Modeling and Calibrating Visual Yield Estimates in Vineyards
Accurate yield estimates are of great value to vineyard growers to make informed management decisions such as crop thinning, shoot thinning, irrigation and nutrient delivery, preparing for harvest and planning for market. Current methods are labor intensive because they involve destructive hand sampling and are practically too sparse to capture spatial variability in large vineyard blocks. Here we report on an approach to predict vineyard yield automatically and non-destructively using images collected from vehicles driving along vineyard rows. Computer vision algorithms are applied to detect grape berries in images that have been registered together to generate high-resolution estimates. We propose an underlying model relating image measurements to harvest yield and study practical approaches to calibrate the two. We report on results on datasets of several hundred vines collected both early and in the middle of the growing season. We find that it is possible to estimate yield to within 4 % using calibration data from prior harvest data and 3 % using calibration data from destructive hand samples at the time of imaging.
KeywordsHarvest Data Yield Prediction Berry Weight Hand Sample Harvest Yield
Work funded by the National Grape and Wine Initiative, (info@NGWI.org). Narasimhan was supported partially by NSF awards IIS-0964562 and CAREER IIS-0643628 and an ONR grant N00014-11-1-0295.
- 1.P. Blom, J. Tarara, Trellis tension monitoring improves yield estimation in vineyards. HortScience 44, 678–685 (2009)Google Scholar
- 2.P. Clingeleffer, G. Dunn, M. Krstic, S. Martin, Crop development, crop estimation and crop control to secure quality and production of major wine grape varieties: A national approach. Grape and Wine Research and Development Corporation, Australia, Technical report, 2001Google Scholar
- 3.D. Dey, L. Mummert, R. Sukthankar, Classication of plant structures from uncalibrated image sequences, in IEEE Workshop on the Applications of Computer Vision (WACV) (2012)Google Scholar
- 5.J. Federici, R. Wample, D. Rodriguez, S. Mukherjee, Application of terahertz gouy phase shift from curved surfaces for estimation of crop yield. Appl. Opt. 48, 1382–1388 (2009)Google Scholar
- 6.A. Jimenez, R. Ceres, J. Pons, A survey of computer vision methods for locating fruit on trees, in Transaction of the ASAE, vol. 43, pp. 1911–1920 (2000)Google Scholar
- 7.B. Kitt, A. Geiger, H. Lategahn, Visual odometry based on stereo image sequences with ransac-based outlier rejection scheme, in IEEE Intelligent Vehicles Symposium (2010)Google Scholar
- 8.J.A. Martinez-Casasnovas, X. Bordes, Viticultura de precisión: Predicción decosecha a partir de variables del cultivo e índices de vegetación. Revista de Teledetección 24, 67–71 (2005)Google Scholar
- 9.S. Nuske, S. Achar, T. Bates, S. Narasimhan, S. Singh, Yield estimation in vineyards by visual grape detection, in Proceedings of the 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (2011)Google Scholar
- 10.S. Singh, M. Bergerman, J. Cannons, B. Grocholsky, B. Hamner, G. Holguin, L. Hull, V. Jones, G. Kantor, H. Koselka, G. Li, J. Owen, J. Park, W. Shi, J. Teza, Comprehensive automation for specialty crops: Year 1 results and lessons learned. J. Intell. Serv. Robot. Spec. Issue Agric. Robot. 3(4), 245–262 (2010)CrossRefGoogle Scholar
- 11.M. Swanson, C. Dima, A. Stentz, A multi-modal system for yield prediction in citrus trees, in ASABE Annual International Meeting, Pittsburgh, PA (2010)Google Scholar
- 12.J.A. Wolpert, E.P. Vilas, Estimating vineyard yields: Introduction to a simple, two-step method. Am. J. Enol. Viticulture 43, 384–388 (1992)Google Scholar