Superpixel Segmentation Using Dynamic and Iterative Spanning Forest

Autor(es)

Belem, Felipe C. ^[1] ; Guimaraes, Silvio Jamil F. ^[2] ; Falcao, Alexandre X. ^[1]

Afiliação do(s) autor(es)

^[1] Univ Campinas UNICAMP, BR-13083852 Campinas, SP - Brazil

^[2] Pontifical Catholic Univ Minas Gerais PUC Minas, BR-31980110 Belo Horizonte, MG - Brazil

• Tipo de documento: Artigo Científico
• Fonte: IEEE SIGNAL PROCESSING LETTERS; v. 27, p. 1440-1444, 2020.
• Citações Web of Science: 0

Resumo

As constituent parts of image objects, superpixels can improve several higher-level operations. However, image segmentation methods might have their accuracy severely compromised for reduced numbers of superpixels. To mitigate the problem, we introduce Dynamic Iterative Spanning Forest (DISF), a seed-based method that improves all components in the Iterative Spanning Forest (ISF) framework for superpixel segmentation. DISF relies on a new strategy for seed estimation that can find more relevant seeds, reconstruct relevant edges along with iterations, and guarantee the desired number of superpixels. DISF also assures optimal spanning forests for path costs based on dynamic arc-weight estimation, being faster as the desired number of superpixels grows. We show that DISF can improve effectiveness on three datasets with distinct object properties, requiring significantly fewer iterations than all seed-based baselines. (AU)

• Processo FAPESP: 14/12236-1 - AnImaLS: Anotação de Imagem em Larga Escala: o que máquinas e especialistas podem aprender interagindo?
• Beneficiário: Alexandre Xavier Falcão
• Modalidade de apoio: Auxílio à Pesquisa - Temático