Abstract
Segmentation and delineation of road features from remotely sensed images find many applications including navigation. Road segmentation of mobile robots for autonomous navigation is further challenging because of illumination conditions of the scene varies as per the environment. The scene becomes more complicated in case of locations such as varying slope and unstructured or rural road conditions. We propose a novel technique called “Dual Segmentation” in which the image is pre-processed with modified RG chromacity based intensity normalization. The normalized image channels obtained are subjected to k-means clustering to find their cluster compactness. Based on the minimum cluster compactness one of the image channel is selected and Otsu segmentation is applied on it to obtain road segments. This segmented image is further processed with morphological operations to remove noise. Finally gray connected operation is applied to retain the single large road segment by removing many small unconnected regions. The outcome of the proposed Dual Segmentation technique gives pixel accuracy of about 99% with reference to ground truth images. The average execution time per image is 0.07 s when run on an Intel i5-M520 @ 2.40 GHz CPU.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wurm, K.M., Kümmerle, R., Stachniss, C., Burgard, W.: Improving robot navigation in structured outdoor environments by identifying vegetation from laser data. In: 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1217–1222, October 2009
Tan, J., Li, J., An, X., He, H.: Robust curb detection with fusion of 3D-lidar and camera data. Sensors (Basel, Switz.) 14, 9046–9073 (2014)
Guignard, M., Schild, M., Bederián, C., Wolovick, N., Vega, A.J.: Performance characterization of state-of-the-art deep learning workloads on an ibm “minsky” platform, January 2018
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision - ECCV 2018, vol. Ferrari, pp. 833–851. Springer International Publishing, Cham (2018)
Xu, W., Zhuang, Y., Hu, H., Zhao, Y.: Real-time road detection and description for robot navigation in an unstructured campus environment. In: Proceeding of the 11th World Congress on Intelligent Control and Automation, pp. 928–933, June 2014
Rotaru, C., Graf, T., Zhang, J.: Color image segmentation in HSI space forautomotive applications. J. Real-Time Image Process. 3(4), 311–322 (2008). https://doi.org/10.1007/s11554-008-0078-9
Rasmussen, C.: Combining laser range, color, and texture cues for autonomous road following. In: Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No. 02CH37292), vol. 4, pp. 4320–4325, May 2002
Kaushik, D., Suny, A.: Shadow detection and removal based on YCbCr color space. Smart Comput. Rev. 4, 02 (2014)
Lu, K., Li, J., An, X., He, H.: Vision sensor-based road detection for field robot navigation. Sensors 15, 29 594–29 617 (2015)
Alvarez, J.M., Lopez, A.M.: Road detection based on illuminant invariance. IEEE Trans. Intell. Transp. Syst. 12(1), 184–193 (2011)
He, Y., Wang, H., Zhang, B.: Color-based road detection in urban traffic scenes. IEEE Trans. Intell. Transp. Syst. 5(4), 309–318 (2004)
Kong, H., Audibert, J., Ponce, J.: General road detection from a single image. IEEE Trans. Image Process. 19(8), 2211–2220 (2010)
Alvarez, J.M., Lopez, A.M., Gevers, T., Lumbreras, F.: Combining priors, appearance, and context for road detection. IEEE Trans. Intell. Transp. Syst. 15(3), 1168–1178 (2014)
Falola, O., Osunmakinde, I., Bagula, A.: Supporting drivable region detection by minimising salient pixels generated through robot sensors, June 2019
Murou, W.: Image segmentation: a watershed transformation algorithm, January 2016
Chen, K.-H., Tsai, W.-H.: Vision-based autonomous land vehicle guidance in outdoor road environments using combined line and road following techniques. J. Robot. Syst. 14(10), 711–728 (1997)
Lyu, Y., Bai, L., Huang, X.: Real-time road segmentation using lidar data processing on an FPGA. In: 2018 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1–5, May 2018
Martinkauppi, J.B., Pietikäinen, M.: Facial skin colormodeling, pp. 113–135. Springer, New York (2005). https://doi.org/10.1007/0-387-27257-7_6
Gevers, T., Gijsenij, A., van de Weijer, J., Geusebroek, J.: Pixel-BasedPhotometric Invariance, ch. 4, pp. 47–68. John Wiley Sons, Ltd. (2012). https://doi.org/10.1002/9781118350089.ch4
Kanungo, T., et al.: An efficient k-means clustering algorithm: analysis and implementation. IEEE Trans. Pattern Anal. Mach. Intell. 24, 881–892 (2002)
Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9, 62–66 (1979)
Yousefi, J.: Image binarization using Otsu thresholding algorithm, May 2015
Anuar, K., Jambek, A., Sulaiman, N.: A study of image processing using morphological opening and closing processes. Int. J. Control Theory Appl. 9, 15–21 (2016)
Wang, Y., Bhattacharya, P.: Image analysis and segmentation using gray connected components. In: 1996 IEEE International Conference on Systems, Man and Cybernetics. Information Intelligence and Systems (Cat. No. 96CH35929), vol. 1, pp. 444–449, October 1996
Zhang, Y.J.: A review of recent evaluation methods for image segmentation. In: Proceedings of the Sixth International Symposium on Signal Processing and its Applications (Cat. No. 01EX467), vol. 1, pp. 148–151, August 2001
Taha, A.A., Hanbury, A.: Metrics for evaluating 3d medical image segmentation: analysis, selection, and tool. BMC Med. Imaging 15(1), 1–28 (2015)
Acknowledgment
The authors would like to thank Director, CAIR and Shri V C Ravi for helping us in procuring resources and publishing these results.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kumar, K.R., Savitha, D.K., Panigrahi, N. (2021). Dual Segmentation Technique for Road Extraction on Unstructured Roads for Autonomous Mobile Robots. In: Singh, S.K., Roy, P., Raman, B., Nagabhushan, P. (eds) Computer Vision and Image Processing. CVIP 2020. Communications in Computer and Information Science, vol 1378. Springer, Singapore. https://doi.org/10.1007/978-981-16-1103-2_40
Download citation
DOI: https://doi.org/10.1007/978-981-16-1103-2_40
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-1102-5
Online ISBN: 978-981-16-1103-2
eBook Packages: Computer ScienceComputer Science (R0)