Interest Point Detectors Stability Evaluation on ApolloScape Dataset

Jacek Komorowski , Konrad Czarnota , Tomasz Trzciński , Łukasz Dąbała , Simon Lynen

Abstract

In the recent years, a number of novel, deep-learning based, interest point detectors, such as LIFT, DELF, Superpoint or LF-Net was proposed. However there’s a lack of a standard benchmark to evaluate suitability of these novel keypoint detectors for real-live applications such as autonomous driving. Traditional benchmarks (e.g. Oxford VGG) are rather limited, as they consist of relatively few images of mostly planar scenes taken in favourable conditions. In this paper we verify if the recent, deep-learning based interest point detectors have the advantage over the traditional, hand-crafted keypoint detectors. To this end, we evaluate stability of a number of hand crafted and recent, learning-based interest point detectors on the street-level view ApolloScape dataset.
Author Jacek Komorowski (FEIT / ICS)
Jacek Komorowski,,
- The Institute of Computer Science
, Konrad Czarnota - [Warsaw University of Technology (PW), MNiSW [80]]
Konrad Czarnota,,
-
- Politechnika Warszawska
, Tomasz Trzciński (FEIT / IN)
Tomasz Trzciński,,
- The Institute of Computer Science
, Łukasz Dąbała (FEIT / IN)
Łukasz Dąbała,,
- The Institute of Computer Science
, Simon Lynen - [Google LLC]
Simon Lynen,,
-
-
Pages727-739
Publication size in sheets0.6
Book Leal-Taixé Laura, Roth Stefan (eds.): Computer Vision – ECCV 2018 Workshops, Lecture Notes In Computer Science, vol. 11133, 2019, Springer International Publishing, ISBN 978-3-030-11020-8, [978-3-030-11021-5 (eBook)], 753 p.
2019_Bookmatter_ComputerVisionECCV2018Workshop.pdf / No licence information (file archived - login or check accessibility on faculty)
Keywords in EnglishKeypoint detectors Interest points stability
DOIDOI:10.1007/978-3-030-11021-5_45
URL https://link.springer.com/chapter/10.1007%2F978-3-030-11021-5_45
Languageen angielski
Score (nominal)140
Score sourceconferenceList
ScoreMinisterial score = 140.0, 06-12-2019, ChapterFromConference
Publication indicators Scopus Citations = 0
Citation count*
Cite
Share Share

Get link to the record


* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Back
Confirmation
Are you sure?