KITTI Vision Benchmark Suite: We take advantage of our autonomous driving platform Annieway to develop novel challenging real-world computer vision benchmarks. Our tasks of interest are: stereo, optical flow, visual odometry, 3D object detection and 3D tracking. For this purpose, we equipped a standard station wagon with two high-resolution color and grayscale video cameras. Accurate ground truth is provided by a Velodyne laser scanner and a GPS localization system. Our datsets are captured by driving around the mid-size city of Karlsruhe, in rural areas and on highways. Up to 15 cars and 30 pedestrians are visible per image. Besides providing all data in raw format, we extract benchmarks for each task. For each of our benchmarks, we also provide an evaluation metric and this evaluation website. Preliminary experiments show that methods ranking high on established benchmarks such as Middlebury perform below average when being moved outside the laboratory to the real world. Our goal is to reduce this bias and complement existing benchmarks by providing real-world benchmarks with novel difficulties to the community.

References in zbMATH (referenced in 15 articles )

Showing results 1 to 15 of 15.
Sorted by year (citations)

  1. Datta, Amitava; Kaur, Amardeep; Lauer, Tobias; Chabbouh, Sami: Exploiting multi-core and many-core parallelism for subspace clustering (2019)
  2. Naiel, Mohamed A.; Ahmad, M. Omair; Swamy, M. N. S.: A vehicle detection scheme based on two-dimensional HOG features in the DFT and DCT domains (2019)
  3. Lindeberg, Tony: Spatio-temporal scale selection in video data (2018)
  4. Berger, Johannes; Lenzen, Frank; Becker, Florian; Neufeld, Andreas; Schnörr, Christoph: Second-order recursive filtering on the rigid-motion Lie group (\mathrmSE_3) based on nonlinear observations (2017)
  5. Burger, Martin; Dirks, Hendrik; Frerking, Lena: On optical flow models for variational motion estimation (2017)
  6. Coninx, Alexandre; Bessière, Pierre; Droulez, Jacques: Quick and energy-efficient Bayesian computing of binocular disparity using stochastic digital signals (2017)
  7. Hollósi, Gergely; Lukovszki, Csaba; Moldován, István; Plósz, Sándor; Harasztos, Frigyes: Monocular indoor localization techniques for smartphones (2016)
  8. Xia, Shengxiang: A topological analysis on patches of optical flow (2016)
  9. Žbontar, Jure; Lecun, Yann: Stereo matching by training a convolutional neural network to compare image patches (2016)
  10. Buades, Antoni; Facciolo, Gabriele: Reliable multiscale and multiwindow stereo matching (2015)
  11. Demetz, Oliver; Hafner, David; Weickert, Joachim: Morphologically invariant matching of structures with the complete rank transform (2015)
  12. Dhiman, Nitin Kumar; Deodhare, Dipti; Khemani, Deepak: \textitWheream I? Creating spatial awareness in unmanned ground robots using SLAM: a survey (2015) ioport
  13. Hafner, David; Demetz, Oliver; Weickert, Joachim; Reißel, Martin: Mathematical foundations and generalisations of the census transform for robust optic flow computation (2015)
  14. Sun, Deqing; Roth, Stefan; Black, Michael J.: A quantitative analysis of current practices in optical flow estimation and the principles behind them (2014) ioport
  15. Becker, Florian; Lenzen, Frank; Kappes, Jörg H.; Schnörr, Christoph: Variational recursive joint estimation of dense scene structure and camera motion from monocular high speed traffic sequences (2013)