elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Match or No Match: Keypoint Filtering based on Matching Probability

Papadaki, Alexandra and Hänsch, Ronny (2020) Match or No Match: Keypoint Filtering based on Matching Probability. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020, pp. 4371-4378. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020-06-14 - 2020-06-19, virtual. doi: 10.1109/CVPRW50498.2020.00515. ISBN 978-1-7281-9360-1. ISSN 2160-7508.

Full text not available from this repository.

Abstract

Keypoints that do not meet the needs of a given application are a very common accuracy and efficiency bottleneck in many computer vision tasks, including keypoint matching and 3D reconstruction. Many computer vision and machine learning methods have dealt with this issue, trying to improve keypoint detection or the matching process. We introduce an algorithm that filters detected keypoints before the matching is even attempted, by predicting the probability of each point to be successfully matched. This is realised using a flexible and time efficient Random Forest classifier. Experiments on stereo and multi-view datasets of building facades show that the proposed method decreases the computational cost of a subsequent keypoint matching and 3D reconstruction, by correctly filtering 50% of the points that wouldn't be matched while preserving 73% of the matchable keypoints. This enables a subsequent processing with minimal mismatches, provides reliable matches, and point clouds. The presented filtering leads to an improved 3D reconstruction of the scene, even in the hard case of repetitive patterns and vegetation.

Item URL in elib:https://elib.dlr.de/139665/
Document Type:Conference or Workshop Item (Speech)
Title:Match or No Match: Keypoint Filtering based on Matching Probability
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Papadaki, AlexandraTU BerlinUNSPECIFIEDUNSPECIFIED
Hänsch, RonnyUNSPECIFIEDhttps://orcid.org/0000-0002-2936-6765UNSPECIFIED
Date:14 June 2020
Journal or Publication Title:2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
DOI:10.1109/CVPRW50498.2020.00515
Page Range:pp. 4371-4378
ISSN:2160-7508
ISBN:978-1-7281-9360-1
Status:Published
Keywords:Keypoint matching, image matching, machine learning, structure from motion, 3D reconstruction
Event Title:IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Event Location:virtual
Event Type:international Conference
Event Start Date:14 June 2020
Event End Date:19 June 2020
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Aircraft SAR
Location: Oberpfaffenhofen
Institutes and Institutions:Microwaves and Radar Institute > SAR Technology
Deposited By: Hänsch, Ronny
Deposited On:16 Dec 2020 10:16
Last Modified:24 Apr 2024 20:40

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.