Table grapes are a crop with high nutritional value that need to be monitored often to achieve high yield and quality. Non-destructive methods, such as satellite and proximal sensing, are widely used to estimate crop yield and quality characteristics, and spectral vegetation indices (SVIs) are commonly used to present site specific information. The aim of this study was the assessment of SVIs derived from satellite and proximal sensing at different growth stages of table grapes from veraison to harvest. The study took place in a commercial table grape vineyard (Vitis vinifera cv. Thompson Seedless) during three successive cultivation years (2015-2017). The Normalized Difference Vegetation Index (NDVI) and Green Normalized Difference Vegetation Index (GNDVI) were calculated by employing satellite imagery (Landsat 8) and proximal sensing (Crop Circle ACS 470) to assess the yield and quality characteristics of table grapes. The SVIs exhibited different degrees of correlations with different measurement dates and sensing methods. Satellite-based GNDVI at harvest presented higher correlations with crop quality characteristics (r = 0.522 for berry diameter, r = 0.537 for pH, r = 0.629 for berry deformation) compared with NDVI. Proximal-based GNDVI at the middle of veraison presented higher correlations compared with NDVI (r = −0.682 for berry diameter, r = −0.565 for berry deformation). Proximal sensing proved to be more accurate in terms of table grape yield and quality characteristics compared to satellite sensing.

No abstract

No abstract

No abstract

Broccoli is an example of a high-value crop that requires delicate handling throughout the growing season and during its post-harvesting treatment. As broccoli heads can be easily damaged, they are still harvested by hand. Moreover, human scouting is required to initially identify the field segments where several broccoli plants have reached the desired maturity level, such that they can be harvested while they are in the optimal condition. The aim of this study was to automate this process using state-of-the-art Object Detection architectures trained on georeferenced orthomosaic-derived RGB images captured from low-altitude UAV flights, and to assess their capacity to effectively detect and classify broccoli heads based on their maturity level. The results revealed that the object detection approach for automated maturity classification achieved comparable results to physical scouting overall, especially for the two best-performing architectures, namely Faster R-CNN and CenterNet. Their respective performances were consistently over 80% mAP@50 and 70% mAP@75 when using three levels of maturity, and even higher when simplifying the use case into a two-class problem, exceeding 91% and 83%, respectively. At the same time, geometrical transformations for data augmentations reported improvements, while colour distortions were counterproductive. The best-performing architecture and the trained model could be tested as a prototype in real-time UAV detections in order to assist in on-field broccoli maturity detection.