Visual Computing
Visual Computing
What You'll Learn
- Process and analyze images using OpenCV and Python
- Implement computer vision algorithms for object detection and recognition
- Build 3D graphics and rendering pipelines for real-time applications
- Develop AR/VR experiences and spatial computing applications
- Apply deep learning for visual understanding and segmentation
- Implement video processing, motion tracking, and gesture recognition
- Optimize and deploy visual computing pipelines on edge devices
- Capstone: Build a complete visual computing application
Course Content
Instructor
Dr. James Morrison
Dr. James Morrison is a Professor of Computer Science and Electrical Engineering at Carnegie Mellon University, where he directs the Computational Vision and Learning Lab. With over 20 years of research experience in computer vision, machine learning, and graphics, he has made foundational contributions to visual recognition, 3D reconstruction, and real-time rendering systems. Dr. Morrison holds a PhD in Computer Science from MIT and has published more than 200 peer-reviewed papers with over 40,000 citations. He is a recipient of the IEEE CVPR Best Paper Award, the ACM SIGGRAPH Achievement Award, and was named one of the top computer vision researchers by IEEE. Dr. Morrison has worked as a technical advisor to major companies including Google, Meta, NVIDIA, and Microsoft, and has contributed to open-source projects like OpenCV. His expertise spans both academic research and industrial applications, making complex visual computing concepts accessible to practitioners.
Throughout this course, James will guide you through the complete spectrum of visual computing, from fundamental image processing to cutting-edge AR/VR applications, combining rigorous mathematical foundations with hands-on coding exercises and real-world projects.
Student Reviews
This visual computing course is incredibly comprehensive. The computer vision hands-on labs with OpenCV and YOLO were immediately useful in my work. The AR/VR section gave me the foundation to build spatial apps. Dr. Morrison makes even complex topics like 3D transformations approachable.
I went from knowing nothing about computer vision to building a real-time object detection system. The deep learning for vision section was particularly valuable. The capstone project where I created an AR app was challenging and rewarding. This course is worth every penny.
The depth of visual computing coverage is impressive - from image processing to 3D rendering to AR/VR. The GPU cloud labs allowed me to experiment with real-time rendering. Dr. Morrison's research background gives unique insights into modern techniques. A complete visual computing education.
Excellent practical approach to visual computing. The YOLO object detection implementation was crystal clear. Video processing and motion tracking sections gave me tools I use daily. The AR/VR module helped me transition into spatial computing roles. Highly recommended!