Video Stabilization Demos

 

Results presented in the following paper:

Junlan Yang, Dan Schonfeld and Magdi Mohamed, ”Robust Video Stabilization Based on Particle Filter Tracking of Projected Camera Motion”, IEEE Transactions on Circuits and Systems for Video Technology, Volume 19, Issue 7, July 2009.

PFME (particle filtering-based motion estimation) stands for the technique we proposed in the above paper. MFME (matched feature-based motion estimation) and CFME (cost function-based motion estimation) stand for another two existing techniques to which we compare our algorithm. Details available in the above paper.

For viewing purpose mainly. Download permitted, however, proper citations must be provided in the case of academic usage, publication and modification of the presented videos. Commercial usage prohibited. Copyright belongs to Junlan Yang, ECE,University of Illinois, Chicago.

Back to Projects

 

ONDESK

Original Video

Stabilized video based on PFME (proposed method)

compared with

Stabilized video based on MFME

Stabilized video based on CFME

 

STREET

Original Video

Stabilized video based on PFME (proposed method)

compared with

Stabilized video based on MFME

Stabilized video based on CFME

 

ONROAD

Original Video

Stabilized video based on PFME (proposed method)

compared with

Stabilized video based on MFME

Stabilized video based on CFME

 

ONROAD_CAR

Original Video

Stabilized video based on PFME (proposed method)

 

SYNTHETIC

Original Video

Stabilized video based on PFME (proposed method)

compared with

Stabilized video based on MFME

Stabilized video based on CFME