Background elimination method in the event based vision sensor for dynamic environment

Autor:	Seongyeong Jeong, Kwanghyuk Bae, Shung Han Cho, Kyu-Min Kyung, Tae-Chan Kim
Rok vydání:	2014
Předmět:	Contextual image classification Motion field Computer science Feature (computer vision) business.industry Gesture recognition Motion detection Computer vision Artificial intelligence Image sensor business Motion (physics)
Zdroj:	ICCE
DOI:	10.1109/icce.2014.6775934
Popis:	This paper presents a background elimination method in the event based vision sensor for dynamic environment. Event based vision sensors quickly output digital data, two dimensional coordinate and time-stamp, in the form of events. Proposed method classifies events into groups according to their position vector. Position vector contains direction and velocity information. Each classified group has their own motion feature. Unintended events are eliminated base on the analysis of motion feature of each group. It makes event based sensor robust in the dynamic environments and guarantees accurate motion detection.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::fc85da230b28ee23490dd3bf81685e50 https://doi.org/10.1109/icce.2014.6775934 Zobrazit plný text záznamu