In recent years, many agriculture-related problems have been evaluated with the integration of artificial intelligence techniques and remote sensing systems. Specifically, in fruit detection problems, several recent works were developed using Deep Learning (DL) methods applied in images acquired in different acquisition levels. However, the increasing use of anti-hail plastic net cover in commercial orchards highlights the importance of terrestrial remote sensing systems. Apples are one of the most highly-challenging fruits to be detected in images, mainly because of the target occlusion problem occurrence. Additionally, the introduction of high-density apple tree orchards makes the identification of single fruits a real challenge. To support farmers to detect apple fruits efficiently, this paper presents an approach based on the Adaptive Training Sample Selection (ATSS) deep learning method applied to close-range and low-cost terrestrial RGB images. The correct identification supports apple production forecasting and gives local producers a better idea of forthcoming management practices. The main advantage of the ATSS method is that only the center point of the objects is labeled, which is much more practicable and realistic than bounding-box annotations in heavily dense fruit orchards. Additionally, we evaluated other object detection methods such as RetinaNet, Libra Regions with Convolutional Neural Network (R-CNN), Cascade R-CNN, Faster R-CNN, Feature Selective Anchor-Free (FSAF), and High-Resolution Network (HRNet). The study area is a highly-dense apple orchard consisting of Fuji Suprema apple fruits (Malus domestica Borkh) located in a smallholder farm in the state of Santa Catarina (southern Brazil). A total of 398 terrestrial images were taken nearly perpendicularly in front of the trees by a professional camera, assuring both a good vertical coverage of the apple trees in terms of heights and overlapping between picture frames. After, the high-resolution RGB images were divided into several patches for helping the detection of small and/or occluded apples. A total of 3119, 840, and 2010 patches were used for training, validation, and testing, respectively. Moreover, the proposed method’s generalization capability was assessed by applying simulated image corruptions to the test set images with different severity levels, including noise, blurs, weather, and digital processing. Experiments were also conducted by varying the bounding box size (80, 100, 120, 140, 160, and 180 pixels) in the image original for the proposed approach. Our results showed that the ATSS-based method slightly outperformed all other deep learning methods, between 2.4% and 0.3%. Also, we verified that the best result was obtained with a bounding box size of 160 × 160 pixels. The proposed method was robust regarding most of the corruption, except for snow, frost, and fog weather conditions. Finally, a benchmark of the reported dataset is also generated and publicly available.

Brazil is one of the three largest beer producers in the world. Four basic ingredients are needed as raw material for the production of beer: water, malt, yeast, and hops (Humulus lupulus L.). Until recently, almost all of the hops in Brazil were imported from other countries. However, in the last decade, hop cultivation in Brazil has emerged due to the increase in the number of new craft breweries, which have demanded diversified raw material for the production of various types of beer. Hops is considered a short-day, temperate species, so the major challenge for the development of hop cultivation in Brazil, with high-yield capacity and with local typicity of bitterness and aroma, is the adaptation of cultivars to the photoperiod conditions in subtropical regions. This review addresses the history of hop cultivation in Brazil and characterizes the main climatic elements of three emerging subtropical growing regions located at different latitudes, such as air temperature, photoperiod, solar radiation, and water availability, to provide support for the development of new technologies for hop cultivation, including supplemental lighting, irrigation, and mulching.

In strawberry production, the combination of a high productive performance and fruits with desirable physicochemical characteristics requires the use of plants with a good quality and high initial vigor. This study aimed to evaluate the effect of plants with different crown diameters on the productive performance and fruit quality of strawberry plants of the cultivar ‘Pircinque’ (Short Day). The study was conducted in two evaluation cycles (2016/2017 and 2017/2018). The experimental design was divided into randomized blocks, with four repetitions, and plots consisting of 20 plants. This study evaluated the crown diameters of plants of 5, 7, 9, 11, 13, 15, 17, and 19 mm. The productivity and number of fruit values increased significantly by 57% with larger caliber plants, which also provided precocity of productivity. The use of more vigorous plants also favored the production of fruits with higher soluble solids/titratable acidity ratios (+28%) and with epidermis coloration closer to intense red (−4.3%). For the cultivar ‘Pircinque’, plant crown diameters between 15 and 17 mm are the most favorable because they condition the best productive performances in combination with precocity and a good fruit quality.

In the search for more efficient production systems, many changes have occurred in the strawberry production sector. Planting density is one of the management techniques that most interferes with the quality of fruits and production aspects. This study aimed to evaluate the effect of different planting densities on the photosynthetic characteristics, fruit quality, and production of the strawberry cultivar Pircinque. The study was conducted in the 2018/2019 and 2019/2020 harvests in Lages, Santa Catarina, Brazil. The treatments consisted of plant spacing of 5, 10, 15, 20, 25, and 30 cm. The experimental design was in randomized blocks, with four blocks and plots of 20 plants. Plant spacing interfered with fruit quality, photosynthetic efficiency, production, productivity, and economic return. Due to the fruits of Pircinque having a higher quality than other cultivars, the planting spacing between 5 and 15 cm allows meeting the fruit’s main production and quality requirements. However, it is up to the producer to adapt the management if opting for higher planting densities, which allow for a greater economic viability of the business.

A cultura da Physalis peruviana, família das solanáceas, ainda é pouco explorada no Brasil, mas é uma nova opção de diversificação para pequenos produtores, com boas perspectivas para o mercado nacional e internacional, mais conhecida como camapum e joá-de-capote, podendo ser confundida com outras espécies. Essa frutífera pode chegar até dois metros de altura quando se utiliza um sistema de condução adequado, influenciando no desenvolvimento da planta e na qualidade do fruto produzido. O objetivo do trabalho foi avaliar a influência de quatro sistemas de condução de plantas de physalis na produção de frutos, em dois ciclos de produção, durante os anos de 2006-2007 e 2007-2008, em Lages-SC. Avaliaram-se os sistemas de condução em "V", em "X", espaldeira simples e livre. O delineamento experimental adotado foi de blocos ao acaso, com quatro repetições, sendo cada unidade experimental constituída de dez plantas. Observou-se que, nos dois ciclos consecutivos, o sistema em "X" apresentou os melhores resultados na maioria das características físico-químicas analisadas, quando comparado com os outros sistemas de condução. Conclui-se que a physalis se adapta bem à região do planalto catarinense e que, independentemente do sistema de condução utilizado, a planta tutorada sob sistema de condução apresentou frutos de maior peso, diâmetro e melhor qualidade, gerando frutos com maior valor comercial, quando comparados com a testemunha, sem condução e sem tutoramento.

O objetivo deste trabalho foi avaliar o efeito de diferentes intensidades de raleio de cachos de uvas (Vitis vinifera L.), em vinhedos de altitude, sobre a evolução dos compostos fenólicos durante a maturação da uva. O experimento foi conduzido em São Joaquim, SC, a uma altitude média de 1.230 m, em videiras da cv.Syrah, enxertadas sobre 'Paulsen 1103', conduzidas em espaldeira, em duplo cordão esporonado, espaçadas em 3x1,2 m, com cobertura antigranizo. Os tratamentos de raleio foram definidos de modo a se ter redução da produtividade em 13,3, 26,6 e 40% em relação à produtividade do tratamento controle sem raleio, estimada em 15 Mg ha-1. Os tratamentos foram ajustados quando 50% das bagas encontravam-se em "véraison". Odelineamento foi o de blocos ao acaso, com quatro repetições e 40 plantas por tratamento. As avaliações foram feitas nas safras 2005/2006 e 2006/2007. Avaliou-se a evolução dos compostos fenólicos durante as oito semanas antecedentes à colheita. O raleio de cachos aumentou o conteúdo de antocianinas quando a produtividade estimada foi de 12 Mg ha-1, e melhorou a composição fenólica das bagas, atributos esses favoráveis à produção de vinhos tintos finos de qualidade.