Panoptic segmentation applied to agriculture

• Grant number: 24/19729-5
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: January 01, 2025
• End date: December 31, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Thiago Teixeira Santos
• Grantee: Lilian Nogueira de Faria
• Host Institution: Embrapa Agricultura Digital. Empresa Brasileira de Pesquisa Agropecuária (EMBRAPA). Ministério da Agricultura, Pecuária e Abastecimento (Brasil). Campinas , SP, Brazil
• Associated research grant: 22/09319-9 - Center of Science for Development in Digital Agriculture - CCD-AD/SemeAr, AP.CCD

Abstract

The project focuses on developing panoptic segmentation models for fruit cultivation in images captured at ground level and aerial images obtained by drones. The main activities include:(i) organizing image databases for fruit cultivation,(ii) developing new annotation methodologies to facilitate panoptic segmentation, considering interactive tools and new foundational models,(iii) integrating RGB-D and multispectral sensors to improve automatic annotation,(iv) training panoptic segmentation models with the obtained data, evaluating performance, accuracy, and computational costs and(v) researching unsupervised techniques to develop efficient models for new domains and agricultural applications.