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.

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.

Registration activities combine data from different sources in order to attain higher accuracy and derive more information than available from one source. The increasing availability of a wide variety of sensors capable of capturing high quality and complementary data requires parallel efforts for developing accurate and robust registration techniques. Currently, photogrammetric and LIDAR systems are being incorporated in a wide spectrum of mapping applications such as city modeling, surface reconstruction, and object recognition. Photogrammetric processing of overlapping imagery provides accurate information regarding object space break-lines in addition to an explicit semantic description of the photographed objects. On the other hand, LIDAR systems supply dense geometric surface information in the form of non-selective points. Considering the properties of photogrammetric and LIDAR data, it is clear that the two technologies provide complementary information. However, the synergic characteristics of both systems can be fully utilized only after successful registration of the photogrammetric and LIDAR data relative to a common reference frame. The registration methodology has to deal with three issues: registration primitives, transformation function, and similarity measure. This paper presents two methodologies for utilizing straight-line features derived from both datasets as the registration primitives. The first methodology directly incorporates the LIDAR lines as control information in the photogrammetric triangulation. The second methodology starts by generating a photogrammetric model relative to an arbitrary datum. Then, LIDAR features are used as control information for the absolute orientation of the photogrammetric model. In addition to the registration methodologies, the paper presents a comparative analysis between two approaches for extracting linear features from raw and processed/interpolated LIDAR data. Also, a comparative analysis between metric analog and amateur digital cameras within the registration process will be presented. The performance analysis is based on the quality of fit of the final alignment between the LIDAR and photogrammetric models.

Several photogrammetric and geographic information system applications such as surface matching, object recognition, city modeling, environmental monitoring, and change detection deal with multiple versions of the same surface that have been derived from different sources and/or at different times. Surface registration is a necessary procedure prior to the manipulation of these 3D datasets. This need is also applicable in the field of medical imaging, where imaging modalities such as magnetic resonance imaging (MRI) can provide temporal 3D imagery for monitoring disease progression. This paper will present a general automated surface registration procedure that can establish correspondences between conjugate surface elements. Experimental results using light detection and ranging (LIDAR) and MRI data will verify the feasibility, robustness, and accuracy of this approach.