This course focuses on the recovery of the 3D structure of a scene from images taken from different viewpoints. We start by first building a comprehensive geometric model of a camera and then develop a method for finding (calibrating) the internal and external parameters of the camera model. Then, we show how two such calibrated cameras, whose relative positions and orientations are known, can be used to recover the 3D structure of the scene. This is what we refer to as simple binocular stereo. Next, we tackle the problem of uncalibrated stereo where the relative positions and orientations of the two cameras are unknown. Interestingly, just from the two images taken by the cameras, we can both determine the relative positions and orientations of the cameras and then use this information to estimate the 3D structure of the scene.
Offert par
Spécialisation First Principles of Computer VisionUniversité ColumbiaÀ propos de ce cours
Learners should know the fundamentals of linear algebra and calculus. The knowledge of any programming language is beneficial, though not required.
Ce que vous allez apprendre
Develop a comprehensive model of a camera and learn how to calibrate a camera by estimating its parameters.
Develop a simple stereo system that uses two cameras of known configuration to estimate the 3D structure of a scene.
Design an algorithm for recovering both the structure of the scene and the motion of the camera from a video.
Develop optical flow algorithms for estimating the motion of points in a video sequence.
Compétences que vous acquerrez
- Epipolar Geometry
- Camera Model
- Camera Calibration
- Structure from Motion
- Simple Stereo
Learners should know the fundamentals of linear algebra and calculus. The knowledge of any programming language is beneficial, though not required.
Offert par
Université Columbia
For more than 250 years, Columbia has been a leader in higher education in the nation and around the world. At the core of our wide range of academic inquiry is the commitment to attract and engage the best minds in pursuit of greater human understanding, pioneering new discoveries and service to society.
Programme de cours : ce que vous apprendrez dans ce cours
Getting Started: 3D Reconstruction - Multiple Viewpoints
Camera Calibration
Uncalibrated Stereo
Optical Flow
À propos du Spécialisation First Principles of Computer Vision
This specialization presents the first comprehensive treatment of the foundations of computer vision. It focuses on the mathematical and physical underpinnings of vision and has been designed for learners, practitioners and researchers who have little or no knowledge of computer vision. The program includes a series of 5 courses. Any learner who completes this specialization has the potential to build a successful career in computer vision, a thriving field that is expected to increase in importance in the coming decades.
Foire Aux Questions
Quand aurai-je accès aux vidéos de cours et aux devoirs ?
À quoi ai-je droit si je m'abonne à cette Spécialisation ?
Une aide financière est-elle possible ?
D'autres questions ? Visitez le Centre d'Aide pour les Étudiants.
