A dataset of aerial photographs acquired with an unmanned aerial vehicle (UAV) DJI Phantom 4 Pro is presented for monitoring a cherry tomato (Solanum lycopersicum var. cerasiforme) crop in Navolato, Mexico. Seven photogrammetric flights were carried out to assess the plant growth using a Mapir Survey 3W multispectral camera. Multispectral images with an approximate spatial resolution of 1.83 cm/px were obtained in each photogrammetric flight. These images were acquired every 15 days starting on October 15, 2021, and ending on January 23, 2022. The database contains the radiometrically calibrated images of the tomato crop divided into 2 treatments (repetitions). The dataset also includes the processed photogrammetric products (ortho-mosaics) using a binary mask to exclude the soil from the plant area. The database was originally acquired to assess plant growth, stress levels, and overall crop health. However, this multispectral imagery dataset can also have various uses, such as creating training datasets with accurate labels or classes which can then be used to develop, train, and/or validate machine learning algorithms for image classification, object detection tasks, or change detection analysis

Cherry tomato seeds were germinated in a greenhouse and transplanted outdoors on September 6, 2021. Plants were locally managed, and supported with nylon twine to maintain upright growth and prevent breakage from fruit weight. The study used two replicated treatments (T1 and T2) with organic-mineral fertilization; no stress was induced in either treatment.

DJI Phantom 4 Pro UAV was used for the photogrammetric flights. A Mapir Survey 3W multispectral camera was mounted on this UAV to obtain images in the GRN (Green, Red, Near Infrared) spectral range. The DJI GS Pro application was used to define the route (polygon), speed (14.1 m/s), flight height (40 m). The photogrammetric flight parameters were constant for all flights performed. These parameters were set according to the resolution of the multispectral camera sensor system. All photogrammetric flights were performed under nadir conditions. The Mapir Survey 3W camera operated independently of the UAV camera. Its configuration was based on UAV speed and height, resulting in longitudinal  and transverse overlaps of 92.8% and 62%, respectively, and a GSD of 1.83 cm/pixel. The dataset is restricted to the Mapir Survey 3W camera imagery.

Images were captured in RAW + JPG format and subsequently underwent radiometric calibration. This involved pre-flight acquisition of a ground target image.  Photogrammetric processing, using Mapir Camera Control software and the empirical line method, converted sensor radiation to reflectance via regression analysis against known ground target reflectance values.  The resulting 12-bit TIF images (Table 1 details flight conditions) have a radiometric resolution of 12 bits and the following channel order: Channel 1 (red), Channel 2 (green), and Channel 3 (near-infrared).  These calibrated images constitute the dataset.  Phenological stage (BBCH scale) observations are also provided. The first flight occurred 15 days post-transplantation from greenhouse to field.

Table 1.- Photogrammetric flight logs