Skip to Main content Skip to Navigation
Conference papers

Non-Additive Approach for Omnidirectional Image Gradient Estimation

Abstract : The way catadioptric images are acquired implies that they present radial distortions. Therefore, classical processing may not be suitable. This statement will be illustrated by considering edge detection matter. Classical edge detectors usually consist in three steps : gradient computation, maximization and thresholding. The two lasts steps use pixels neighborhood concept. On the opposite of perspective images where pixel neighborhood is intuitive, catadioptric images present radial resolution changes. Then, the size and shape of pixel neighborhood have to be depending on pixel location. This article presents a new gradient estimation approach based on non-additive kernels. This technique is adapted to catadioptric images and also provides a natural threshold discarding the arbitrary thresholding step.
Document type :
Conference papers
Complete list of metadata

Cited literature [17 references]  Display  Hide  Download
Contributor : Florence Jacquey <>
Submitted on : Thursday, December 6, 2007 - 8:58:32 AM
Last modification on : Tuesday, October 16, 2018 - 7:52:01 AM
Long-term archiving on: : Monday, April 12, 2010 - 6:19:59 AM



  • HAL Id : lirmm-00194216, version 1



Florence Jacquey, Frédéric Comby, Olivier Strauss. Non-Additive Approach for Omnidirectional Image Gradient Estimation. ICCV'07: International Conference on Computer Vision OMNIVIS'07: Workshop on Omnidirectional Vision, Camera Networks and Non-classical Cameras, Oct 2007, Rio de Janeiro, Brésil, pp.1-4. ⟨lirmm-00194216⟩



Record views


Files downloads