Dominant crowd flow segmentation is the first step towards building an automated monitoring system for high density crowd scenes. In computer vision, optical flow is widely used to compute pixel wise instantaneous motion between consecutive frames, and numerous methods are reported to efficiently compute accurate optical flow. However, optical flow does not capture long-range temporal dependencies, since it is based on just two frames. In order to achieve an accurate representation of flow from crowd motion, we use the streaklines to compute a new motion field which we refer to as streak flow. To compute streak flow, streaklines are computed by temporally integrating optical flow.
-
Notifications
You must be signed in to change notification settings - Fork 1
psk001/DIP-project
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
No description or website provided.
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published