Abstract
Car pose estimation is an essential part of different applications, including traffic surveillance, Augmented Reality (AR) guides or inductive charging assistance systems. For many systems, the accuracy of the determined pose is important. When displaying AR guides, a small estimation error can result in a different visualization, which will be directly visible to the user. Inductive charging assistance systems have to guide the driver as precise as possible, as small deviations in the alignment of the charging coils can decrease charging efficiency significantly. For accurate pose estimation, matches between image coordinates and 3d real-world points have to be determined. Since wheels are a common feature of cars, we use the wheelbase and rim radius to compute those real-world points. The matching image coordinates are obtained by three different approaches, namely the circular Hough-Transform, ellipse-detection and a neural network. To evaluate the presented algorithms, we perform different experiments: First, we compare their accuracy and time performance regarding wheel-detection in a subset of the images of The Comprehensive Cars (CompCars) dataset [37]. Second, we capture images of a car at known positions, and run the algorithms on these images to estimate the pose of the car. Our experiments show that the neural network based approach is the best in terms of accuracy and speed. However, if training of a neural network is not feasible, both other approaches are accurate alternatives.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Achler, O., Trivedi, M.M.: Camera based vehicle detection, tracking, and wheel baseline estimation approach. In: ITSC (2004)
Achler, O., Trivedi, M.M.: Vehicle wheel detector using 2d filter banks. In: IV (2004)
Barrois, B., Hristova, S., Wohler, C., Kummert, F., Hermes, C.: 3d pose estimation of vehicles using a stereo camera. In: IV (2009)
Bay, H., Tuytelaars, T., Van Gool, L.: Surf: Speeded up robust features. In: ECCV (2006)
Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection (2020)
Canny, J.: A Computational Approach to Edge Detection. TPAMI (1986)
Collins, T., Bartoli, A.: Infinitesimal plane-based pose estimation. IJCV (2014)
Davies, E.: A modified hough scheme for general circle location. Pattern Recogn. Lett. 7, 37–43 (1988)
Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: CARLA: an open urban driving simulator. In: CoRL (2017)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. IJCV (2010)
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: CVPR (2012)
Grigoryev, A., Bocharov, D., Terekhin, A., Nikolaev, D.: Vision-based vehicle wheel detector and axle counter. In: ECMS (2015)
Hesch, J.A., Roumeliotis, S.I.: A direct least-squares (dls) method for pnp. In: ICCV (2011)
Hinterstoisser, S., et al.: Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes. In: ACCV (2013)
Hu, Y., Hugonot, J., Fua, P., Salzmann, M.: Segmentation-driven 6d object pose estimation. In: CVPR (2019)
Hutter, M., Brewer, N.: Matching 2-d ellipses to 3-d circles with application to vehicle pose identification. In: IVCNZ (2009)
Hödlmoser, M., Micusik, B., Liu, M., Pollefeys, M., Kampel, M.: Classification and pose estimation of vehicles in videos by 3d modeling within discrete-continuous optimization. In: 3DIMPVT (2012)
Illingworth, J., Kittler, J.: The adaptive hough transform. TPAMI (1987)
Kaempchen, N., Franke, U., Ott, R.: Stereo vision based pose estimation of parking lots using 3d vehicle models. In: IV (2002)
Ke, T., Roumeliotis, S.I.: An efficient algebraic solution to the perspective-three-point problem. In: CVPR (2017)
Laan, C.: Real-time 3D car pose estimation trained on synthetic data (2019). https://labs.laan.com/blog/real-time-3d-car-pose-estimation-trained-on-synthetic-data.html. Accessed 16 Feb 2021
Lehrstuhl für Internationales Automobilmanagement, Universität Duisburg-Essen: Taxiladekonzept für Elektrotaxis im öffentlichen Raum. https://talako.uni-due.de/. Accessed 25 Jan 2021
Lepetit, V., Moreno-Noguer, F., Fua, P.: Epnp: an accurate o(n) solution to the PNP problem. IJCV (2009)
Lin, T.Y., et al.: Microsoft coco: common objects in context. In: ECCV (2014)
Lu, C., Xia, S., Shao, M., Fu, Y.: Arc-support line segments revisited: an efficient high-quality ellipse detection. IEEE Trans. Image Process. 29, 768–781 (2020)
Nilsson, J., Fredriksson, J., Ödblom, A.C.E.: Reliable vehicle pose estimation using vision and a single-track model. T-ITS (2014)
Peng, S., Liu, Y., Huang, Q., Zhou, X., Bao, H.: Pvnet: pixel-wise voting network for 6dof pose estimation. In: CVPR (2019)
Reddy, N.D., Vo, M., Narasimhan, S.G.: Occlusion-net: 2d/3d occluded keypoint localization using graph networks. In: CVPR (2019)
Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement (2018)
Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: Orb: an efficient alternative to sift or surf. In: ICCV (2011)
Shahbaz Nejad, B., Roch, P., Handte, M., Marrón, P.J.: A driver guidance system to support the stationary wireless charging of electric vehicles. In: Advances in Visual Computing (2020)
Terzakis, G., Lourakis, M.: A consistently fast and globally optimal solution to the perspective-n-point problem. In: ECCV (2020)
Vinoharan, V., Ramanan, A., Kodituwakku, S.R.: A wheel-based side-view car detection using snake algorithm. In: ICIAfS (2012)
Welch, G., Bishop, G.: An introduction to the kalman filter (1997)
Gao, X.-S., Hou, X.-R., Tang, J.: Complete solution classification for the perspective-three-point problem. TPAMI, Hang-Fei Cheng (2003)
Xu, G., Su, J., Pan, H., Zhang, D.: A novel method for wheel rim recognition. In: ISECS (2008)
Yang, L., Luo, P., Loy, C.C., Tang, X.: A large-scale car dataset for fine-grained categorization and verification. In: CVPR (2015)
Zakharov, S., Shugurov, I., Ilic, S.: Dpod: 6d pose object detector and refiner. In: ICCV (2019)
Zensors: Car Pose Net (2019). https://www.zensors.com/car-pose/. Accessed 16 Feb 2021
Zivkovic, Z.: Improved adaptive gaussian mixture model for background subtraction. In: CVPR (2004)
Zivkovic, Z., van der Heijden, F.: Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recognition Letters (2006)
Acknowledgment
This research is funded by the Bundesministerium für Wirtschaft und Energie as part of the TALAKO project [22] (grant number 01MZ19002A).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Roch, P., Shahbaz Nejad, B., Handte, M., Marrón, P.J. (2021). Car Pose Estimation Through Wheel Detection. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2021. Lecture Notes in Computer Science(), vol 13017. Springer, Cham. https://doi.org/10.1007/978-3-030-90439-5_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-90439-5_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-90438-8
Online ISBN: 978-3-030-90439-5
eBook Packages: Computer ScienceComputer Science (R0)