Our Computer Vision program explores the fundamentals and advanced techniques of visual perception for machines. Students learn how to design algorithms that enable computers to interpret and understand visual data from images to video streams.
Key Topics Covered
- Image Processing & Feature Extraction: Techniques like edge detection, corner detection, and feature matching.
- Deep Learning for Vision: CNNs, transfer learning, and fine-tuning models for tasks like object detection and segmentation.
- 3D Vision: Depth estimation, point cloud processing, and 3D reconstruction.
- Real-Time Vision Systems: Optimizing models for embedded systems and edge devices.
Learning Outcomes
- Develop custom computer vision pipelines for real-world applications.
- Implement state-of-the-art object detection and tracking systems.
- Build vision-based autonomous systems for drones, robots, and IoT devices.
Who Should Join?
- Undergraduate and graduate students in Computer Science, AI, and Robotics.
- Researchers and engineers working on vision-based autonomous systems.
- Professionals looking to upskill in deep learning and computer vision.
Format
- Workshops: Hands-on sessions with Librosa, OpenCV, PyTorch, and TensorFlow.
- Projects: Build a vision-based object tracker or real-time scene analyzer.
- Resources: Access to GPU clusters, datasets (ImageNet, COCO), and pre-trained models.