Search Results (2)

Our story starts in April 2020, in the early stages of the UK’s first national COVID-19 lockdown. A multidisciplinary team of researchers and artists began a collaboration with Migrateful, a charity that runs cookery classes led by refugees, asylum seekers, and migrants struggling to integrate and access employment. Teaching classes and sharing their cuisine and stories helps the chefs develop their confidence and sense of belonging, and food is central to the enterprise. The focus of the project was a series of interactive online cookery classes delivered by Migrateful chefs, with ongoing involvement from the researchers and artists. In this paper, we weave together the research team’s reflections on the project with commentary from the participants and artists. We outline our methods and our learning from the collaboration and explain how it inspired new ways of thinking about refugee representation, food and belonging, co-creative storytelling, and virtual engagement. We discuss the ways in which Migrateful’s model helps to support the production of counter-narratives that value, foreground, and amplify migrants’ perspectives and voices while acknowledging the tensions involved in adapting this model to the virtual space. We emphasise the power dynamics inherent in engaging and researching with marginalised people and their stories while considering whether artistic involvement and creation may help to navigate some of these challenges, and we address how the virtual environment affected the potential for collaborative storytelling, interaction, and engagement levels among participants. Together, these reflections form a ‘recipe’ for what we hope to be a more meaningful and ethical model of engagement activity that builds on this learning. Full article

The pixel-based adaptive segmenter (PBAS) is a classic background modeling algorithm for change detection. However, it is difficult for the PBAS method to detect foreground targets in dynamic background regions. To solve this problem, based on PBAS, a weighted pixel-based adaptive segmenter named WePBAS for change detection is proposed in this paper. WePBAS uses weighted background samples as a background model. In the PBAS method, the samples in the background model are not weighted. In the weighted background sample set, the low-weight background samples typically represent the wrong background pixels and need to be replaced. Conversely, high-weight background samples need to be preserved. According to this principle, a directional background model update mechanism is proposed to improve the segmentation performance of the foreground targets in the dynamic background regions. In addition, due to the “background diffusion” mechanism, the PBAS method often identifies small intermittent motion foreground targets as background. To solve this problem, an adaptive foreground counter was added to the WePBAS to limit the “background diffusion” mechanism. The adaptive foreground counter can automatically adjust its own parameters based on videos’ characteristics. The experiments showed that the proposed method is competitive with the state-of-the-art background modeling method for change detection. Full article