GMS: Grid-Based Motion Statistics for Fast, Ultra-Robust Feature Correspondence

Incorporating smoothness constraints into feature matching is known to enable ultra-robust matching. However, such formulations are both complex and slow, making them unsuitable for video applications. This paper proposes GMS (Grid-based Motion Statistics), a simple means of encapsulating motion smo...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) s. 2828 - 2837
Hlavní autoři:	JiaWang Bian, Wen-Yan Lin, Matsushita, Yasuyuki, Sai-Kit Yeung, Tan-Dat Nguyen, Ming-Ming Cheng
Médium:	Konferenční příspěvek
Jazyk:	angličtina
Vydáno:	IEEE 01.07.2017
Témata:	Coherence Real-time systems Robustness Silicon Three-dimensional displays
ISSN:	1063-6919, 1063-6919
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Incorporating smoothness constraints into feature matching is known to enable ultra-robust matching. However, such formulations are both complex and slow, making them unsuitable for video applications. This paper proposes GMS (Grid-based Motion Statistics), a simple means of encapsulating motion smoothness as the statistical likelihood of a certain number of matches in a region. GMS enables translation of high match numbers into high match quality. This provides a real-time, ultra-robust correspondence system. Evaluation on videos, with low textures, blurs and wide-baselines show GMS consistently out-performs other real-time matchers and can achieve parity with more sophisticated, much slower techniques.
ISSN:	1063-6919 1063-6919
DOI:	10.1109/CVPR.2017.302