An eye for an eye: robust motion segmentation by applying the latest in human vision research

Automatically extracting interesting objects from videos is a very challenging task and is applicable to many research areas such robotics, medical imaging, content based indexing and visual surveillance. Automated visual surveillance is a major research area in computational vision and a commonly applied technique in an attempt to extract objects of interest is that of motion segmentation. Motion segmentation relies on the temporal changes that occur in video sequences to detect objects, but as a technique it presents many challenges that researchers have yet to surmount. Changes in real-time video sequences not only include interesting objects, environmental conditions such as wind, cloud cover, rain and snow may be present, in addition to rapid lighting changes, poor footage quality, moving shadows and reflections. The list provides only a sample of the challenges present. This thesis explores the use of motion segmentation as part of a computational vision system and provides solutions for a practical, generic approach with robust performance, using current neuro-biological, physiological and psychological research in primate vision as inspiration.

Achieving market segmentation from B2B sectorisation

Purpose – The creation of a target market strategy is integral to developing an effective business strategy. The concept of market segmentation is often cited as pivotal to establishing a target market strategy, yet all too often business-to-business marketers utilise little more than trade sectors or product groups as the basis for their groupings of customers, rather than customers' characteristics and buying behaviour. The purpose of this paper is to offer a solution for managers, focusing on customer purchasing behaviour, which evolves from the organisation's existing criteria used for grouping its customers. Design/methodology/approach – One of the underlying reasons managers fail to embrace best practice market segmentation is their inability to manage the transition from how target markets in an organisation are currently described to how they might look when based on customer characteristics, needs, purchasing behaviour and decision-making. Any attempt to develop market segments should reflect the inability of organisations to ignore their existing customer group classification schemes and associated customer-facing operational practices, such as distribution channels and sales force allocations. Findings – A straightforward process has been derived and applied, enabling organisations to practice market segmentation in an evolutionary manner, facilitating the transition to customer-led target market segments. This process also ensures commitment from the managers responsible for implementing the eventual segmentation scheme. This paper outlines the six stages of this process and presents an illustrative example from the agrichemicals sector, supported by other cases. Research implications – The process presented in this paper for embarking on market segmentation focuses on customer purchasing behaviour rather than business sectors or product group classifications - which is true to the concept of market segmentation - but in a manner that participating managers find non-threatening. The resulting market segments have their basis in the organisation's existing customer classification schemes and are an iteration to which most managers readily buy-in. Originality/value – Despite the size of the market segmentation literature, very few papers offer step-by-step guidance for developing customer-focused market segments in business-to-business marketing. The analytical tool for assessing customer purchasing deployed in this paper originally was created to assist in marketing planning programmes, but has since proved its worth as the foundation for creating segmentation schemes in business marketing, as described in this paper.

On fusion for robust motion segmentation

While a multitude of motion segmentation algorithms have been presented in the literature, there has not been an objective assessment of different approaches to fusing their outputs. This paper investigates the application of 4 different fusion schemes to the outputs of 3 probabilistic pixel-level segmentation algorithms. We performed an extensive experimentation using 6 challenge categories from the changedetection.net dataset demonstrating that in general simple majority vote proves to be more effective than more complex fusion schemes.

Segmentation-level fusion for iris recognition

This paper investigates the potential of fusion at normalisation/segmentation level prior to feature extraction. While there are several biometric fusion methods at data/feature level, score level and rank/decision level combining raw biometric signals, scores, or ranks/decisions, this type of fusion is still in its infancy. However, the increasing demand to allow for more relaxed and less invasive recording conditions, especially for on-the-move iris recognition, suggests to further investigate fusion at this very low level. This paper focuses on the approach of multi-segmentation fusion for iris biometric systems investigating the benefit of combining the segmentation result of multiple normalisation algorithms, using four methods from two different public iris toolkits (USIT, OSIRIS) on the public CASIA and IITD iris datasets. Evaluations based on recognition accuracy and ground truth segmentation data indicate high sensitivity with regards to the type of errors made by segmentation algorithms.

Tensor LRR and sparse coding-based subspace clustering

Subspace clustering groups a set of samples from a union of several linear subspaces into clusters, so that the samples in the same cluster are drawn from the same linear subspace. In the majority of the existing work on subspace clustering, clusters are built based on feature information, while sample correlations in their original spatial structure are simply ignored. Besides, original high-dimensional feature vector contains noisy/redundant information, and the time complexity grows exponentially with the number of dimensions. To address these issues, we propose a tensor low-rank representation (TLRR) and sparse coding-based (TLRRSC) subspace clustering method by simultaneously considering feature information and spatial structures. TLRR seeks the lowest rank representation over original spatial structures along all spatial directions. Sparse coding learns a dictionary along feature spaces, so that each sample can be represented by a few atoms of the learned dictionary. The affinity matrix used for spectral clustering is built from the joint similarities in both spatial and feature spaces. TLRRSC can well capture the global structure and inherent feature information of data, and provide a robust subspace segmentation from corrupted data. Experimental results on both synthetic and real-world data sets show that TLRRSC outperforms several established state-of-the-art methods.