An Overview on Computer Vision Analysis in the Airport Applications

This research serves a dual purpose: it aims to map the current landscape of knowledge in a field rich with technological challenges while simultaneously showcasing innovative techniques that demonstrate the transformative power of computer vision in airport applications. To achieve this, the study offers a thorough analysis of various object recognition and tracking methods, exploring their implications both in general contexts and specifically within airport environments. As airport operations become increasingly complex, the integration of advanced technologies such as computer vision and AI models is essential. This review examines a variety of object detection and tracking techniques, including deep learning models, traditional algorithms, and hybrid approaches, highlighting their effectiveness in addressing specific challenges to airport environments and detailing their performance under real-world conditions such as adverse weather, occlusion, low visibility, and data privacy concerns. A key insight is the superior capability of deep learning techniques, which, through multiscale feature extraction and region proposal strategies, provide enhanced detection accuracy and robustness in dynamic airport settings. In addition, emerging trends such as federated learning and hybrid sensor fusion are explored, emphasizing their potential to improve scalability and situational awareness by integrating data from various sources, including radar and optical sensors. The analysis also examines precise aircraft detection to optimize ground operations, real-time runway surveillance to ensure safe takeoffs and landings, and advanced passenger monitoring systems that improve security by identifying potential threats. These findings underscore the pivotal role of computer vision in improving operational efficiency and safety while laying the foundation for the future development of intelligent, integrated airport management systems.