Automatic grape bunch detection in vineyards based on affordable 3D phenotyping using a consumer webcam.

• Main Author: SANTOS, T. T.
• Publication Date: 2017
• Other Authors: BASSOI, L. H., OLDONI, H., MARTINS, R. L.
• Language: eng
• Source: Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice)
• Download full: http://www.alice.cnptia.embrapa.br/alice/handle/doc/1083291
• topic: Estimativa de podução; Métodos não-invasivos; Fenotipagem 3D; Visão estéro múltipla; Simultaneous localization and mapping; Yield estimation; Non-invasive methods; 3-D phenotyping; Multiple view stereo; Videira; Viticultura; Viticulture; Phenotype

This work presents a methodology for 3-D phenotyping of vineyards based on images captured by a low cost high-definition webcamera. A novel software application integrated visual odometry and multiple-view stereo components to create dense and accurate three-dimensional points clouds for vines, properly transformed to millimeter scale. Geometrical and color features of the points were employed by a classification procedure that reached 93% of accuracy on detecting points belonging to grapes. Individual bunches were automatically delimited and their volumes estimated. The sum of the estimated volumes per vine presented a coefficient of correlation of R = 0.99 to the real grape weight observed in each vine after harvesting.