Abstract
Creating stereo ground truth based on real images is a measurement task. Measurements are never perfectly accurate: the depth at each pixel follows an error distribution. A common way to estimate the quality of measurements are error bars. In this paper we describe a methodology to add error bars to images of previously scanned static scenes. The main challenge for stereo ground truth error estimates based on such data is the nonlinear matching of 2D images to 3D points. Our method uses 2D feature quality, 3D point and calibration accuracy as well as covariance matrices of bundle adjustments. We sample the reference data error which is the 3D depth distribution of each point projected into 3D image space. The disparity distribution at each pixel location is then estimated by projecting samples of the reference data error on the 2D image plane. An analytical Gaussian error propagation is used to validate the results. As proof of concept, we created ground truth of an image sequence with 100 frames. Results show that disparity accuracies well below one pixel can be achieved, albeit with much large errors at depth discontinuities mainly caused by uncertain estimates of the camera location.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Although most of the following works comprise additional datasets next to stereo data, we only focus on the latter.
- 2.
Horizontal vertical focal lengths \((f_x, f_y)\), principle point \((c_x, c_y)\).
- 3.
- 4.
Cross correlation window: 21 \(\times \) 21. Search neighborhood 21 \(\times \) 21.
- 5.
Screenshots and usage videos of the tools can be found in the supplemental material.
- 6.
Based on the maximum deviation of the angle-axis vector.
- 7.
References
Baker, S., Scharstein, D., Lewis, J.P., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. Int. J. Comput. Vis. 92, 1–31 (2011)
Kondermann, D.: Ground truth design principles: an overview. In: Proceedings of the International Workshop on Video and Image Ground Truth in Computer Vision Applications, p. 5. ACM (2013)
Onkarappa, N., Sappa, A.D.: Synthetic sequences and ground-truth flow field generation for algorithm validation. Multimedia Tools Appl. 4, 1–15 (2013)
Haltakov, V., Unger, C., Ilic, S.: Framework for generation of synthetic ground truth data for driver assistance applications. In: Weickert, J., Hein, M., Schiele, B. (eds.) GCPR 2013. LNCS, vol. 8142, pp. 323–332. Springer, Heidelberg (2013)
Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VI. LNCS, vol. 7577, pp. 611–625. Springer, Heidelberg (2012)
Meister, S., Kondermann, D.: Real versus realistically rendered scenes for optical flow evaluation. In: Proceedings of 14th ITG Conference on Electronic Media Technology, Informatik Centrum Dortmund e.V. (2011)
Güssefeld, B., Kondermann, D., Schwartz, C., Klein, R.: Are reflectance field renderings appropriate for optical flow evaluation? In: IEEE International Conference on Image Processing 2014 (ICIP 2014), Paris, France (2014)
Liu, C., Freeman, W.T., Adelson, E.H., Weiss, Y.: Human-assisted motion annotation. In: IEEE Computer Society Conference on Computer Vision and PatternRecognition, CVPR 2008, pp. 1–8 (2008)
Donath, A., Kondermann, D.: Is crowdsourcing for optical flow ground truth generation feasible? In: Chen, M., Leibe, B., Neumann, B. (eds.) ICVS 2013. LNCS, vol. 7963, pp. 193–202. Springer, Heidelberg (2013)
Morales, S., Klette, R.: A third eye for performance evaluation in stereo sequence analysis. In: Jiang, X., Petkov, N. (eds.) CAIP 2009. LNCS, vol. 5702, pp. 1078–1086. Springer, Heidelberg (2009)
Meister, S., Izadi, S., Kohli, P., Hämmerle, M., Rother, C., Kondermann, D.: When can we use kinectfusion for ground truth acquisition? In: Proceedings Workshop on Color-Depth Camera Fusion in Robotics (2012)
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The kitti vision benchmark suite. In: Computer Vision and Pattern Recognition (CVPR), Providence, USA (2012)
Strecha, C., von Hansen, W., Van Gool, L., Fua, P., Thoennessen, U.: On benchmarking camera calibration and multi-view stereo for high resolution imagery. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1–8. IEEE (2008)
Vaudrey, T., Rabe, C., Klette, R., Milburn, J.: Differences between stereo and motion behaviour on synthetic and real-world stereo sequences. In: Proceedings of 23rd International on Conference Image and Vision Computing New Zealand (IVCNZ 2008), pp.1–6 (2008)
Kanatani, K.: Statistical optimization for geometric fitting: theoretical accuracy bound and high order error analysis. Int. J. Comput. Vis. 80, 167–188 (2008)
Kanatani, K.: Uncertainty modeling and model selection for geometric inference. IEEE Trans. Pattern Anal. Mach. Intell. 26, 1307–1319 (2004)
Triggs, B., McLauchlan, P.F., Hartley, R.I., Fitzgibbon, A.W.: Bundle adjustment – a modern synthesis. In: Triggs, B., Zisserman, A., Szeliski, R. (eds.) ICCV-WS 1999. LNCS, vol. 1883, pp. 298–372. Springer, Heidelberg (2000)
Förstner, W.: Reliability analysis of parameter estimation in linear models with applications to mensuration problems in computer vision. Comp. Vis. Graph. Image Proc. 40, 273–310 (1987)
Dickscheid, T., Läbe, T., Förstner, W.: Benchmarking automatic bundle adjustment results. In: 21st Congress of the International Society for Photogrammetry and Remote Sensing (ISPRS), Part B3a, pp. 7–12 (2008)
Jähne, B.: Digitale Bildverarbeitung, 7th edn. Springer, Heidelberg (2012)
Abraham, S., Hau, T.: Towards autonomous high-precision calibration of digital cameras. In: Videometrics, V. (ed.) Proceedings of SPIE Annual Meeting, vol. 3174, pp. 82–93. Citeseer (1997)
Afonso, M.V., Bioucas-Dias, J.M., Figueiredo, M.A.: Fast image recovery using variable splitting and constrained optimization. IEEE Trans. Image Process. 19, 2345–2356 (2010)
Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-\(\mathit{L}^1\) optical flow. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214–223. Springer, Heidelberg (2007)
Agarwal, S., Mierle, K., Others: ceres solver. (http://ceres-solver.org)
Boehler, W., Bordas Vicent, M., Marbs, A.: Investigating laser scanner accuracy. Int. Arch. Photogrammetry Remote Sens. Spat. Inf. Sci. 34, 696–701 (2003)
Acknowledgments
We thank Wolfgang Niehsen and his Team at Robert Bosch GmbH, Computer Vision Research Lab, Hildesheim, for supplying the test car, camera mount and tons of input regarding meaningful content of the scenes we recorded. We further thank Jens Taupadel, Jakob Knauer and Moritz Wandsleb at Universität Hannover for acquiring and processing the scans. Finally, we thank our lab members Karsten Krispin, Alexandro Sanchez-Bach, Ekaterina Melnik for their assistance in data processing, Florian Becker and Frank Lenzen for helpful discussions as well as AEON Verlag&Studio GmbH for the organization of all helpers and facilities.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Kondermann, D. et al. (2015). Stereo Ground Truth with Error Bars. In: Cremers, D., Reid, I., Saito, H., Yang, MH. (eds) Computer Vision -- ACCV 2014. ACCV 2014. Lecture Notes in Computer Science(), vol 9007. Springer, Cham. https://doi.org/10.1007/978-3-319-16814-2_39
Download citation
DOI: https://doi.org/10.1007/978-3-319-16814-2_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16813-5
Online ISBN: 978-3-319-16814-2
eBook Packages: Computer ScienceComputer Science (R0)