Computer Vision
Undergraduate course, School of Computer Science and Technology, Guangdong University of Technology, 2024
Computer vision is a core area of artificial intelligence, enabling machines to analyze and interpret visual data from the world, driving advancements in autonomous vehicles, augmented reality, medical diagnostics, and robotics. This course introduces core concepts such as image acquisition, processing, feature extraction, segmentation, and 3D reconstruction, with practical applications in depth estimation and panoramic stitching.
Hands-on experiments utilize OpenCV for tasks like object detection and motion tracking, alongside deep learning frameworks such as TensorFlow, PyTorch or Mindspore for modern applications like scene understanding and image generation. Students will gain practical skills through projects, preparing them to address contemporary challenges in computer vision.