In-field high throughput grapevine phenotyping with a consumer-grade depth camera

Abstract

Plant phenotyping, that is, the quantitative assessment of plant traits including growth, morphology, physiology, and yield, is a critical aspect towards efficient and effective crop management. Currently, plant phenotyping is a manually intensive and time consuming process, which involves human operators making measurements in the field, based on visual estimates or using hand-held devices. In this work, methods for automated grapevine phenotyping are developed, aiming to canopy volume estimation and bunch detection and counting. It is demonstrated that both measurements can be effectively performed in the field using a consumer-grade depth camera mounted onboard an agricultural vehicle.

Code and data availability

The supplied blocks describe grapevine phenotyping with an Intel RealSense R200 and CNN-based bunch detection, but contain no public phenotype dataset, image release, author code, or trained model availability statement. The only URL present (Caltech calibration toolbox) is a generic third-party calibration tool cited,

No evidence-backed public reproduction asset is currently recorded.