Abstract
A map that can fully express environment is of great significance for intelligent robots. Traditional grid maps such as occupancy grid map can only express the simple “free or occupied”. So, it is difficult to meet the demand of tasks in a complex environment. This paper proposes a framework called Semantic Evidential Grid Map (SEGM) for generating a semantic evidential grid map based on Dempster-Shafer theory of evidence, which can combine laser scanner and stereo camera to make a map more accurate in expressing the environment without losing any details. As a result, this work allows a better handling of uncertainty information and provides more detailed semantic representations. It will be very helpful for intelligent robots or autonomous vehicles to execute tasks such as localization, perception and navigation in a complex environment. The experimental results on the KITTI CITY dataset show that the proposed method can provide a more detailed and accurate map representation than the traditional methods.
J.Li—Student
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Nuss, D., Reuter, S., Thom, M., et al.: A random finite set approach for dynamic occupancy grid maps with real-time application [J]. Int. J. Robot. Res. 37(8), 841–866 (2018)
Singh, R., Nagla, K.S.: Sonar sensor model for the precision measurement to generate robust occupancy grid map [J]. MAPAN 34(2), 239–257 (2019)
Shafer, G.: A Mathematical Theory of Evidence [M]. Princeton university press, New Jersey (1976)
Moras, J., Dezert, J., Pannetier, B.: Grid occupancy estimation for environment perception based on belief functions and PCR6 [C]. In: Signal Processing, Sensor/Information Fusion, and Target Recognition XXIV. International Society for Optics and Photonics, vol. 9474, p. 94740P (2015)
Mullane, J., Adams, M.D., Wijesoma, W.S.: Evidential versus Bayesian estimation for radar map building [C]. In: 2006 9th International Conference on Control, Automation, Robotics and Vision, pp. 1–8. IEEE (2006)
Yu, C., Cherfaoui, V., Bonnifait, P.: Evidential occupancy grid mapping with stereo-vision [C]. In: 2015 IEEE Intelligent Vehicles Symposium (IV), pp. 712–717. IEEE (2015)
Valente, M., Joly, C., de La Fortelle, A.: Fusing laser scanner and stereo camera in evidential grid maps [C]. In: 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV), pp. 990–997. IEEE (2018)
Valente, M., Joly, C., de La Fortelle, A.: Evidential SLAM fusing 2D laser scanner and stereo camera [J]. Unmanned Syst. 7(03), 149–159 (2019)
Moras, J., Cherfaoui, V., Bonnifait, P.: Moving objects detection by conflict analysis in evidential grids [C]. In: 2011 IEEE Intelligent Vehicles Symposium (IV), pp. 1122–1127. IEEE (2011)
Kurdej, M., Moras, J., Cherfaoui, V., et al.: Map-aided evidential grids for driving scene understanding [J]. IEEE Intell. Trans. Syst. Mag. 7(1), 30–41 (2015)
Trehard, G., Pollard, E., Bradai, B., et al.: On line mapping and global positioning for autonomous driving in urban environment based on evidential SLAM [C]. In: 2015 IEEE Intelligent Vehicles Symposium (IV), pp. 814–819 IEEE (2015)
Ran, Z.: Research on fast and low power binocular parallax estimation method [D]. University of Science and Technology Beijing (2020)
Zhu, Y., Sapra, K., Reda, F.A., et al.: Improving semantic segmentation via video propagation and label relaxation [C]. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8856–8865 (2019)
Perrollaz, M., Yoder, J.D., Spalanzani, A., et al.: Using the disparity space to compute occupancy grids from stereo-vision [C]. In: 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 2721–2726. IEEE (2010)
Jousselme, A.L., Grenier, D., Bossé, É.: A new distance between two bodies of evidence [J]. Inform. Fusion 2(2), 91–101 (2001)
Mur-Artal, R., Tardós, J.D.: Orb-slam2: an open-source slam system for monocular, stereo, and rgb-d cameras [J]. IEEE Trans. Robot. 33(5), 1255–1262 (2017)
Yager, R.R.: Entropy and specificity in a mathematical theory of evidence [J]. Int. J. Gen Syst 9(4), 249–260 (1983)
Acknowledgment
This work is supported by the National Natural Science Foundation of China (Grant No. 61973029).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, J., Li, H., Zeng, H. (2020). SEGM: A Novel Semantic Evidential Grid Map by Fusing Multiple Sensors. In: Peng, Y., et al. Pattern Recognition and Computer Vision. PRCV 2020. Lecture Notes in Computer Science(), vol 12305. Springer, Cham. https://doi.org/10.1007/978-3-030-60633-6_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-60633-6_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60632-9
Online ISBN: 978-3-030-60633-6
eBook Packages: Computer ScienceComputer Science (R0)