计算机视觉导论-Introduction to Computer Vision
Course ID：
04834920
Credits：
3
Department：
信息科学技术学院
Introduction in Chinese：
计算机视觉是人工智能的主要研究和应用领域之一，在诸如图像理解和处理、医疗、无人驾驶及机器人领域都有广泛的应用。本课程致力于介绍计算机视觉中的基本概念和众多应用问题，力图扎实基础、展现计算机视觉的全貌，以一种平衡的方式覆盖传统方法与基于深度学习的解决思路。课程具体内容包括：计算机视觉基础概念（相机模型与标定、多视角几何、基于structure from motion的三维重建）、基础方法（特征提取、深度学习基础、拟合与匹配）和各种视觉任务（图像分类与分割、目标检测、时序数据的处理、生成模型以及三维视觉初步）。在本课程中学生将学习如何搭建基础的视觉系统，并实现基于神经网络的视觉数据处理和网络学习。
Introduction in English：
Computer vision is one of the major research fields of artificial intelligence, with many applications in image understanding and processing, medical care, autonomous driving, and robotics. This course provides a comprehensive introduction to the basic concepts and applications in computer vision, aims at consolidating the basics and depicting a full picture of this field, and will balance the material of traditional methods and deep learning based methods. Topics include: computer vision fundamentals such as camera models and calibration, multi-view geometry, structure from motion; basic methods (feature extraction, filtering, deep neural networks, fitting and matching); and many vision tasks (image recognition, segmentation, object detection, temporal data processing, generative model and 3D vision). During this course, students will learn to build a basic vision system and implement and train their own neural networks to process and analyze vision data.
