Abstract
Given the large randomness and the low color information utilization rate, a region growing algorithm based on super pixel is proposed. It can also eliminate the uncertainty of the initial setting parameters of super pixel segmentation. The method in this paper was proposed by three steps. In the first step, set the most suitable number of super pixel by the lab feature histogram of the image. In the second step, segment the original image by the SLIC super pixel segmentation algorithm. In the third step, merge super pixel blocks by region growing algorithm and then obtain the target unstructured road. This paper uses Jaccard coefficients to evaluate the segmentation accuracy. In a warehouse environment, this method is more accurate than traditional region growing algorithm and normalized segmentation method based on SLIC super pixel.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang, J., Luo, Y., Qian, W.: Road segmentation recognition of color image region growing algorithm. Autom. Instrum. 166(5), 158–159 (2014). https://doi.org/10.3969/j.issn.1001-9227.2014.05.052
Hu, X., Sun, M., Su, X.: Detection method of completely unstructured road in pseudo color space. J. Image Graph. 17(2), 203–208 (2012)
Chen, Q., Jing, Y., Chen, J.: Unstructured road detection based on adaptive template. J. Southeast Univ. (Nat. Sci. Edn.) 37(6), 1102–1107 (2007)
Wang, H., Cai, Y., Jia, Y.: Scene adaptive road segmentation algorithm based on deep convolutional neural network. J. Electron. Inf. Technol. 39(2), 263–269 (2017)
Wang, X., Meng, F., Lv, G.: Unstructured road recognition based on PCA-SVM criterion to improve regional growth. Comput. Appl. 37(6), 1782–1786 (2017). https://doi.org/10.11772/j.issn.1001-9081.2017.06.1782
Li, Y., Fu, X., Xue, Q.: Unstructured road segmentation method based on RGB entropy. Comput. Eng. Des. 38(06), 1570–1574 (2017). https://doi.org/10.16208/j.issn1000-7024.2017.06.031
Qi, N., Yang, X., Li, C.: Unstructured road detection via combining the model-based and feature-based methods. IET Intell. Transp. Syst. 13(10), 1533–1544 (2019). https://doi.org/10.1049/iet-its.2018.5576
Khan, J., Adham, I.R., Bhu Iyan, S.: A customized gabor filter for unsupervised color image segmentation. Image Vis. Comput. 27(4), 489–501 (2009). https://doi.org/10.1016/j.imavis.2008.07.001
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Ssstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell., 2274-2282 (2012). https://doi.org/10.1109/TPAMI.2012.120
Achanta, R., Smith, K., Lucchi, A., Fua, P., Susstrunk, S.: Technical Report, EPFL, Technical report 149300: SLIC Superpixels (2010)
Yu, W., Wang, Y., Liu, H., He, J.: Superpixel-based CFAR target detection for high-resolution SAR images. IEEE Geosci. Remote Sens. Lett. 13(5), 730–734 (2016). https://doi.org/10.1109/LGRS.2016.2540809
Liao, M., Li, Y., Zhao, Y.: A new image superpixel segmentation method. J. Electron. Inf. Technol. 42(2), 364–370 (2020). https://doi.org/10.11999/JEIT190111
Gong, B., Lu, L., Cao, X.: Unstructured road segmentation based on gray features. Comput. Knowl. Technol. 11(26), 147–149 (2015). https://doi.org/10.14004/j.cnki.ckt.2015.2986
Zhang, Y.: Research on normalized segmentation method based on SLIC Superpixels (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, T., Zhong, X., Zhang, L. (2021). Unstructured Road Segmentation Method Based on Super Pixel and Region Growing Algorithm. In: Jia, Y., Zhang, W., Fu, Y. (eds) Proceedings of 2020 Chinese Intelligent Systems Conference. CISC 2020. Lecture Notes in Electrical Engineering, vol 706. Springer, Singapore. https://doi.org/10.1007/978-981-15-8458-9_44
Download citation
DOI: https://doi.org/10.1007/978-981-15-8458-9_44
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-8457-2
Online ISBN: 978-981-15-8458-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)