Title: | A framework for robust object multi-detection with a vote aggregation and a cascade filtering |
Authors: | Kurzejamski, Grzegorz Zawistowski, Jacek Sarwas, Grzegorz |
Citation: | WSCG '2015: short communications proceedings: The 23rd International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision 2015 in co-operation with EUROGRAPHICS: University of West Bohemia, Plzen, Czech Republic8-12 June 2015, p. 9-16. |
Issue Date: | 2015 |
Publisher: | Václav Skala - UNION Agency |
Document type: | konferenční příspěvek conferenceObject |
URI: | wscg.zcu.cz/WSCG2015/CSRN-2502.pdf http://hdl.handle.net/11025/29660 |
ISBN: | 978-80-86943-66-4 |
ISSN: | 2464-4617 |
Keywords: | počítačové vidění;analýza obrazu;detekce více objektů;lokalizace objektu;přizpůsobení vzoru |
Keywords in different language: | computer vision;image analysis;multiple object detection;object localization;pattern matching |
Abstract: | This paper presents a framework designed for the multi-object detection purposes and adjusted for the application of product search on the market shelves. The framework uses a single feedback loop and a pattern resizing mechanism to demonstrate the top effectiveness of the state-of-the-art local features. A high detection rate with a low false detection chance can be achieved with use of only one pattern per object and no manual parameters adjustments. The method incorporates well known local features and a basic matching process to create a reliable voting space. Further steps comprise of metric transformations, graphical vote space representation, two-phase vote aggregation process and a cascade of verifying filters. |
Rights: | © Václav Skala - UNION Agency |
Appears in Collections: | WSCG '2015: Short Papers Proceedings |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Kurzejamski.pdf | Plný text | 1,42 MB | Adobe PDF | View/Open |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/29660
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.