Speaker diarization can be considered to be one of the complex problems in speaker recognition. A reliable diarization system should be able to accurately determine the variable length utterances which a speaker contributes to multi-speaker conversations. This is a difficult problem since text-independent speaker identification and verification is yet to be improved for it to be applied reliably. While efficient speaker modelling is important for diarization, the acoustical representation of speech is the basic entity that signifies a speaker. This representation should be outstanding enough to prevent a speaker’s utterances from being lost in the acoustical congestion that is imposed by the rest of the talkers. For this purpose, it is proposed here, for the case of multiple-microphone diarization, multiple speech signals are used in the acoustic feature extraction instead of combining the signals beforehand. The reason is to make an optimal use of those signals in order to enrich the quality of the acoustical representation of the speaker. To this end, and since not all microphone signals (channels) may be desirable, two selection approaches are proposed in this work. These are, a best quality channel selection method and a novel approach for diverse channel selection. Furthermore, a novel method is proposed which retains the speech spectrum from selected least reverberated subbands of the available channels’ spectrums. A new model, referred to here as Averaged Joint Gradient (AJG), is introduced for this purpose. The proposed approach reduces the Diarization Error Rate (DER) in both of the diarization systems used in the evaluations. The first system is based on binary keys and achieves a maximum relative reduction in DER of 14%. The second one is a Gaussian Mixture Model-Bayesian Information Criterion (GMM-BIC) based system which achieves a maximum relative reduction in DER of 20%.

Abstract Human action recognition remains an important yet challenging task. This work proposes a novel action recognition system. It uses a novel multi-view region-adaptive multi-resolution-in-time depth motion map (MV-RAMDMM) formulation combined with appearance information. Multi-stream 3D convolutional neural networks (CNNs) are trained on the different views and time resolutions of the region-adaptive depth motion maps. Multiple views are synthesised to enhance the view invariance. The region-adaptive weights, based on localised motion, accentuate and differentiate parts of actions possessing faster motion. Dedicated 3D CNN streams for multi-time resolution appearance information are also included. These help to identify and differentiate between small object interactions. A pre-trained 3D-CNN is used here with fine-tuning for each stream along with multi-class support vector machines. Average score fusion is used on the output. The developed approach is capable of recognising both human action and human–object interaction. Three public-domain data-sets, namely MSR 3D Action, Northwestern UCLA multi-view actions and MSR 3D daily activity, are used to evaluate the proposed solution. The experimental results demonstrate the robustness of this approach compared with state-of-the-art algorithms.

Spectrum awareness is an important function in the context of cognitive radio systems. It determines the presence or absence of free channels in the spectrum and identifies free channels for secondary users. Cyclostationary Feature Detection is an example of a spectrum awareness technique which involves the detection of signals based on their features such as cyclic frequencies, symbol rates, carrier frequencies and modulation types. It detects signals at very low signal-to-noise ratios. However there are performance degrading constraints such as cyclic and sampling clock offsets that can occur at the receiver end. These offsets result from local oscillator frequency offsets, Doppler effects and jitter. We propose an efficient low complexity multi-slot cyclostationary feature detector that reduces the effects of these constraints through an offline optimization approach that produces the number and size of slot and fast Fourier transform to be used. These slots and fast Fourier transforms are used to show the reduction of these offsets and the detection performance compared for the case of different signal to noise ratios in the presence or absence of the receiver offsets. Also, the complexity of the model is compared with the complexity of the conventional implementation and it shows significant reductions in the number of required computations.

This paper is concerned with the modeling and analysis of the orientation and distance between steel fibers in X-ray micro-tomography data. The advantage of combining both orientation and separation in a model is that it helps provide a detailed understanding of how the steel fibers are arranged, which is easy to compare. The developed models are designed to summarize the randomness of the orientation distribution of the steel fibers both locally and across an entire volume based on multiscale entropy. Theoretical modeling, simulation, and application to real imaging data are shown here. The theoretical modeling of multiscale entropy for orientation includes a proof showing the final form of the multiscale taken over a linear range of scales. A series of image processing operations are also included to overcome interslice connectivity issues to help derive the statistical descriptions of the orientation distributions of the steel fibers. The results demonstrate that multiscale entropy provides unique insights into both simulated and real imaging data of steel fiber reinforced concrete.

A method to monitor elderly people in an indoor environment using conventional cameras is presented. The method can be used to identify people's activities and initiate suitable actions as needed. The originality of our approach is in combining spatial and temporal contexts with the position and orientation for the detected person. Preliminary evaluation, based only on the first two features (spatial and temporal), achieved the accuracy over 60% in a realistic residential environment. Although the results are based on using only two out of the four proposed input features, they already demonstrate a promising improvement over using a single feature in isolation.

A new fully automatic object tracking and segmentation framework is proposed. The framework consists of a motion-based bootstrapping algorithm concurrent to a shape-based active contour. The shape-based active contour uses finite shape memory that is automatically and continuously built from both the bootstrap process and the active-contour object tracker. A scheme is proposed to ensure that the finite shape memory is continuously updated but forgets unnecessary information. Two new ways of automatically extracting shape information from image data given a region of interest are also proposed. Results demonstrate that the bootstrapping stage provides important motion and shape information to the object tracker. This information is found to be essential for good (fully automatic) initialization of the active contour. Further results also demonstrate convergence properties of the content of the finite shape memory and similar object tracking performance in comparison with an object tracker with unlimited shape memory. Tests with an active contour using a fixed-shape prior also demonstrate superior performance for the proposed bootstrapped finite-shape-memory framework and similar performance when compared with a recently proposed active contour that uses an alternative online learning model.

We present segmentation and tracking of deformable objects using non-linear on-line learning of high-level shape information in the form of a level set function. The emphasis is for successful tracking of objects that undergo smooth arbitrary deformations, but without the a priori learning of shape constraints. The high-level shape information is learnt on-line by defining a memory of object samples in a high-dimensional shape space. These shape samples are then used as weights via a locally defined shape space kernel function to define a template against which potential future shapes of the tracked object can be compared. Results for the successful tracking of a range of deformable motions are presented. 1

An active contour based tracking framework is described that generates and integrates dynamic shape information without having to learn a priori shape constraints. This dynamic shape information is combined with fixative pho-tometric foreground model matching and background mismatching. Bound-ary based optical flow is also used to estimate the location of the object in each new video frame, incorporating Procrustes based shape alignment. Promising results under complex deformations of shape, varied levels of noise, and close-to-complete occlusion in the presence of complex textured backgrounds are presented. 1

A new variational Maximum A Posteriori (MAP) contextual modeling approach is presented that minimizes the product of two ratios: (a) the ratio of the model distribution to the distribution of currently estimated foreground pixels; (b) the ratio of the background distribution to the model distribution for all estimated background pixels. This approach provides robust discrimination to identify the division between foreground and background pixels, which is useful for applications such as object tracking.

Accurate classification of signals composed of two or more classification classes (e.g., biomedical imaging data with pathological structures) might utilize a density that takes account of the signal acquisition process. A new density based on a Gaussian point spread function (PSF) and another utilizing a phenomenological observation known as Benford's Law are presented. Histograms of filtered signals are compared with these densities. The results suggest that the Gaussian PSF-based density is somewhat better than the Benford's Law density. Both approaches provide improved fits to histograms from data convolved with a variety of different PSFs over an existing mixture formulation.