performance FER systems that can work in real-world video is still a challenging task, due to the various unpredictable facial variations and complicated exterior environmental conditions, as well as the difficulty of choosing a suitable type of feature descriptor for extracting discriminative facial information. Facial variations caused by factors such as pose, age, gender, race and occlusion, can exert profound influence on the robustness, while a suitable feature descriptor largely determines the performance. Most present attention on FER has been paid to addressing variations in pose and illumination. No approach has been reported on handling face localization errors and relatively few on overcoming facial occlusions, although the significant impact of these two variations on the performance has been proved and highlighted in many previous studies. Many texture and geometric features have been previously proposed for FER. However, few comparison studies have been conducted to explore the performance differences between different features and examine the performance improvement arisen from fusion of texture and geometry, especially on data with spontaneous emotions. The majority of existing approaches are evaluated on databases with posed or induced facial expressions collected in laboratory environments, whereas little attention has been paid on recognizing naturalistic facial expressions on real-world data. This thesis investigates techniques for building robust and high performance FER systems based on a number of established feature sets. It comprises of contributions towards three main objectives: (1) Robustness to face localization errors and facial occlusions. An approach is proposed to handle face localization errors and facial occlusions using Gabor based templates. Template extraction algorithms are designed to collect a pool of local template features and template matching is then performed to covert these templates into distances, which are robust to localization errors and occlusions. (2) Improvement of performance through feature comparison, selection and fusion. A comparative framework is presented to compare the performance between different features and different feature selection algorithms, and examine the performance improvement arising from fusion of texture and geometry. The framework is evaluated for both discrete and dimensional expression recognition on spontaneous data. (3) Evaluation of performance in the context of real-world applications. A system is selected and applied into discriminating posed versus spontaneous expressions and recognizing naturalistic facial expressions. A database is collected from real-world recordings and is used to explore feature differences between standard database images and real-world images, as well as between real-world images and real-world video frames. The performance evaluations are based on the JAFFE, CK, Feedtum, NVIE, Semaine and self-collected QUT databases. The results demonstrate high robustness of the proposed approach to the simulated localization errors and occlusions. Texture and geometry have different contributions to the performance of discrete and dimensional expression recognition, as well as posed versus spontaneous emotion discrimination. These investigations provide useful insights into enhancing robustness and achieving high performance of FER systems, and putting them into real-world applications.

The prevalence and perception of pain amongst hospital in-patients

The aim of this paper is to describe the prevalence and perceptions of pain and pain management amongst hospital in-patients. A cross-sectional descriptive survey of 205 patients was conducted. Presence and severity of pain was assessed using verbal descriptor and visual analogue scales, and perceptions of pain were assessed using multi-item scales. Although the severity of pain reported was consistent across age groups and clinical areas, women in the study sample were significantly more likely to report high levels of pain than men. Differences in how men and women communicate their pain were observed, with women indicating that they were less willing to ask for help with their pain. Results suggest that pain continues to be an important problem for a large number of men and women in hospital, and that the experience of pain impacts negatively upon their well-being. Gender differences in the experience of and response to pain remain important considerations for clinical nurses who have major responsibilities for the management of pain in hospitalized patients.

Improved foreground detection via block-based classifier cascade with probabilistic decision integration

Background subtraction is a fundamental low-level processing task in numerous computer vision applications. The vast majority of algorithms process images on a pixel-by-pixel basis, where an independent decision is made for each pixel. A general limitation of such processing is that rich contextual information is not taken into account. We propose a block-based method capable of dealing with noise, illumination variations, and dynamic backgrounds, while still obtaining smooth contours of foreground objects. Specifically, image sequences are analyzed on an overlapping block-by-block basis. A low-dimensional texture descriptor obtained from each block is passed through an adaptive classifier cascade, where each stage handles a distinct problem. A probabilistic foreground mask generation approach then exploits block overlaps to integrate interim block-level decisions into final pixel-level foreground segmentation. Unlike many pixel-based methods, ad-hoc postprocessing of foreground masks is not required. Experiments on the difficult Wallflower and I2R datasets show that the proposed approach obtains on average better results (both qualitatively and quantitatively) than several prominent methods. We furthermore propose the use of tracking performance as an unbiased approach for assessing the practical usefulness of foreground segmentation methods, and show that the proposed approach leads to considerable improvements in tracking accuracy on the CAVIAR dataset.

On robust face recognition via sparse encoding : the good, the bad, and the ugly

In the field of face recognition, Sparse Representation (SR) has received considerable attention during the past few years. Most of the relevant literature focuses on holistic descriptors in closed-set identification applications. The underlying assumption in SR-based methods is that each class in the gallery has sufficient samples and the query lies on the subspace spanned by the gallery of the same class. Unfortunately, such assumption is easily violated in the more challenging face verification scenario, where an algorithm is required to determine if two faces (where one or both have not been seen before) belong to the same person. In this paper, we first discuss why previous attempts with SR might not be applicable to verification problems. We then propose an alternative approach to face verification via SR. Specifically, we propose to use explicit SR encoding on local image patches rather than the entire face. The obtained sparse signals are pooled via averaging to form multiple region descriptors, which are then concatenated to form an overall face descriptor. Due to the deliberate loss spatial relations within each region (caused by averaging), the resulting descriptor is robust to misalignment & various image deformations. Within the proposed framework, we evaluate several SR encoding techniques: l1-minimisation, Sparse Autoencoder Neural Network (SANN), and an implicit probabilistic technique based on Gaussian Mixture Models. Thorough experiments on AR, FERET, exYaleB, BANCA and ChokePoint datasets show that the proposed local SR approach obtains considerably better and more robust performance than several previous state-of-the-art holistic SR methods, in both verification and closed-set identification problems. The experiments also show that l1-minimisation based encoding has a considerably higher computational than the other techniques, but leads to higher recognition rates.

Matching relevance features with ontological concepts

In order to comprehend user information needs by concepts, this paper introduces a novel method to match relevance features with ontological concepts. The method first discovers relevance features from user local instances. Then, a concept matching approach is developed for matching these features to accurate concepts in a global knowledge base. This approach is significant for the transition of informative descriptor and conceptional descriptor. The proposed method is elaborately evaluated by comparing against three information gathering baseline models. The experimental results shows the matching approach is successful and achieves a series of remarkable improvements on search effectiveness.

Fast exact nearest neighbour matching in high dimensions using d-D Sort

Data structures such as k-D trees and hierarchical k-means trees perform very well in approximate k nearest neighbour matching, but are only marginally more effective than linear search when performing exact matching in high-dimensional image descriptor data. This paper presents several improvements to linear search that allows it to outperform existing methods and recommends two approaches to exact matching. The first method reduces the number of operations by evaluating the distance measure in order of significance of the query dimensions and terminating when the partial distance exceeds the search threshold. This method does not require preprocessing and significantly outperforms existing methods. The second method improves query speed further by presorting the data using a data structure called d-D sort. The order information is used as a priority queue to reduce the time taken to find the exact match and to restrict the range of data searched. Construction of the d-D sort structure is very simple to implement, does not require any parameter tuning, and requires significantly less time than the best-performing tree structure, and data can be added to the structure relatively efficiently.

Real-time video event detection in crowded scenes using MPEG derived features : a multiple instance learning approach

This paper presents an investigation into event detection in crowded scenes, where the event of interest co-occurs with other activities and only binary labels at the clip level are available. The proposed approach incorporates a fast feature descriptor from the MPEG domain, and a novel multiple instance learning (MIL) algorithm using sparse approximation and random sensing. MPEG motion vectors are used to build particle trajectories that represent the motion of objects in uniform video clips, and the MPEG DCT coefficients are used to compute a foreground map to remove background particles. Trajectories are transformed into the Fourier domain, and the Fourier representations are quantized into visual words using the K-Means algorithm. The proposed MIL algorithm models the scene as a linear combination of independent events, where each event is a distribution of visual words. Experimental results show that the proposed approaches achieve promising results for event detection compared to the state-of-the-art.

Establishing definitions and modeling public transport travel time variability

Public transport travel time variability (PTTV) is essential for understanding deteriorations in the reliability of travel time, optimizing transit schedules and route choices. This paper establishes key definitions of PTTV in which firstly include all buses, and secondly include only a single service from a bus route. The paper then analyses the day-to-day distribution of public transport travel time by using Transit Signal Priority data. A comprehensive approach using both parametric bootstrapping Kolmogorov-Smirnov test and Bayesian Information Creation technique is developed, recommends Lognormal distribution as the best descriptor of bus travel time on urban corridors. The probability density function of Lognormal distribution is finally used for calculating probability indicators of PTTV. The findings of this study are useful for both traffic managers and statisticians for planning and researching the transit systems.

Semi-binary based video features for activity representation

Efficient and effective feature detection and representation is an important consideration when processing videos, and a large number of applications such as motion analysis, 3D scene understanding, tracking etc. depend on this. Amongst several feature description methods, local features are becoming increasingly popular for representing videos because of their simplicity and efficiency. While they achieve state-of-the-art performance with low computational complexity, their performance is still too limited for real world applications. Furthermore, rapid increases in the uptake of mobile devices has increased the demand for algorithms that can run with reduced memory and computational requirements. In this paper we propose a semi binary based feature detectordescriptor based on the BRISK detector, which can detect and represent videos with significantly reduced computational requirements, while achieving comparable performance to the state of the art spatio-temporal feature descriptors. First, the BRISK feature detector is applied on a frame by frame basis to detect interest points, then the detected key points are compared against consecutive frames for significant motion. Key points with significant motion are encoded with the BRISK descriptor in the spatial domain and Motion Boundary Histogram in the temporal domain. This descriptor is not only lightweight but also has lower memory requirements because of the binary nature of the BRISK descriptor, allowing the possibility of applications using hand held devices.We evaluate the combination of detectordescriptor performance in the context of action classification with a standard, popular bag-of-features with SVM framework. Experiments are carried out on two popular datasets with varying complexity and we demonstrate comparable performance with other descriptors with reduced computational complexity.

A novel method for analysing lighting variance

Robust descriptor matching across varying lighting conditions is important for vision-based robotics. We present a novel strategy for quantifying the lighting variance of descriptors. The strategy works by utilising recovered low dimensional mappings from Isomap and our measure of the lighting variance of each of these mappings. The resultant metric allows different descriptors to be compared given a dataset and a set of keypoints. We demonstrate that the SIFT descriptor typically has lower lighting variance than other descriptors, although the result depends on semantic class and lighting conditions.

Training-free probability models for whole-image based place recognition

Whole-image descriptors such as GIST have been used successfully for persistent place recognition when combined with temporal filtering or sequential filtering techniques. However, whole-image descriptor localization systems often apply a heuristic rather than a probabilistic approach to place recognition, requiring substantial environmental-specific tuning prior to deployment. In this paper we present a novel online solution that uses statistical approaches to calculate place recognition likelihoods for whole-image descriptors, without requiring either environmental tuning or pre-training. Using a real world benchmark dataset, we show that this method creates distributions appropriate to a specific environment in an online manner. Our method performs comparably to FAB-MAP in raw place recognition performance, and integrates into a state of the art probabilistic mapping system to provide superior performance to whole-image methods that are not based on true probability distributions. The method provides a principled means for combining the powerful change-invariant properties of whole-image descriptors with probabilistic back-end mapping systems without the need for prior training or system tuning.

Towards training-free appearance-based localization : probabilistic models for whole-image descriptors

Whole image descriptors have recently been shown to be remarkably robust to perceptual change especially compared to local features. However, whole-image-based localization systems typically rely on heuristic methods for determining appropriate matching thresholds in a particular environment. These environment-specific tuning requirements and the lack of a meaningful interpretation of these arbitrary thresholds limits the general applicability of these systems. In this paper we present a Bayesian model of probability for whole-image descriptors that can be seamlessly integrated into localization systems designed for probabilistic visual input. We demonstrate this method using CAT-Graph, an appearance-based visual localization system originally designed for a FAB-MAP-style probabilistic input. We show that using whole-image descriptors as visual input extends CAT-Graph’s functionality to environments that experience a greater amount of perceptual change. We also present a method of estimating whole-image probability models in an online manner, removing the need for a prior training phase. We show that this online, automated training method can perform comparably to pre-trained, manually tuned local descriptor methods.

Novelty-based visual obstacle detection in agriculture

This paper describes a novel obstacle detection system for autonomous robots in agricultural field environments that uses a novelty detector to inform stereo matching. Stereo vision alone erroneously detects obstacles in environments with ambiguous appearance and ground plane such as in broad-acre crop fields with harvested crop residue. The novelty detector estimates the probability density in image descriptor space and incorporates image-space positional understanding to identify potential regions for obstacle detection using dense stereo matching. The results demonstrate that the system is able to detect obstacles typical to a farm at day and night. This system was successfully used as the sole means of obstacle detection for an autonomous robot performing a long term two hour coverage task travelling 8.5 km.