The intelligent transportation system (ITS), which commonly integrates advanced sensing, communication, and information technologies, has emerged as a critical field for promoting the efficiency, effectiveness, and safety of transportation systems. It is essentially based on the increasing demands of transportation development. Several different types of sensors have been installed to collect continuously generated traffic information for enhancing ITS. It is well known that we are more used to visual information than to other types of perceptual information in practice. Due to the attractive price-to-performance ratio for imaging sensors, computer vision techniques have become increasingly important for ITS, especially for different autonomous transport devices in the on-going transportation revolution. It is able to provide an accurate and timely traffic situation by developing specific computer vision techniques from the acquired visual information from the imaging sensors. Taking full advantage of the visual information would enable a human or machine to better understand complex transportation environments.

Although significant progress has been made in computer vision techniques in ITS, researchers from both academia and industry are still facing several major challenges that hinder further advances in ITS development: how to improve the visual perception for ITS in adverse weather conditions; how to take full advantage of multi-sensor perceptual data in ITS; how to develop the ITS-specific computer vision techniques through advanced artificial intelligence techniques; how to develop a computer vision-based traffic monitoring system and enhance the traffic situational awareness and safety; and finally, how to guarantee the effectiveness of different autonomous transport devices using computer vision techniques. Previous ITS mainly focuses on road transport, but this Special Issue also considers the applications of ITS in water and air transport, etc.

This Special Issue mainly focuses on recent computer vision techniques in ITS, which addresses the original theoretical development and practical applications. We especially welcome high-quality original research and review articles, which cover a broad range of topics related to mathematical, physical and computational methods of computer vision and their practical applications in ITS.

Potential topics include but are not limited to the following:

• Image quality improvement for ITS in adverse weather conditions (e.g., video/image stabilisation, dehazing/defogging, desnowing, deraining, low-light enhancement, etc.)
• Multi-sensor perceptual data (e.g., radar, visible, infrared imagery, etc.) acquisition, fusion, and analysis in ITS
• Deep learning and reinforcement learning for promoting specific computer vision techniques in ITS
• Computer vision techniques for traffic flow computation (e.g., spatio-temporal traffic flow modelling, analysis, prediction and visualization, etc.)
• Computer vision techniques for enhancing traffic situational awareness and safety
• Computer vision-based traffic monitoring system (e.g., pedestrian/car/ship/aircraft detection and tracking, abnormal behaviour detection, driver monitoring, etc.)
• Vision-based integrated techniques for intelligent collision avoidance systems
• Vision-based positioning and navigation for autonomous transport devices (e.g., self-driving cars, autonomous surface ships, unmanned aircrafts, etc.)