Fast 2D/3D object representation with growing neural gas

This work presents the design of a real-time system to model visual objects with the use of self-organising networks. The architecture of the system addresses multiple computer vision tasks such as image segmentation, optimal parameter estimation and object representation. We first develop a framework for building non-rigid shapes using the growth mechanism of the self-organising maps, and then we define an optimal number of nodes without overfitting or underfitting the network based on the knowledge obtained from information-theoretic considerations. We present experimental results for hands and faces, and we quantitatively evaluate the matching capabilities of the proposed method with the topographic product. The proposed method is easily extensible to 3D objects, as it offers similar features for efficient mesh reconstruction.

Community-led upgrading for self-reliance in informal settlements in South Africa: a review

Around the world, informal and low-income settlements (so-called “slums”) have been a major issue in city management and environmental sustainability in developing countries. Overall, African cities have an agenda for slum management and response. For example, the South African government introduced the Upgrade of Informal Settlements Program (UISP), as a comprehensive plan for upgrading slum settlements. Nevertheless, upgrading informal settlements from the bottom-up is key to inform broad protocols and strategies for sustainable communities and `adaptive cities´. Community-scale schemes can drive sustainability from the bottom-up and offer opportunities to share lessons learnt at the local level. Key success factors in their roll-out are: systems thinking; empowered local authorities that support decentralised solutions and multidisciplinary collaboration between the involved actors, including the affected local population. This research lies under the umbrella of sustainable bottom-up urban regeneration. As part of a larger project of collaboration between UK and SA research institutions, this paper presents an overview of in-situ participatory upgrade as an incremental strategy for upgrading informal settlements in the context of sustainable and resilient city. The motivation for this research is rooted in identifying the underpinning barriers and enabling drivers for up-scaling community-led, participatory upgrading approaches in informal settlements in the metropolitan area. This review paper seeks to provide some preliminary guidelines and recommendations for an integrated collaborative environmental and construction management framework to enhance community self-reliance. A theoretical approach based on the review of previous studies was combined with a pilot study conducted in Durban (South Africa) to investigate the feasibility of community-led upgrading processes.