Vertical line-based descriptor for omnidirectional view image

Nguan Soon Chong, M. L. Dennis Wong, Yau Hee Kho

2014

Closed access Metadata (CSL-JSON)
DOI 10.1109/elinfocom.2014.6914386
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Catadioptric omnidirectional view sensor has a convenient 360 degree field of view that favours various robotic applications. The distortion nature in omnidirectional view images allows the discovery of a new robust image feature in the form of vertical/central propagating lines. In this paper, we proposed an improvement to the existing vertical line detection algorithm using Haar wavelet transform under integral image environment. Subsequently, a new lightweight descriptor scheme is developed using the same Haar wavelet response that complies with the nature of line features.