Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
skip to main content
10.5555/2354409.2354978guideproceedingsArticle/Chapter ViewAbstractPublication PagesConference Proceedingsacm-pubtype
Article

Are we ready for autonomous driving? The KITTI vision benchmark suite

Published: 16 June 2012 Publication History

Abstract

Today, visual recognition systems are still rarely employed in robotics applications. Perhaps one of the main reasons for this is the lack of demanding benchmarks that mimic such scenarios. In this paper, we take advantage of our autonomous driving platform to develop novel challenging benchmarks for the tasks of stereo, optical flow, visual odometry/SLAM and 3D object detection. Our recording platform is equipped with four high resolution video cameras, a Velodyne laser scanner and a state-of-the-art localization system. Our benchmarks comprise 389 stereo and optical flow image pairs, stereo visual odometry sequences of 39.2 km length, and more than 200k 3D object annotations captured in cluttered scenarios (up to 15 cars and 30 pedestrians are visible per image). Results from state-of-the-art algorithms reveal that methods ranking high on established datasets such as Middlebury perform below average when being moved outside the laboratory to the real world. Our goal is to reduce this bias by providing challenging benchmarks with novel difficulties to the computer vision community. Our benchmarks are available online at: www.cvlibs.net/datasets/kitti

Cited By

View all
  • (2024)VOGUESProceedings of the 33rd USENIX Conference on Security Symposium10.5555/3698900.3699254(6327-6344)Online publication date: 14-Aug-2024
  • (2024)MMT-benchProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3694429(57116-57198)Online publication date: 21-Jul-2024
  • (2024)PositionProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3694048(48390-48403)Online publication date: 21-Jul-2024
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings
CVPR '12: Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
June 2012
3800 pages
ISBN:9781467312264

Publisher

IEEE Computer Society

United States

Publication History

Published: 16 June 2012

Author Tags

  1. Benchmark testing
  2. Cameras
  3. Measurement
  4. Optical imaging
  5. Optical sensors
  6. Visualization

Qualifiers

  • Article

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)0
  • Downloads (Last 6 weeks)0
Reflects downloads up to 16 Jan 2025

Other Metrics

Citations

Cited By

View all
  • (2024)VOGUESProceedings of the 33rd USENIX Conference on Security Symposium10.5555/3698900.3699254(6327-6344)Online publication date: 14-Aug-2024
  • (2024)MMT-benchProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3694429(57116-57198)Online publication date: 21-Jul-2024
  • (2024)PositionProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3694048(48390-48403)Online publication date: 21-Jul-2024
  • (2024)Compositional image decomposition with diffusion modelsProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3693975(46823-46842)Online publication date: 21-Jul-2024
  • (2024)Stereo riskProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3693335(31326-31343)Online publication date: 21-Jul-2024
  • (2024)GeminiFusionProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3692943(21753-21767)Online publication date: 21-Jul-2024
  • (2024)Neuroexplicit diffusion models for inpainting of optical flow fieldsProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3692618(13691-13705)Online publication date: 21-Jul-2024
  • (2024)DSD-DAProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3692601(13225-13240)Online publication date: 21-Jul-2024
  • (2024)VILAMProceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation10.5555/3691825.3691925(1831-1845)Online publication date: 16-Apr-2024
  • (2024)A comprehensive survey and taxonomy on point cloud registration based on deep learningProceedings of the Thirty-Third International Joint Conference on Artificial Intelligence10.24963/ijcai.2024/922(8344-8353)Online publication date: 3-Aug-2024
  • Show More Cited By

View Options

View options

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media