Brazil is the largest producer of oranges in the world and the automatic detection of fruits has been a challenging task in the context of remote sensing, due to variations in fruit appearance, changes in lighting and occlusions of foliage and neighboring fruits. In this sense, this paper focus on the detection of oranges in multispectral images, with different spectral bands and exposures, using a convolutional neural network (CNN) known as YOU ONLY LOOK ONCE (YOLO). The results indicate that, after 300 epochs, the model demonstrated an accuracy of 81.5% and an approximate recovery rate of 85%. Shutter speeds 1/640s and 1/250s are not suitable for detection due to low light and overexposure, respectively. Intermediate values may be more suitable for identifying a larger number of fruits.

Huanglongbing (HLB) is a bacterial disease transmitted by different vectors of sap-sucking insects. It affects all crops of citrus trees, decreasing the values of those fruits in the market and eventually the decay of orchards. In Brazil, the world's leading orange producer, citriculture faces severe issues with HLB and substantial economic loss. Technical means of scanning the orchards with high-throughput becomes essential for the sustainability of this industry. In this study, we propose to investigate an operational strategy consisting of scanning large portions of foliage (the canopy of one tree or more) in which there can few early foliage symptoms. It is proposed to investigate deep learning tools to solve this complex binary classification problem. The study is based on a dataset comprising 1,297 terrestrial multispectral (14 channels) images captured at high spatial resolution in a commercial orange orchard in Brazil. It is proposed to adapt and retrain standard neural network architectures, namely ResNets18 and ResNets34, to process such images. Our analysis reveals promising results, with both models demonstrating convergence and achieving stable performance. Notably, ResNet18 outperformed ResNet34, achieving an accuracy of 76.45% compared to 66.79% from ResNet34. These findings suggest that deep neural network methods can effectively manage non-radiometrically calibrated data and accurately distinguish images with HLB symptoms from healthy plants . However, with reduced datasets and limited possibilities for transfer learning and fine-tuning, it seems that only reasonable sized networks can be trained. Thus, more advanced state-of-the-art tools of the are still challenging to deploy for agricultural multi- or hyperspectral data.