Abstract

Abstract

Abstract

Phenological monitoring of Actinidia chinensis is critical for optimising operational costs and yield prediction. However, current manual assessment methods are time-consuming, making them impractical for large-scale precision agriculture applications. Most existing phenological datasets focus exclusively on image data without spatial validation. The Multi-Modal Actinidia chinensis Phenology Dataset is composed of (i) 1 665 annotated images of phenological stages from bud to fruit set and (ii) georeferenced videos with systematic manual ground truth of spatial stage distributions. The dataset employs an adapted 17-class BBCH system that consolidates visually similar stages, excludes problematic categories, and introduces generic structural classes to address practical annotation difficulties. Additionally, the data is organised hierarchically across various plant structures, genders, and phenological stages. The annotated images offer versatility for a range of applications, including training data for computer vision models to detect phenological stages. Furthermore, the georeferenced videos facilitate the validation of automated counting algorithms. This combined approach enables plant-level detection accuracy and provides an illustrative methodology for spatial validation that users can extend to additional orchards, promoting the development and benchmarking of automated phenological monitoring systems for precision agriculture applications in kiwifruit production.

Abstract
High-throughput plant phenotyping (HTPP) enhances the throughput, resolution, and dimensionality of conventional manual phenotyping techniques. However, existing platforms face significant challenges, including high acquisition and maintenance costs, limited adaptability to field conditions, and inadequate data management capabilities. This paper introduces GREENTRIBE, an open-source, multi-sensor HTPP architecture that integrates Internet of Things sensing devices and robotics to collect, process, and manage comprehensive phenotypic and environmental data. GREENTRIBE features a multiscale sensing network, built on a sensor-independent communication protocol. An ontology-driven data management layer was designed in accordance with common standards and metadata guidelines, ensuring FAIR (Findable, Accessible, Interoperable, and Reusable) (meta)data. The architecture combines Computer Vision and Artificial Intelligence data analysis pipelines with a process-based crop model for data assimilation, allowing the quantitative traits derived from the sensing layer to be linked to contextual data (genotype, environment, and management conditions). The architecture and performance indicators are presented, demonstrating efficient data collection, processing, and management. Phenotyping is the cornerstone of GREENTRIBE, offering a valuable platform for generating data-rich, reproducible workflows, multimodal datasets, and analysis systems with high impact on Precision Agriculture, improving real-time monitoring, input application, and environmental impacts assessment towards maximized crop productivity, quality, and sustainability.