Answers are grounded in this paper and cite their sources.
Accurate and timely monitoring of strawberry phenology is required for harvest planning, labor allocation, and related management decisions, yet routine data collection at a commercial scale remains labor-intensive. A sprayer-mounted georeferenced imaging system, termed the AgriBerry Vision (ABV), was developed to support high-throughput image acquisition during routine strawberry field operations. Sequential RGB images were recorded during spraying and were linked with GNSS coordinates for later offline analysis. The present study focused on field image acquisition and workflow demonstrations. Representative multistage strawberry detection was performed on the collected imagery, and class-specific relative spatial distribution maps were generated from image-level detection counts assigned to image coordinates. Clear within-trial spatial heterogeneity was observed in the resulting maps. Green and white fruit generally exhibited broader spatial distributions, whereas pink fruit was observed over more limited portions of the mapped transects. Several trials also showed substantial representation of red fruit, which was plausibly associated with crop developmental status and harvest timing. These results indicate that georeferenced image acquisition can be integrated into routine sprayer operation and can provide usable inputs for offline strawberry phenology analysis and relative spatial mapping. The present work should be interpreted as a workflow demonstration rather than a fully calibrated precision georeferencing system. Code and data are available at: https://github.com/Sycamorers/AgriBerry-Vision .
No takes yet. Share an insight, caveat, or question.
Huang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: