Corn is an important part of the Mexican diet. The crop requires constant monitoring to ensure production. For this, plant density is often used as an indicator of crop yield, since knowing the number of plants helps growers to manage and control their plots. In this context, it is necessary to detect and count corn plants. Therefore, a database of aerial RGB images of a corn crop in weedy conditions was created to implement and evaluate deep learning algorithms. Ten flight missions were conducted, six with a ground sampling distance (GSD) of 0.33 cm/pixel at vegetative stages from V3 to V7 and four with a GSD of 1.00 cm/pixel for vegetative stages V6, V7 and V8. The detectors compared were YOLOv4, YOLOv4-tiny, YOLOv4-tiny-3l, and YOLOv5 versions s, m and l. Each detector was evaluated at intersection over union (IoU) thresholds of 0.25, 0.50 and 0.75 at confidence intervals of 0.05. A strong F1-Score penalty was observed at the IoU threshold of 0.75 and there was a 4.92% increase in all models for an IoU threshold of 0.25 compared to 0.50. For confidence levels above 0.35, YOLOv4 shows greater robustness in detection compared to the other models. Considering the mode of 0.3 for the confidence level that maximizes the F1-Score metric and the IoU threshold of 0.25 in all models, YOLOv5-s obtained a mAP of 73.1% with a coefficient of determination ($R^2$) of 0.78 and a relative mean square error (rRMSE) of 42% in the plant count, followed by YOLOv4 with a mAP of 72.0%, $R^2$ of 0.81 and rRMSE of 39.5%.

Within the context of precision agriculture, goods insurance, public subsidies, fire damage assessment, etc., accurate knowledge about the plant population in crops represents valuable information. In this regard, the use of Unmanned Aerial Vehicles (UAVs) has proliferated as an alternative to traditional plant counting methods, which are laborious, time demanding and prone to human error. Hence, a methodology for the automated detection, geolocation and counting of crop trees in intensive cultivation orchards from high resolution multispectral images, acquired by UAV-based aerial imaging, is proposed. After image acquisition, the captures are processed by means of photogrammetry to yield a 3D point cloud-based representation of the study plot. To exploit the elevation information contained in it and eventually identify the plants, the cloud is deterministically interpolated, and subsequently transformed into a greyscale image. This image is processed, by using mathematical morphology techniques, in such a way that the absolute height of the trees with respect to their local surroundings is exploited to segment the tree pixel-regions, by global statistical thresholding binarization. This approach makes the segmentation process robust against surfaces with elevation variations of any magnitude, or to possible distracting artefacts with heights lower than expected. Finally, the segmented image is analysed by means of an ad-hoc moment representation-based algorithm to estimate the location of the trees. The methodology was tested in an intensive olive orchard of 17.5 ha, with a population of 3919 trees. Because of the plot’s plant density and tree spacing pattern, typical of intensive plantations, many occurrences of intra-row tree aggregations were observed, increasing the complexity of the scenario under study. Notwithstanding, it was achieved a precision of 99.92%, a sensibility of 99.67% and an F-score of 99.75%, thus correctly identifying and geolocating 3906 plants. The generated 3D point cloud reported root-mean square errors (RMSE) in the X, Y and Z directions of 0.73 m, 0.39 m and 1.20 m, respectively. These results support the viability and robustness of this methodology as a phenotyping solution for the automated plant counting and geolocation in olive orchards.

Apples are among the most important agricultural products worldwide. Ensuring apple quality with minimal effort is crucial for both large-scale and local producers. In Mexico, the manual detection of damaged apples has led to inconsistencies in product quality, a problem that can be addressed by integrating vision systems with machine learning algorithms. The YOLO (You Only Look Once) neural network has significantly improved fruit detection through image processing and has automated several related tasks. However, training and deploying YOLO models typically requires substantial computational resources, making it essential to develop lightweight and cost-effective detection systems, especially for edge computing systems. This paper presents a mechatronic system designed to detect apple varieties and potential damage in apples (Malus domestica) within the visible spectrum. The cultivated apple varieties considered were Gala, Golden, Granny Smith, and Red Delicious. Our contribution lies in developing a lightweight neural network architecture optimized specifically for embedded systems. The proposed architecture was compared against YOLOv3-Tiny, YOLOv4-Tiny, and YOLOv5-s. Our optimized model achieved a high accuracy and sensitivity (94–99%) and was successfully implemented on a Jetson Xavier NX board, where it reached a processing speed of 37 FPS.

Agave plants (Agave tequilana Weber) are an indispensable element in the tequila production chain. Traditionally, plantation monitoring has been done manually; however, having accurate information on agave inventories is crucial for planning and estimating production volume. In this context, it was proposed that deep learning algorithms can achieve high detection rates of agave plants, improving the management and control of plantations. For this purpose, YOLOv4 and YOLOv4-tiny convolutional algorithms were implemented and evaluated using high-resolution RGB aerial images captured by a remotely piloted aircraft system for the determination of agave plant density. Three flight plans were planned and carried out, with ground sampling distances of 1.10, 1.64, and 2.19 cm pixel-1, respectively. The database was created, and the algorithms were evaluated for a confidence level of 0.25 and an intersection threshold over the junction of 0.50. The results showed an average mean accuracy of 0.99 for both algorithms and an F1 score of 0.95 for YOLOv4 and 0.96 for YOLOv4-tiny. Furthermore, a high detection rate (Rc) of 99 % and precision values (Pr) between 90 and 92 % were obtained. A decrease in the performance of the algorithms was observed when detecting agave tillers in images with a spatial resolution of 2.19 cm pixel-1. The implemented YOLO convolutional algorithms proved to be highly robust and able to generalize agave plant characteristics at different phenological stages, allowing accurate detections. In addition, the coordinates of the detected plants were used to estimate the distance between them, with a maximum error of 20 cm.

Actualmente, en puntos de venta y en empresas agroindustriales de México, la clasificación de manzanas (Malus domestica) la realizan personas de forma manual, lo que genera deficiencias en la calidad del producto. Estos problemas se pueden reducir con la implementación de equipos de visión en sitio equipados con algoritmos de aprendizaje automático. En este estudio se analizaron varias arquitecturas de red neuronal convolucional (CNN) y se seleccionó una que permite clasificar manzanas en sanas y dañadas en el proceso en postcosecha. Las variedades utilizadas fueron Red Delicious, Granny Smith, Golden Delicious y Gala. Se comparó la exactitud de las CNN LeNet5 y VGG16. Se realizó una serie de tratamientos (combinación de red con hiperparámetros) que se utilizaron para la clasificación del objeto de estudio. Al probarse cada tratamiento se midió su rendimiento. Al finalizar, el tratamiento con mejor rendimiento fue LeNet5 entrenada desde cero con el optimizador RMSProp, que obtuvo una exactitud del 97 %.

The fruit of black sapote (Diospyros nigra (J.F.Gmel.) Perr.) has been consumed in Mexico and Central America since pre-Hispanic times. They contain antioxidant compounds, minerals, and vitamins, making them valuable for nutraceutical and agro-industrial applications. Despite this, there is no scientific information on the physical and mechanical characterization of the fruit that helps in the design and development of protocols and equipment for storage, handling, processing, and added value for a better use of the fruit. In the present work, the physical and mechanical qualities of physiologically ripe black sapote fruit from the State of Hidalgo, Mexico, were characterized after one day of storage after harvest under environmental storage conditions. Models were also determined for the prediction of the mass of the fruit using their dimensional characteristics, finding that the quadratic models based on the volume of the ellipsoid (R2 = 0.8919) and width of the fruit (R2 = 0.8252) were the most appropriate to predict their mass. Likewise, a maximum compressive load force of 869.99 N and an apparent modulus of elasticity of 0.0.088 MPa were determined.