Computer Vision III: Detection, Segmentation and Tracking (CV3DST) (IN2375)

Welcome to Computer Vision III: Detection, Segmentation and Tracking course offered in WS22.

Lecture

Date and location: TBA

Lecturers: Prof. Dr. Laura Leal-Taixé

ECTS: 6

2V + 2U

Practical sessions

Date and location: TBA

Details will be announced soon.

Preliminary Content

• Date TBA - Lecture 1: Introduction and Lecture 2: Two-stage detectors (RCNN, Fast RCNN, Faster RCNN)
• Date TBA - Lecture 3: One-stage detectors (YOLO, RetinaNet)
• Date TBA - Lecture 4: Single/multi-object tracking
• Date TBA - Lecture 5: Multiple object tracking (Message Passing Networks)
• Date TBA - Lecture 6: Transformers and its usage in Computer Vision
• Date TBA - Lecture 7: Pedestrian Trajectory Prediction (GANs)
• Date TBA - No lecture
• Date TBA - Lecture 8: Semantic segmentation
• Date TBA - Lecture 9: Instance segmentation
• Date TBA - No lecture
• Date TBA - Lecture 10: Video object segmentation
• Date TBA - Lecture 11: 3D Tracking and segmentation
• Date TBA - Final competition presentation by the winners

Slides

TBA

Videos

TBA

Prerequisites

• Introduction to Deep Learning (I2DL) (IN2346)
• Strong mathematical background: Linear algebra and calculus.
• Previous knowledge of Python is mandatory.
• Previous knowledge of PyTorch is highly recommended.

Moodle

We use Moodle for discussions and to distribute important information. Please check the News and Discussion boards regularly or subscribe to them. The slides and all material will also be posted on Moodle.

FINAL EXAM:

• Exam date: TBA

Office Hours

TBA

Contact us

If you have any questions regarding the organization of the course, do not hesitate to contact us at: cv3dst-ss22@dvl.in.tum.de

For questions on the syllabus, exercises or any other questions on the content of the lecture, we will use the Moodle discussion board.