The forest constitutes an essential and irreplaceable component of life for all organisms, with its primary significance lying in its role in creating a breathable atmosphere on Earth. Forests are vital for human health and well-being and hold significant ecological and economic value for humanity. This study aims to propose a method for identifying forest stands using artificial intelligence techniques. A custom dataset was developed, comprising high-quality satellite images that capture various structures such as forests, fields, roads, buildings, and lakes. This dataset was employed to train models from the category of convolutional neural networks that operate on the principle of instance segmentation. Several models, including YOLOv8, YOLOv5 and Mask R-CNN, were tested and compared. An optimal model was selected based on parameters such as detection accuracy, total training time, and the precision of labeling detected image elements. The selected model was then evaluated using images not included in the original training dataset to simulate real-world deployment scenarios. The final accuracy of best model achieved 91.67%. This model can detect the presence of forest stands in satellite images, as well as other features such as roads, buildings etc. The proposed method offers potential benefits for forest technicians, who can integrate it with other methods to monitor forest cover effectively.

Traffic accident detection and object detection have become key areas of research due to their direct impact on safety, traffic congestion mitigation, and intelligent traffic planning. This study presents a structured analysis of classical detection methods and artificial intelligence-based techniques, highlighting their methodologies, objectives, and performance results. The study categorizes existing research into threshold-based approaches, statistical approaches, image processing, rule-based approaches, and machine learning approaches, with further emphasis on predictive modeling, graph-based approaches, and optimization approaches. Considerable emphasis is placed on identifying systems that are capable of operating under adverse weather conditions such as fog, rain, and snow. These scenarios significantly affect detection accuracy. Although several authors incorporate environmental resilience into their models, most studies still evaluate performance under ideal conditions, revealing a critical gap in research. This analysis highlights the need to develop robust detection mechanisms that can adapt to real-world variability and environmental disturbances. Findings show that AI-based methods significantly outperform classical approaches in terms of adaptability and scalability, but their dependence on training data limits their performance in adverse conditions. The study concludes with recommendations for future work to prioritize multimodal sensing, generalization across weather conditions, and integration of environmental intelligence to ensure reliable real-time detection of traffic events under all operating conditions.