In the field of remote sensing, semantic segmentation of Unmanned Aerial Vehicle (UAV) imagery is crucial for tasks such as land resource management, urban planning, precision agriculture, and economic assessment. Traditional methods use Convolutional Neural Networks (CNNs) for hierarchical feature extraction but are limited by their local receptive fields, restricting comprehensive contextual understanding. To overcome these limitations, we propose a combination of transformer and attention mechanisms to improve object classification, leveraging their superior information modeling capabilities to enhance scene understanding. In this paper, we present SwinFAN (Swin-based Focal Axial attention Network), a U-Net framework featuring a Swin transformer as encoder, equipped with a novel decoder that introduces two new components for enhanced semantic segmentation of urban remote sensing images. The first proposed component is a Guided Focal-Axial (GFA) attention module which combines local and global contextual information, enhancing the model's ability to discern intricate details and complex structures. The second component is an innovative Attention-based Feature Refinement Head (AFRH) designed to improve the precision and clarity of segmentation outputs through self-attention and convolutional techniques. Comprehensive experiments demonstrate that the accuracy of our proposed architecture significantly outperforms state-of-the-art models. More specifically, our method achieves mIoU (mean Intersection over Union) improvements of 1.9% on UAVid, 3.6% on Potsdam, 1.9% on Vaihingen, and 0.8% on LoveDA.

Miniature self-driving cars are intended to facilitate the research and development in the domain of autonomous vehicles. Algorithms developed for the tasks of perception, navigation, and control on such platforms enable fast implementation and testing in scenarios similar to the real world. In this paper, we present a novel methodology for developing the assistance system for a 1/10 scale car, in which we use a simulated GPS to position the vehicle and to navigate on the test track. We propose a method for lane detection and tracking that is robust and accounts for the cases when one or both lines of the lane are missing or not seen in the image. We also present a new solution for detecting road traffic signs. In addition, we have implemented an application for map visualization, that enables us to test the correctness of our algorithms. Our miniature vehicle is capable of successfully navigating from a start point to a goal, while taking into account the lanes, intersections, traffic signs, and can perform lateral parking.

In an autonomous driving system, drift can affect the sensor's position, introducing errors in the extrinsic calibration. For this reason, we have developed a method which continuously monitors two sensors, camera, and LIDAR with 16 beams, and adjusts the value of their cross-calibration. Our algorithm, starting from correct values of the extrinsic cross-calibration parameters, can detect small sensor drift during vehicle driving, by overlapping the edges from the LIDAR over the edges from the image. The novelty of our method is that in order to obtain edges, we create a range image and filter the data from the 3D point cloud, and we use distance transform on 2D images to find edges. Another improvement we bring is applying motion correction on laser scanner data to remove distortions that appear during vehicle motion. An optimization problem on the 6 calibration parameters is defined, from which we are able to obtain the best value of the cross-calibration, and readjust it automatically. Our system performs successfully in real time, in a wide variety of scenarios, and is not affected by the speed of the car.

Large and high-quality training datasets are of critical importance for deep learning. In the context of the sematic segmentation challenge for UAV aerial images, we propose a strategy for data augmentation that can significantly reduce the effort of manually annotating a large number of images. The result is a set of semantic, depth and RGB images that can be used to improve the performance of neural networks. The main focus of the method is the generation of semantic images, with depth and texture images also being generated through the process. The proposed method for semantic image generation relies on a 3D semantic mesh representation of the real-world environment. First, we propagate the existing semantic information from a reduced set of manually labeled images into the mesh representation. To deal with errors in the manually labeled images, we propose a specific weighted voting mechanism for the propagation process. Second, we use the semantic mesh to create new images. Both steps use the perspective projection mechanism and the Depth Buffer algorithm. The images can be generated using different camera orientations, allowing novel view perspectives. Our approach is conceptually general and can be used to improve various existing datasets. Experiments with existing datasets (UAVid and WildUAV), augmented with the proposed method, are performed on HRNet. An overall performance improvement of the inference results by up to 5.5% (mIoU) is obtained. The augmented datasets are publicly available on GitHub.

This work describes the Forest Inspection dataset, a synthetic aerial image collection designed for semantic segmentation of forest environments with an emphasis on UAV-based forest inspection. The dataset consists of high-resolution RGB images paired with dense pixel-level semantic labels covering 11 classes, including deciduous trees, coniferous trees, fallen trees, ground vegetation, dirt ground, rocks, sky, buildings, fences, and vehicles. Images were generated in AirSim using a photorealistic virtual forest environment and captured with simulated UAV flights at three altitudes (30 m, 50 m, 80 m) and three camera pitch angles (0°, 60°, 90°) to reproduce diverse observation conditions, under two weather settings: sunny and overcast. Each data sample includes the corresponding UAV pose metadata for spatial context. The dataset is provided in standard image and annotation formats, accompanied by a description of the scene configuration and acquisition parameters. This resource is intended to support the development and evaluation of semantic segmentation models and other computer vision methods for UAV-based forest scene understanding and inspection.

Accurate building change detection in high-resolution remote sensing imagery requires models that can simultaneously capture fine-grained geometric detail and semantically meaningful temporal differences. Existing deep learning approaches predominantly rely on convolutional or transformer-based architectures with uniform tokenization and global prediction strategies, often overlooking object-level spatial structure and instance-aware alignment. In this article, we propose RADNet, a novel region-aware dual-path network for building change detection, that introduces an instance-consistent tokenizer, which leverages segmentation masks to generate structured region tokens, preserving building-level semantics. These tokens are fused through a global–local attention encoder (GLAE) that captures multiscale contextual dependencies and cross-temporal interactions. To enhance prediction fidelity, we introduce a cross-scale correspondence decoder, which aligns token-level differences via correlation maps and reconstructs dense change maps with instance-level precision. Extensive experiments on EGY-BCD, LEVIR-CD, and SYSU-CD datasets demonstrate that region-aware dual-path network outperforms state-of-the-art baselines, achieving superior boundary accuracy and region consistency, with average gains of +2.15% intersection over union and +1.71% F1.