No abstract

Within this work a novel semi-supervised learning technique is introduced based on a simple iterative learning cycle together with learned thresholding techniques and an ensemble decision support system. State-of-the-art model performance and increased training data volume are demonstrated, through the use of unlabelled data when training deeply learned classification models. The methods presented work independently from the model architectures or loss functions, making this approach applicable to a wide range of machine learning and classification tasks. Evaluation of the proposed approach is performed on commonly used datasets when evaluating semi-supervised learning techniques as well as a number of more challenging image classification datasets (CIFAR-100 and a 200 class subset of ImageNet).

In this paper we evaluate the notion of scene analysis with regard to risk. We consider the problem of evaluating risk and potential hazards in an environment and providing a quantified risk score. A definition of risk is given incorporating two elements; Firstly scene stability, where Newtonian Physics are introduced into the scene analysis process, evaluating object stability within a scene. The effectiveness of which is demonstrated by conducting experiments on several scenes including a variety of stability levels. Secondly the analysis of the intrinsic risk related properties of an object, which is estimated using learning techniques and the utilisation of the 3D Voxel HOG descriptor, analysed against the state-of-the-art descriptors. Finally a new dataset is provided that is designed for scene analysis focusing on risk evaluation.

This is a repository copy of Smart IoT cameras for crowd analysis based on augmentation for automatic pedestrian detection, simulation and annotation.

Within this chapter the emerging topic of automated risk assessment in a domestic scene is discussed, state of the art techniques are reviewed followed by developed methodologies which focus on safer human and robotic interactions with an environment. By using the risk estimation framework, the notion of a quantitative risk score is presented. Hazards within a scene are evaluated and measured using risk elements which provide a numeric representation of specific types of risk. Emphasis is given to the concept of risk as a result of interaction with an environment, specifically whether human or robotic actions in a scene can effect overall risk. To this end, techniques which simulate human or robotic behaviour with regard to risk in an environment are reviewed. Specifically the ideas of interaction and visibility are addressed defining risk in terms of areas within a scene that are visited most often and which are least visible. As with any behaviour simulation techniques, validation of their accuracy is required and a number of simulation evaluation techniques are reviewed. Finally a conclusion as to the current state of automated risk assessment is given, with a brief look at the future of the research area.