GRAPE CS-ML DATABASE-INFORMED METHODS FOR CONTEMPORARY VINEYARD MANAGEMENT
Kancharakunt Yakubreddy, Srinivas Sai, Khader Basha Sk, Venkateswara Reddy, Venkateswara Reddy, Arturo Aquino, Maria Diago, Borja Millan, Javier Aguila, G Dunn, S Martin, R Chamelat, E Rosso, A Choksuriwong, C Rosenberger, H Laurent, P Bro, G Rabatel, C &guizard, S Madhuri, D Lokeshsai Phani Praveen, S Kumar, Sindhura, Srinivas Sai, Vellela, Srinivas Sai, Dr Vellela, Balamanigandan, A Madhuri, V Jyothi, S Praveen, S Sindhura, V Srinivas, D Kumar, Sk, P Khader Basha, A Venkata Kishan Rao, Venkateswara Reddy, B, Khader Bashask, D Roja, Phani Praveen, Tns Pappulasarala, Mani Koti, Siva Kumar, V Ganesh Manuri, D Saisrinivas, Swapna, Bethineedi, B Veerendra, Venkateswara, Reddy, Srinivas Sai, Venkateswara Vellela, B Reddy, M Kancharla K Chaitanya, Venkateswararao, Srinivas Sai, Dr Vellela, Krishna Murali, Srinivas Sai, Dr Vellela, Dr Balamanigandan, Phani Praveen
Abstract
This work makes two significant contributions to the current status of viticulture technology studies.We start with a detailed look at the history and current state of computer vision, image processing, and machine learning applications in the wine industry.We provide a concise overview of recent advances in vision systems and methodologies by analysing case studies from a wide range of fields, including as crop yield estimation, vineyard management and monitoring, disease detection, quality evaluation, and grape phonology.Here, we zero in on the ways in which modern vineyard management and vinification procedures can benefit from the application of computer vision and machine learning.In the paper's second section, we introduce the brandnew Grape CS-ML Database, which contains photos of grape varietals at various stages of development alongside the relevant ground truth data (e.g.pH, Brix, etc.) collected from chemical analysis.The creation of useful solutions for use in smart vineyards is a primary goal of this database, and it is hoped that it will inspire academics in computer vision and machine learning to work on this problem.We showcase the database's potential for a color-based berry recognition application by comparing white and red cultivars across a number of machine learning methods and colour spaces, and providing a set of reference data for evaluation.The study finishes by pointing out some of the issues that will need to be resolved in the future in order to fully utilise this technology in the viticulture industry.