Abstract
The fisheye camera can get rich information, and the fisheye camera has a lower installation cost. Therefore, it has an irreplaceable role in the assisted driving system. This paper proposes a detection method based on the fisheye camera. Firstly, a method of feature block filtering based on gradient maxima is proposed, which makes it possible to distribute the features as much as possible on the outer and inner edges of the obstacle and on the edge of the texture, while limiting the number of selected features. Much of the integrity of the obstacle area is preserved. The feature block classes are then clustered to obtain a complete obstacle region. Compared with the current popular moving target detection methods, the proposed algorithm can preserve the integrity of the obstacle area more effectively, and can effectively reduce the feature matching error rate. Moreover, the method can effectively judge the relative distance between the obstacle and the vehicle. Change the situation to detect proximity to obstacles. Experiments show that the proposed method is effective in many scenarios and has stronger accuracy and robustness.
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
Wei, Z., Ji, X., Feng, Y.: A Moving Object Detection Method Based on Self-Adaptive Updating of Background Acta Electronica Sinica (2005)
Lai, F.: Research on background motion compensation algorithm in dynamic background. Mod. Comput. (2018)
Lucas, B.D.: Generalized Image Matching by the Method of Difference. Carnegie Mellon University (1985)
Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. Int. J. Comput. Vis. 1(4), 321–331 (1988)
Yu, Z., Jain, A.K., Dubuissonjolly, M.P.: Object tracking using deformable templates. IEEE Trans. Pattern Anal. Mach. Intell. (2000)
Xia, H., Hong, W., An, X.: Research on object recognition based on feature points. J. Jilin Univ. (Information Science Edition) (2017)
Zhang, Y., Lou, L., Liang, S.: Research on moving object detection technology based on improved optical flow algorithm. Intell. Comput. Appl. (2018)
Huang, S., Tao, L., Zhang, T.: An improved algorithm of moving object detection based on optical flow. J. Huazhong Univ. Sci. Technol. (Natural Science Edition) (2005)
Schueler, K., Raaijmakers, M., Neumaier, S., et al.: Detecting Parallel Moving Vehicles with Monocular Omnidirectional Side Cameras. Intelligent Vehicles Symposium. IEEE, Piscataway (2013)
Fan, J., Gao, Y., Wu, Z. et al.: Research of moving target detection method on moving camera. Electron. Meas. Technol. (2018)
Luo, X., Wang, P., Li, S. et al.: Dynamic target detection method in motor vehicle assisted driving system. Comput. Eng. (2018)
Caraffi, C., Vojir, T., Trefny J., Sochman J., Matas J.: A system for real-time detection and tracking of vehicles from a single carmounted camera. IEEE (2012)
Ke, Q., Kanade, T.: Transforming camera geometry to a virtual downward-looking camera: robust ego-motion estimation and groundlayer detection. IEEE (2003)
Zhang, C., Ren, X.: Feature point based object detection method. Telecom World (2017)
Kannala, J., Brandt, S.S.: A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses. IEEE Trans. 28(8), 1335–1340 (2006)
Acknowledgements
This work is supported by research on the National Natural Science Foundation of China (61702247); The Application of Big Data Technology in Student Innovation and Entrepreneurship Ability Analysis (JG18DA013).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Shi, Y.P., Wei, H.P., Yu, H.F. (2020). Approaching Obstacle Detection by a Vehicle Fisheye Camera. In: Kountchev, R., Patnaik, S., Shi, J., Favorskaya, M. (eds) Advances in 3D Image and Graphics Representation, Analysis, Computing and Information Technology. Smart Innovation, Systems and Technologies, vol 179. Springer, Singapore. https://doi.org/10.1007/978-981-15-3863-6_46
Download citation
DOI: https://doi.org/10.1007/978-981-15-3863-6_46
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-3862-9
Online ISBN: 978-981-15-3863-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)