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

Welcome to Computer Vision III: Detection, Segmentation and Tracking course offered in WS19.

Lecture

Date and location: Fridays (16:00-18:00) - MI HS2 (00.04.011), Informatics Building

Lecturers: Prof. Dr. Laura Leal-Taixé and Dr. Aljosa Osep.

ECTS: 6

2V + 2Ü

Practical

No location.

The practical part of the course will consist of an internal Kaggle-type of competition. Details will be announced soon.

Content

• 18.10 - Lecture 1: Introduction
• 08.11 - Lecture 2: Two-stage detectors (RCNN, Fast RCNN, Faster RCNN)
• 29.11 - Lecture 3: One-stage detectors (YOLO, RetinaNet)
• 06.12 - Lecture 4: Single/multi-object tracking
• 13.12 - Lecture 5: Multiple object tracking (Message Passing Networks)
• 20.12 - Lecture 6: Pedestrian Trajectory Prediction (GANs)
• 10.01 - Lecture 7: Video object segmentation
• 17.01 - Lecture 8: Semantic segmentation networks
• 24.01 - Lecture 9: Semantic segmentation networks
• 31.01 - Lecture 10: 3D Tracking and segmentation

• 07.02 - Project presentations

• 11.02 - Exam, 16:00-17:30

Practical sessions

• Presentations of the best performing methods will be held on February 7th

Slides

You can now download the slides in PDF format:

• Slides

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.

Contact us

If you have any questions regarding the organization of the course, do not hesitate to contact us at: dst@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.