The automation of classification and grading of horticultural products attending to different features comprises a major challenge in food industry. Thus, focused on the olive sector, which boasts of a huge range of cultivars, it is proposed a methodology for olive-fruit variety classification, approaching it as an image classification problem. To that purpose, 2,800 fruits belonging to seven different olive varieties were photographed. After processing these initial captures by means of image processing techniques, the resulting set of images of individual fruits were used to train, and continuedly to externally validate, the implementations of six different Convolutional Neural Networks architectures. This, in order to compute the classifiers with which perform the variety categorization of the fruits. Remarkable hit rates were obtained after testing the classifiers on the corresponding external validation sets. Thus, it was yielded a top accuracy of 95.91% when using the Inception-ResnetV2 architecture. The results suggest that the proposed methodology, once integrated into industrial conveyor belts, promises to be an advanced solution to postharvest olive-fruit processing and classification.

Fruit grading is an essential post-harvest task in the olive industry, where size-and-mass based fruit classification is especially important when processing high-quality table olives. Within this context, this research presents a new methodology aimed at supporting accurate automatic olive-fruit grading by using computer vision techniques and feature modelling. For its development, 3,600 olive-fruits from nine varieties were photographed, stochastically distributing the individuals on scene, using an ad-hoc designed imaging chamber. Then, an image analysis algorithm, based on mathematical morphology, was designed to individually segment olives and extract descriptive features to estimate their major and minor axes, and their mass. Regarding its accuracy for the individual segmentation of olive-fruits, the algorithm was proven through 117 captures containing 11,606 fruits, producing only six fruit-segmentation mistakes. Next, by linearly correlating the data obtained by image analysis and the corresponding reference measurements, models for estimating the three features were computed. Then, the models were tested on 2,700 external validation samples, giving relative errors below 0.80% and 1.05% for the estimation of the major and minor axis length for all varieties, respectively. In the case of estimating olive-fruit mass, the models provided relative errors never exceeding 1.3%. The ability of the developed algorithm to individually segment olives stochastically positioned, along with the low error rates of around 1% reported by the estimation models for the three features, makes the methodology a promising alternative to be integrated in a new generation of improved and non-invasive olive classification machines. The new developed system has been registered in the Spanish Patent and Trademark Office with the number P201930297.

In recent years, many olive orchards, which are a major crop in the Mediterranean basin, have been converted into intensive or super high-density hedgerow systems. This configuration is more efficient in terms of yield per hectare, but at the same time the water requirements are higher than in traditional grove arrangements. Moreover, irrigation regulations have a high environmental (through water use optimization) impact and influence on crop quality and yield. The mapping of (spatio-temporal) variability with conventional water stress assessment methods is impractical due to time and labor constraints, which often involve staff training. To address this problem, this work presents the development of a new low-cost device based on a thermal infrared (IR) sensor for the measurement of olive tree canopy temperature and monitoring of water status. The performance of the developed device was compared to a commercial thermal camera. Furthermore, the proposed device was evaluated in a commercially managed olive orchard, where two different irrigation treatments were established: a full irrigation treatment (FI) and a regulated deficit irrigation (RDC), aimed at covering 100% and 50% of crop evapotranspiration (ETc), respectively. Predawn leaf water potential (Ψ_PD) and stomatal conductance (g_s), two widely accepted indicators for crop water status, were regressed to the measured canopy temperature. The results were promising, reaching a coefficient of determination R² ≥ 0.80. On the other hand, the crop water stress index (CWSI) was also calculated, resulting in a coefficient of determination R² ≥ 0.79. The outcomes provided by the developed device support its suitability for fast, low-cost, and reliable estimation of an olive orchard’s water status, even suppressing the need for supervised acquisition of reference temperatures. The newly developed device can be used for water management, reducing water usage, and for overall improvements to olive orchard management.

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.

This paper presents a new methodology for the estimation of olive-fruit mass and size, characterized by its major and minor axis length, by using image analysis techniques. First, different sets of olives from the varieties Picual and Arbequina were photographed in the laboratory. An original algorithm based on mathematical morphology and statistical thresholding was developed for segmenting the acquired images. The estimation models for the three targeted features, specifically for each variety, were established by linearly correlating the information extracted from the segmentations to objective reference measurement. The performance of the models was evaluated on external validation sets, giving relative errors of 0.86% for the major axis, 0.09% for the minor axis and 0.78% for mass in the case of the Arbequina variety; analogously, relative errors of 0.03%, 0.29% and 2.39% were annotated for Picual. Additionally, global feature estimation models, applicable to both varieties, were also tried, providing comparable or even better performance than the variety-specific ones. Attending to the achieved accuracy, it can be concluded that the proposed method represents a first step in the development of a low-cost, automated and non-invasive system for olive-fruit characterization in industrial processing chains.