Automated Measurement of Berry Size in Images*. Issue 16 (2016)

• Record Type: Journal Article
• Authors: Mirbod, Omeed; Yoder, Luke; Nuske, Stephen
• Is Part Of: IFAC-PapersOnLine. Volume 49:Issue 16(2016)
• Page Start: 79
• Page End: 84
• Publication Date: 2016
• Subjects: computer vision -- agriculture -- stereo vision -- image segmentation -- image processing; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2016.10.015
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: Knowledge on berry size in grape vineyards can be a great asset for growers to help manage their crop whether for yield assessment or grape quality control. Having the ability to size berries of an entire field would allow growers to effectively monitor their vineyards at various stages of the growing season. Manual methods for determining berry size distribution of an entire field can be time consuming and rely on small sample sets which can lead to inaccuracies. This paper introduces an automated imaging system that measures diameter of grapes for every vine in an entire vineyard and generates a comprehensive map showing berry size variability which until now has not been available to growers. Believed to be the first example of mapping berry size across commercial vineyard blocks, this system uses computer vision techniques to locate and size the berries identifying submillimeter berry diameter differences. Maps of variability in berry size are shown to correlate with canopy size and yield. Diameter estimations are found to measure within 6% of manual measurements and a strong correlation is seen between estimated berry sizes and actual berry weights with r 2 = 0.96.