Journal of Computer Science

Optical imaging and sensing in autonomous vehicles

Description

Advances in communication, controls and embedded systems now pave the way for autonomous vehicles, which use sensors and software to control, navigate and drive the vehicle without any human intervention, to a predetermined destination. Autonomous vehicles help in increasing car utilization by 5-75%, thus reducing CO₂ emissions, helping to save fuel and time, reducing congestion, parking utilization, and even preventing and reducing severe accidents.

Autonomous vehicles with optical imaging and sensing technologies incorporate safety systems such as lane departure warning systems, sign detection systems, parking assistance, collision avoidance, and accident recorders. Radars, Lidars, sensors, and cameras are the main components in the development of self-driving cars. Radars lag in the detection of the exact size and shape of an object, whereas lidar, though more accurate than radar, its detection distance is critical. Lidars can help in generating 3D point maps around the vehicle. These components provide the necessary information about the environment around the vehicle in real-time. 

Optical sensors and image processing systems are indispensable for modern driver assistance systems and autonomous driving. So, these vehicles utilize vast amounts of data from image-recognition systems, along with machine learning and neural networks, to build systems that can drive autonomously. As multispectral imaging provides more information, the processing time is a vital problem, for making quick decisions. Almost all cameras rely on ambient light, which varies widely with the weather, time, and vehicle condition. Therefore developers need to work on developing low-light cameras. Each type of sensor has its limitations, whether it be glare that distorts video, radar's poor vision abilities, ultrasonics’ distance challenges, or lidar's inability to cope with poor weather. For the autonomous vehicle to be roadworthy, its perception must be accurate enough to enable the classification of any object at a variety of distances.

This special issue aims to present the recent advances in optical imaging and sensing in autonomous vehicles. It is an opportunity to gather researchers in developing fundamental principles to discuss and share original research works and practical experiences.

Scope of the Special Issue:

The scope includes but is not limited to:

• Optical fibres for imaging and sensing
• Advances in optical sensing techniques
• Quantum imaging and Computational imaging
• Deep learning for optical imaging, sensing and devices
• Optical signal processing for imaging and sensing
• Challenges of sensors’ data dissemination in autonomous vehicles
• Simulation techniques for autonomous driving
• State-of-the-art sensors applied to autonomous driving
• Algorithms for sensor-based object detection and/or tracking in autonomous vehicles
• AI and deep learning for self-driving cars
• Big data and data analysis in autonomous vehicles
• Vehicle localization and autonomous navigation
• Camera Technologies: Low-light cameras, Monochrome cameras
• Advanced driver assistance systems (ADAS)
• Sensor fusion techniques
• Traffic and flow optimization techniques
• Vehicles and infrastructure cooperation
• Risk-based maneuver selection
• Human vehicle interaction
• Uncertainty modelling
• Dynamic modelling
• Decision making

Guest Editors

Important Dates