Title: Fast Rotation Invariant Object Detection with Gradient based Detection Models
Authors: De Smedt, Floris
Goedemé, Toon
Issue Date: 11-Mar-2015
Publisher: VISIGRAPP
Host Document: Proceedings of the 10th International Conference on Computer Vision Theory and Applications - (Volume 2) (VISIGRAPP 2015) pages:400-407
Conference: VISAPP edition:10 location:Berlin, Germany date:11-14 March 2015
Article number: 210
Abstract: Accurate object detection has been studied thoroughly over the years. Although these techniques have become very precise, they lack the capability to cope with a rotated appearance of the object. In this paper we tackle this problem in a two step approach. First we train a specific model for each orientation we want to cover. Next to that we propose the use of a rotation map that contains the predicted orientation information at a specific location based on the dominant orientation. This helps us to reduce the number of models that will be evaluated at each location. Based on 3 datasets, we obtain a high speed-up while still maintaining accurate rotated object detection.
ISBN: 978-989-758-090-1
Publication status: published
KU Leuven publication type: IC
Appears in Collections:Electrical Engineering (ESAT) TC, Technology Campus De Nayer Sint-Katelijne-Waver
Technologiecluster ESAT Elektrotechnische Engineering

Files in This Item:
File Description Status SizeFormat
VISAPP_2015_210_CR.pdf Published 727KbAdobe PDFView/Open


All items in Lirias are protected by copyright, with all rights reserved.