The aim of this course is to introduce digital image processing techniques and their applications in target detection. Countless images are generated every day from various types of cameras, such as regular RGB cameras, LIDAR scanners, IR cameras, multi/hyperspectral scanners, depth cameras and more. The cameras can be mounted on driverless cars, UAV, aircraft or satellites. They form part of the big data to handle and to utilise for information mining and target detection. Digital image processing is a computer-based technique which carries out manipulation, enhancement, compression and representation of the information embedded. Machine learning and artificial intelligence algorithms can then be applied for target detection, classification and identification. The topics covered in this course are the key elements in computer vision and artificial intelligence for a wide range of applications in various disciplines and fields, including robot control, search and rescue, surveillance and Earth observation.
This course covers basic concepts and fundamental methodologies applicable to digital image processing: Image registration; image enhancement in spatial and spatial frequency domains; image coding and compression; deep learning, image segmentation and classification; applications in remote sensing, defence and security, law enforcement and space management.
