A Particle Filtering approach to salient video object localization

Gray, Charles; James, Stuart; Collomosse, John; Asente, Paul

Abstract

We describe a novel fully automatic algorithm for identifying salient objects in video based on their motion. Spatially coherent clusters of optical flow vectors are sampled to generate estimates of affine motion parameters local to super-pixels identified within each frame. These estimates, combined with spatial data, form coherent point distributions in a 5D solution space corresponding to objects or parts there-of. These distributions are temporally denoised using a particle filtering approach, and clustered to estimate the position and motion parameters of salient moving objects in the clip. We demonstrate localization of salient object/s in a variety of clips exhibiting moving and cluttered backgrounds.

Citation

Gray, C., James, S., Collomosse, J., & Asente, P. (2014, October). A Particle Filtering approach to salient video object localization. Presented at 2014 IEEE International Conference on Image Processing (ICIP), Paris, France

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2014 IEEE International Conference on Image Processing (ICIP)
• Start Date: Oct 27, 2014
• End Date: Oct 30, 2014
• Online Publication Date: Jan 29, 2015
• Publication Date: 2014
• Deposit Date: Dec 13, 2023
• Publisher: Institute of Electrical and Electronics Engineers
• Book Title: 2014 IEEE International Conference on Image Processing (ICIP)
• DOI: https://doi.org/10.1109/ICIP.2014.7025038
• Public URL: https://durham-repository.worktribe.com/output/2024584