Computer Vision Laboratory (CVL)

Welcome to the Computer Vision Laboratory (CVL), part of the Department of Electrical engineering at Linköping University.

Autonoma system datorseende Photo: Göran BillesonThe research at the Computer Vision Laboratory (CVL) covers a wide range of topics within artificial visual systems (AVS): computational imaging; detection, tracking and recognition of objects; estimation of pose and 3D structure; robot vision and autonomous systems; medical imaging.

The design of AVS has its roots in the modelling of the human visual system (HVS) and CVL aims at improving AVS capabilities substantially, driven by an HVS-inspired approach. This choice is compellingly motivated by the fact that AVS are supposed to coexist with – and therefore predict actions of – humans, e.g. regarding self-driving cars sharing road space and interacting with humans.

Courses

Courses given by the Division of Computer Vision Laboratory

Thesis

Master Thesis Projects in Computer Vision

Contact

Research within WASP

WASP Computer Vision Laboratory

The research covers a broad range of topics within artificial visual systems with a particular focus on machine learning for robot vision. The group has made major contributions in establishing the concept of computer vision in Sweden.

.

Machine Learning for Visual Navigation and Localization

Navigation and localization are principal challenges in Robot Vision, where the task is to estimate the geometric relation between a vehicle and its environment, either passively in a virtual model or actively through controlling the robot.

Visual Object Tracking

Visual Object Tracking is one of the principal challenges in Computer Vision, where the task is to locate a certain object in all frames of a video, given only its location in the first frame.

A Detailed Framework for Semantic Description of Humans

Semantic description of humans in images and videos is one of the fundamental problems in computer vision with applications such as visual surveillance, facial verification, health care, image and video search engines and human-computer interaction.

.

Point Cloud Processing

With the growing availability of depth cameras and lidar, the processing of the resulting point clouds has become its own sub-area of Computer Vision.

WASP - Wallenberg AI, Autonomous Systems and Software Program

The fourth industrial revolution is upon us, as automation becomes autonomy. LiU conducts outstanding research in several of the fields that are central to the Wallenberg AI Autonomous Systems and Software Program, WASP.

WASP associated doctoral thesis from CVL

Joakim Johnander: Dynamic Visual Learning
Abdelrahman Eldesokey: Uncertainty-Aware Convolutional Neural Networks for Vision Tasks on Sparse Data
Gustav Häger: Learning visual perception for autonomous systems
Bertil Grelsson: Vision-based Localization and Attitude Estimation Methods in Natural Environments
Martin Danelljan: Learning Convolution Operators for Visual Tracking

Research Computer Vision

Computer Vision

In large-scale emergencies caused by natural disasters, terrorist attacks or major accidents, blue-light forces and mission control need instantaneous info and visualization of the scenario, usually provided in terms of Hastily Formed Networks.

News

The supercomputer Berzelius photographed with fisheye lens.

Swedish AI research gets more muscle

The supercomputer Berzelius was inaugurated in the spring of 2021, and was then Sweden's fastest supercomputer for AI. Yet, more power is needed to meet the needs of Swedish AI research.

Portrait of Michael Felsberg with closed eyes.

Human vision – a challenge for AI

Achieving diversity in human vision is one of the major challenges for AI research. In the vast majority of cases, we are better than machines at understanding the world around us. But machines are catching up – slowly but surely.

Facial recognition used in more and more ways

Research into facial recognition has been under way for a long time, but has really taken off in recent years. “The technology is beginning to be used in more and more contexts”, says Jörgen Ahlberg, researcher in computer vision.

Lasse illuminates distance learning

As the coronavirus swept over us, Lasse Alfredsson in the Department of Electrical Engineering was already well set up for distance teaching. He uses video and a lightboard he built himself to make sure that the students can take part in teaching.

Michael Felsberg: Deep learning led to a gold rush

“We have been teaching deep learning in both undergraduate and postgraduate courses for several years", says Michael Felsberg, one of Sweden’s best AI researchers.

A computer algorithm to recognise and follow objects

Master's graduate Goutam Bhat has been awarded the Christer Gilén Scholarship for 2019 in the field of statistics and machine learning. The scholarship recognises his work in computer vision.

Latest publications

2023

Staff at CVL

Jörgen Ahlberg

Adjunct Associate Professor, Docent

Lasse Alfredsson

Associate Professor

Ioannis Athanasiadis

PhD student

Amanda Berg

Adjunct Assistant Lecturer

Frida Blomstedt

Emil Brissman

Johan Edstedt

PhD student

Michael Felsberg

Professor, Head of Division

Niclas Fock

Adjunct Associate Professor

Per-Erik Forssén

Senior Associate Professor

Leif Haglund

Adjunct Professor

Hannah Helgesen

PhD student

Joakim Johnander Faxén

Arvi Jonnarth

Fahad Khan

Associate Professor, Docent

Lena Klasén

Cuong Le

PhD student

William Ljungbergh

Maria Magnusson

Associate Professor

Pavlo Melnyk

PhD student

Andreas Robinson

Emanuel Sanchez Aimar

PhD student

Mårten Wadenbäck

Assistant Professor

Bastian Wandt

Assistant Professor

Ziliang Xiong

PhD student

Yushan Zhang

PhD student

About the Department

Department of Electrical Engineering (ISY)

The department is central to the engineering education at the Institute of Technology, one of four faculties at Linköping University, and this regards both basic and applied knowledge.

Computer Vision Laboratory (CVL)

Courses

Thesis

Contact

Michael Felsberg

Carina Lindström