Instance segmentation is the state-of-the-art in object detection, and there are numerous applications in remote sensing data where these algorithms can produce significant results. Nevertheless, one of the main problems is that most algorithms use Red, Green, and Blue (RGB) images, whereas Satellite images often present more channels that can be crucial to improve performance. Therefore, the present work brings three contributions: (a) conversion system from ground truth polygon data into the Creating Common Object in Context (COCO) annotation format; (b) Detectron2 software source code adaptation and application on multi-channel imagery; and (c) large scene image mosaicking. We applied the procedure in a Center Pivot Irrigation System (CPIS) dataset with ground truth produced by the Brazilian National Water Agency (ANA) and Landsat-8 Operational Land Imager (OLI) imagery (7 channels with 30-m resolution). Center pivots are a modern irrigation system technique with massive growth potential in Brazil and other world areas. The round shapes with different textures, colors, and spectral behaviors make it appropriate to use Deep Learning instance segmentation. We trained the model using 512 × 512-pixel sized patches using seven different backbone structures (ResNet50- Feature Pyramid Network (FPN), Resnet50-DC5, ResNet50-C4, Resnet101-FPN, Resnet101-DC5, ResNet101-FPN, and ResNeXt101-FPN). The model evaluation used standard COCO metrics (Average Precision (AP), AP₅₀, AP₇₅, AP_small, AP_medium, and AR₁₀₀). ResNeXt101-FPN had the best results, with a 3% advantage over the second-best model (ResNet101-FPN). We also compared the ResNeXt101-FPN model in the seven-channel and RGB imagery, where the multi-channel model had a 3% advantage, demonstrating great improvement using a larger number of channels. This research is also the first with a mosaicking algorithm using instance segmentation models, where we tested in a 1536 × 1536-pixel image using a non-max suppression sorted by area method. The proposed methodology is innovative and suitable for many other remote sensing problems and medical imagery that often present more channels.

Panoptic segmentation combines instance and semantic predictions, allowing the detection of countable objects and different backgrounds simultaneously. Effectively approaching panoptic segmentation in remotely sensed data is very promising since it provides a complete classification, especially in areas with many elements as the urban setting. However, some difficulties have prevented the growth of this task: (a) it is very laborious to label large images with many classes, (b) there is no software for generating DL samples in the panoptic segmentation format, (c) remote sensing images are often very large requiring methods for selecting and generating samples, and (d) most available software is not friendly to remote sensing data formats (e.g., TIFF). Thus, this study aims to increase the operability of panoptic segmentation in remote sensing by providing: (1) a pipeline for generating panoptic segmentation datasets, (2) software to create deep learning samples in the Common Objects in Context (COCO) annotation format automatically, (3) a novel dataset, (4) leverage the Detectron2 software for compatibility with remote sensing data, and (5) evaluate this task on the urban setting. The proposed pipeline considers three inputs (original image, semantic image, and panoptic image), and our software uses these inputs alongside point shapefiles to automatically generate samples in the COCO annotation format. We generated 3400 samples with 512 × 512 pixel dimensions and evaluated the dataset using Panoptic-FPN. Besides, the metric analysis considered semantic, instance, and panoptic metrics, obtaining 93.865 mean intersection over union (mIoU), 47.691 Average (AP) Precision, and 64.979 Panoptic Quality (PQ). Our study presents the first effective pipeline for generating panoptic segmentation data for remote sensing targets.

Recognizing insect pests using images is an important and challenging research issue. A correct species classification will help choosing a more proper mitigation strategy regarding crop management, but designing an automated solution is also difficult due to the high similarity between species at similar maturity stages. This research proposes a solution to this problem using a few-shot learning approach. First, a novel insect data set based on curated images from IP102 is presented. The IP-FSL data set is composed of 97 classes of adult insect images, and 45 classes of early stages, totalling 6817 images. Second, a few-shot prototypical network is proposed based on a comparison with other state-of-art models and further divergence analysis. Experiments were conducted separating the adult classes and the early stages into different groups. The best results achieved an accuracy of 86.33% for the adults, and 87.91% for early stages, both using a Kullback–Leibler divergence measure. These results are promising regarding a crop scenario where the more significant pests are few and it is important to detect them at earlier stages. Further research directions would be in evaluating a similar approach in particular crop ecosystems, and testing cross-domains.

Vehicle classification is a hot computer vision topic, with studies ranging from ground-view to top-view imagery. Top-view images allow understanding city patterns, traffic management, among others. However, there are some difficulties for pixel-wise classification: most vehicle classification studies use object detection methods, and most publicly available datasets are designed for this task, creating instance segmentation datasets is laborious, and traditional instance segmentation methods underperform on this task since the objects are small. Thus, the present research objectives are as follows: first, propose a novel semisupervised iterative learning approach using the geographic information system software, second, propose a box-free instance segmentation approach, and third, provide a city-scale vehicle dataset. The iterative learning procedure considered the following: first, labeling a few vehicles from the entire scene, second, choosing training samples near those areas, third, training the deep learning model (U-net with efficient-net-B7 backbone), fourth, classifying the whole scene, fifth, converting the predictions into shapefile, sixth, correcting areas with wrong predictions, seventh, including them in the training data, eighth repeating until results are satisfactory. We considered vehicle interior and borders to separate instances using a semantic segmentation model. When removing the borders, the vehicle interior becomes isolated, allowing for unique object identification. Our procedure is very efficient and accurate for generating data iteratively, which resulted in 122 567 mapped vehicles. Metrics-wise, our method presented higher intersection over union when compared to box-based methods (82% against 72%), and per-object metrics surpassed 90% for precision and recall.

This letter proposes a novel method to obtain panoptic predictions by extending the semantic segmentation task with a few non-learning image processing steps, presenting the following benefits: 1) annotations do not require a specific format [e.g., common objects in context (COCO)]; 2) fewer parameters (e.g., single loss function and no need for object detection parameters); and 3) a more straightforward sliding windows implementation for large image classification (still unexplored for panoptic segmentation). Semantic segmentation models do not individualize touching objects, as their predictions can merge; i.e., a single polygon represents many targets. Our method overcomes this problem by isolating the objects using borders on the polygons that may merge. The data preparation requires generating a one-pixel border, and for unique object identification, we create a list with the isolated polygons, attribute a different value to each one, and use the expanding border (EB) algorithm for those with borders. Although any semantic segmentation model applies, we used the U-Net with three backbones (EfficientNet-B5, EfficientNet-B3, and EfficientNet-B0). The results show that the following hold: 1) the EfficientNet-B5 had the best results with 70% mean intersection over union (mIoU); 2) the EB algorithm presented better results for better models; 3) the panoptic metrics show a high capability of identifying things and stuff with 65 panoptic quality (PQ); and 4) the sliding windows on a $2560\times 2560$ -pixel area has shown promising results, in which the ratio of merged objects by correct predictions was lower than 1% for all classes.