Robust recognition and segmentation of human actions using HMMs with missing observations

This paper describes the integration of missing observation data with hidden Markov models to create a framework that is able to segment and classify individual actions from a stream of human motion using an incomplete 3D human pose estimation. Based on this framework, a model is trained to automatically segment and classify an activity sequence into its constituent subactions during inferencing. This is achieved by introducing action labels into the observation vector and setting these labels as missing data during inferencing, thus forcing the system to infer the probability of each action label. Additionally, missing data provides recognition-level support for occlusions and imperfect silhouette segmentation, permitting the use of a fast (real-time) pose estimation that delegates the burden of handling undetected limbs onto the action recognition system. Findings show that the use of missing data to segment activities is an accurate and elegant approach. Furthermore, action recognition can be accurate even when almost half of the pose feature data is missing due to occlusions, since not all of the pose data is important all of the time.

Robust learning of discriminative projection for multicategory classification on the Stiefel manifold

Learning a robust projection with a small number of training samples is still a challenging problem in face recognition, especially when the unseen faces have extreme variation in pose, illumination, and facial expression. To address this problem, we propose a framework formulated under statistical learning theory that facilitates robust learning of a discriminative projection. Dimensionality reduction using the projection matrix is combined with a linear classifier in the regularized framework of lasso regression. The projection matrix in conjunction with the classifier parameters are then found by solving an optimization problem over the Stiefel manifold. The experimental results on standard face databases suggest that the proposed method outperforms some recent regularized techniques when the number of training samples is small.

Generating comprehensible summaries of rushes sequences based on robust feature matching

This paper describes our first attempt at tackling a pilot task in Trecvid: video summarization of rushes data [3]. Our method is based on the tight clustering produced via SIFT matching. In this first attempt, we try to examine how our approach performs without complex implementation in terms of concept detection and excerpt assembly (i.e, no picture-in-picture, split screen and special transitions). Although we do not perform very well in terms of concept inclusion, we rank very well in terms of the summary being easy to understand and relevancy of included segments.

Linking identities and viewpoints in home movies based on robust feature matching

The identification of useful structures in home video is difficult because this class of video is distinguished from other video sources by its unrestricted, non edited content and the absence of regulated storyline. In addition, home videos contain a lot of motion and erratic camera movements, with shots of the same character being captured from various angles and viewpoints. In this paper, we present a solution to the challenging problem of clustering shots and faces in home videos, based on the use of SIFT features. SIFT features have been known to be robust for object recognition; however, in dealing with the complexities of home video setting, the matching process needs to be augmented and adapted. This paper describes various techniques that can improve the number of matches returned as well as the correctness of matches. For example, existing methods for verification of matches are inadequate for cases when a small number of matches are returned, a common situation in home videos. We address this by constructing a robust classifier that works on matching sets instead of individual matches, allowing the exploitation of the geometric constraints between matches. Finally, we propose techniques for robustly extracting target clusters from individual feature matches.

Robust finite-horizon Kalman filtering for uncertain discrete-time systems

In this note, we propose a design for a robust finite-horizon Kalman filtering for discrete-time systems suffering from uncertainties in the modeling parameters and uncertainties in the observations process (missing measurements). The system parameter uncertainties are expected in the state, output and white noise covariance matrices. We find the upper-bound on the estimation error covariance and we minimize the proposed upper-bound.

Robust patchwork-based embedding and decoding scheme for digital audio watermarking

This paper presents a novel patchwork-based embedding and decoding scheme for digital audio watermarking. At the embedding stage, an audio segment is divided into two subsegments and the discrete cosine transform (DCT) coefficients of the subsegments are computed. The DCT coefficients related to a specified frequency region are then partitioned into a number of frame pairs. The DCT frame pairs suitable for watermark embedding are chosen by a selection criterion and watermarks are embedded into the selected DCT frame pairs by modifying their coefficients, controlled by a secret key. The modifications are conducted in such a way that the selection criterion used at the embedding stage can be applied at the decoding stage to identify the watermarked DCT frame pairs. At the decoding stage, the secret key is utilized to extract watermarks from the watermarked DCT frame pairs. Compared with existing patchwork watermarking methods, the proposed scheme does not require information of which frame pairs of the watermarked audio signal enclose watermarks and is more robust to conventional attacks.

Robust modular artmap for multi-class shape recognition

This paper presents a fuzzy ARTMAP (FAM) based modular architecture for multi-class pattern recognition known as modular adaptive resonance theory map (MARTMAP). The prediction of class membership is made collectively by combining outputs from multiple novelty detectors. Distance-based familiarity discrimination is introduced to improve the robustness of MARTMAP in the presence of noise. The effectiveness of the proposed architecture is analyzed and compared with ARTMAP-FD network, FAM network, and One-Against-One Support Vector Machine (OAO-SVM). Experimental results show that MARTMAP is able to retain effective familiarity discrimination in noisy environment, and yet less sensitive to class imbalance problem as compared to its counterparts.

Developing robust assessment criteria for postgraduate research oriented papers

Assessment criteria designed to fully evaluate prescribed learning outcomes is a significant aid to both student and staff alike. For the student, it allows them to fully understand the requirements for a specific grade and for staff, it simplifies marking (grading) and minimises the likelihood of student appeals against assessment. Whilst criterion referencing is common place in the more traditional analytical type taught papers common in the Engineering degree curriculum it is perhaps less commonly utilised for research based papers. Presented here is a case study where both learning outcomes and achievement criteria have been proposed for a postgraduate research methodology paper which prepares students for their thesis. It has significant cross over to a descriptor for the thesis paper itself and is considered a template which could be equally applied to other subject domains where research methodology is taught.

Robust single-hidden layer feedforward network-based pattern classifier

In this paper, a new robust single-hidden layer feedforward network (SLFN)-based pattern classifier is developed. It is shown that the frequency spectrums of the desired feature vectors can be specified in terms of the discrete Fourier transform (DFT) technique. The input weights of the SLFN are then optimized with the regularization theory such that the error between the frequency components of the desired feature vectors and the ones of the feature vectors extracted from the outputs of the hidden layer is minimized. For the linearly separable input patterns, the hidden layer of the SLFN plays the role of removing the effects of the disturbance from the noisy input data and providing the linearly separable feature vectors for the accurate classification. However, for the nonlinearly separable input patterns, the hidden layer is capable of assigning the DFTs of all feature vectors to the desired positions in the frequencydomain such that the separability of all nonlinearly separable patterns are maximized. In addition, the output weights of the SLFN are also optimally designed so that both the empirical and the structural risks are well balanced and minimized in a noisy environment. Two simulation examples are presented to show the excellent performance and effectiveness of the proposed classification scheme.

Global non-smooth optimization in robust multivariate regression

Robust regression in statistics leads to challenging optimization problems. Here, we study one such problem, in which the objective is non-smooth, non-convex and expensive to calculate. We study the numerical performance of several derivative-free optimization algorithms with the aim of computing robust multivariate estimators. Our experiences demonstrate that the existing algorithms often fail to deliver optimal solutions. We introduce three new methods that use Powell's derivative-free algorithm. The proposed methods are reliable and can be used when processing very large data sets containing outliers.