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.

Computer vision

Some example frames showing the scale adaptation of our approach.

Due to variations of appearance, the model generated from the first frame needs to be updated on the fly. We address this problem by online machine learning approaches, more concretely, discriminative correlation filters.

This video illustrates online adaptation of feature (color) selection to the model appearance.

Application scenario within WASP where the developed code has been used for people tracking:

Researchers

Joakim Johnander Faxén

Fahad Khan

Associate Professor, Docent

Michael Felsberg

Professor, Head of Division

External partners

International VOT benchmark committee

http://www.votchallenge.net/

Publications

Martin Danelljan, Goutam Bhat, Susanna Gladh, Fahad Shahbaz Khan, Michael Felsberg (2019)

Deep motion and appearance cues for visual tracking

Pattern Recognition Letters , Vol.124 , s.74-81 Continue to DOI

Martin Danelljan, Gustav Häger, Fahad Shahbaz Khan, Michael Felsberg (2017)

Discriminative Scale Space Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence , Vol.39 , s.1561-1575 Continue to DOI

Unveiling the Power of Deep Tracking, Goutam Bhat , Joakim Johnander, Martin Danelljan, Fahad Shahbaz Khan, and Michael Felsberg, Computer Vision Foundation 2018.

WASP at CVL

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.