Fast Scale Invariant Tracker and Re-identification for First-Person Social Videos

ABSTRACT

We address the problem of pedestrian tracking in videos of crowded scene which are captured by first-person viewpoint. The constant motion of camera and pedestrian makes this task challenging. The prime challenges are natural head motion of wearer and target loss and reappearance in a later frame, due to frequent changes in field of view. We propose that the use of first-person vision specific optical flow information and also the modification in the update process along with search region of trackers are useful to identify a lost target in a later frame. This process is termed re-identification in this paper. The specific trackers modified are MEEM and STRUCK. In addition to re-identification we achieve scale invariant tracking (upto $50\mathrm{\%}$ scale variation) and speed up by a factor of 2. We name our tracker as EgoTracker, since it utilizes the information which is specific to egocentric vision.

Keywords:

• Classification score
• EgoTracker
• Fast tracker
• Human tracking
• Optical flow
• Re-identification
• Scale invariance

DISCLOSURE STATEMENT

No potential conflict of interest was reported by the author(s).

Notes

1 All results in the form of videos are available at https://www.youtube.com/playlist?list=PLJtUItpEnvbNQaGvVqF-bZYtn_75wR212

Additional information

Notes on contributors

Jyoti Nigam

Jyoti Nigam is a PhD student in School of Computing and Electrical Engineering (SCEE) at Indian Institute of Technology, India. Her research interest is computer vision.

Renu M. Rameshan

Renu M Rameshan is an assistant professor in School of Computing and Electrical Engineering (SCEE) at Indian Institute of Technology, India. Her research interest is computer vision, image processing and ill-posed problems. Email: [email protected]