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.

Este é um artigo publicado em acesso aberto (Open Access) sob a licença Creative Commons Attribution, que permite uso, distribuição e reprodução em qualquer meio, sem restrições desde que o trabalho original seja corretamente citado. Eficácia da arquitetura MLP em modo closed-loop para simulação de um Sistema HidrológicoEfficiency of MLP architecture on closed-loop mode for the simulation of a hydrological system ABSTRACTEstimatives of hydrological responses are needed for the watershed planning. The aim of this study was to evaluate the hydrological behavior simulation of the Upper Canoas basin using artificial neural networks Multi Layer Perceptron (MLP) method, as well as to analyze the contribution of the input variables for modeling. It were tested 12 treatments with combinations of variables such as precipitation, evapotranspiration (ET0) and discharge, as well as transformations and temporal displacements of these variables, in order to determine the variables that promoted the better performance on discharge modeling. The MLP was trained in open-loop mode using part of the observed discharges. The discharges for the whole series were simulated in closed-loop, using the discharge simulated on the previous time step as input. The learning algorithm used was the Levenberg-Marquardt. The treatment with the best performance (NS = 0.9119, RMS = 14.29 m 3 /s) employed the daily precipitation of the four rainfall stations (Urubici, Vila Canoas, Lomba Alta e Anitápolis), precipitation of the four stations with -2 days of response time, and simulated discharge from the previous day. Despite the low RMS, the modeled discharge using MLP was generally overestimated.

SPATIAL BEHAVIOR OF THE AGRONOMIC VARIABLES OF THE 'FUJI' APPLE DURING TWO YEARS IN THE PLANALTO SERRANO OF SANTA CATARINA STATEABSTRACT-The precision agriculture (AP) provide useful tool for evaluation agricultural risk in fruitculture and rational programming of its practical. The objective of this work was to evaluate spatial behavior of weight of fruits for plant (PP), number of fruits for plant (NF) and average weight of fruits for plant (PMF) in two years in the harvest of 2004 and 2005. The Fuji cultivar was selected in a commercial orchard in the city of São Joaquim -SC, Brazil. The data were imported to the Geographic Information System -GIS SPRING, where it was made a kriging to construct maps of spatial variability. In the harvest of 2005 there was a period of time with dry climate that they had influenced on the production. It had a reduction in the average values of PP and MF in relation to the previous year, but the PMF presented an addition. The geostatistics analysis made possible modeling the spatial behavior of the variables at the experimental area. The used GIS revealed satisfactory for the effected analyses.

No abstract

The Santa Catarina Southern Plateau is located in Southern Brazil and is a region that has gained considerable attention due to the rapid conversion of the typical landscape of natural grasslands and wetlands into agriculture, reforestation, pasture, and more recently, wind farms. This study’s main goal was to characterize the polarimetric attributes of the experimental quad-polarization acquisition mode of the Advanced Land Observing Satellite/Phased Array type L-band Synthetic Aperture Radar (ALOS/PALSAR-2) for mapping seven land cover classes. The polarimetric attributes were evaluated alone and combined with SENTINEL-2A using a supervised classification method based on the Support Vector Machine (SVM) algorithm. The results showed that the intensity backscattering alone reached an overall classification accuracy of 37.48% and a Kappa index of 0.26. Interestingly, the addition of polarimetric features increased to 71.35% and 0.66, respectively. It shows that the use of polarimetric decomposition features was relatively efficient in discriminating land cover classes. SENTINEL-2A data alone performed better and achieved a weighted overall accuracy and Kappa index of 85.56% and 0.82. This increase was also significant for the Z-test. However, the addition of ALOS/PALSAR-2 derived features to SENTINEL-2A slightly improved accuracy and was marginally significant at a 95% confidence level only when all features were considered. Possible implications for that performance are the accumulated precipitation prior to SAR data acquisition, which coincides with the rainy season period. The experimental quad-polarization mode of ALOS/PALSAR- 2 shall be evaluated in the near future over different seasonal conditions to confirm results. Alternatively, further studies are then suggested by focusing on additional features derived from SAR data such as texture and interferometric coherence to increase classification accuracy. These measures would be an interesting data source for monitoring specific land cover classes such as the threatened grasslands and wetlands during periods of frequent cloud coverage. Future investigations could also address multitemporal approaches employing either single or multifrequency SAR.