Abstract
Rapid boost in the density of the pedestrians and vehicles on the roads have made the life of visually impaired people very difficult. In this direction, we present the design of a smart phone based cost-effective system to guide visually impaired people to walk safely on the roads by detecting obstacles in real-time scenarios. Monocular vision based method is used to capture the video and then frames are extracted out of it after removing the blurriness caused by the motion of camera. For each frame, a computationally simple approach based on the ground plane is proposed for detecting and removing the ground plane. After removing ground plane, features like Speeded-Up Robust Features (SURF) of the non-ground area are computed and compared with features of obstacles. An active contour model is used to segment the area of non-ground image whose SURF features are matched with obstacle features. This area is referred as Region of Interest (ROI). To check whether ROI belongs to an obstacle or not, Gray Level Co-occurrence matrix (GLCM) features are calculated and passed onto a classification model. Classification results show that this system is efficiently able to detect the obstacles that are known to the system in near real-time.
Similar content being viewed by others
References
T. Gandhi and M. M. Trivedi, “Pedestrian collision avoidance systems: A survey of computer vision based recent studies,” in Proc. 2006 IEEE Intelligent Transportation Systems Conference (ITSC’06) (Toronto, Sept. 2006), pp. 976–981.
I. Ulrich and I. R. Nourbakhsh, “Appearance-based obstacle detection with monocular color vision,” in Proc. AAAI 7th National Conf. on Artificial Intelligence and 12th Conf. on Innovative Applications of Artificial Intelligence (Austin, TX, July 2000), pp. 866–871.
S. Sivaraman and M. M. Trivedi, “A review of recent developments in vision-based vehicle detection,” in Proc. 2013 IEEE Intelligent Vehicle Symposium (IV), (Gold Coast, Australia, June 2013), pp. 310–315.
D. G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” Int. J. Comput. Vision 60 (2), 91–110 (2004).
H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool, “Speeded-up robust features (SURF),” Comput. Vision Image Understand. 110 (3), 346–359 (2008).
G. Beliakov, S. James, and L. Troiano, “Texture recognition by using GLCM and various aggregation functions,” in Proc. 2008 IEEE International Conference on Fuzzy Systems (IEEE World Congress on Computational Intelligence) (Hong Kong, Jun. 2008), pp. 1472–1476.
G. Zhao and M. Pietikainen, “Dynamic texture recognition using local binary patterns with an application to facial expressions,” IEEE Trans. Pattern Anal. Mach. Intellig. 29 (6), 915–928 (2007).
M. M. Ali, M. B. Fayek, and E. E. Hemayed, “Humaninspired features for natural scene classification,” Pattern Recogn. Lett. 34, (13), 1525–1530 (2013).
G.-H. Liu and J.-Y. Yang, “Content-based image retrieval using color difference histogram,” Pattern Recogn. 46 (1), 188–198 (2013).
J. Lim and W. Kim, “Detecting and tracking of multiple pedestrians using motion, color information and the AdaBoost algorithm,” Multimed. Tools Appl. 65 (1), 161–179 (2012).
K. van de Sande, T. Gevers, and C. Snoek, “Evaluating color descriptors for object and scene recognition,” IEEE Trans. Pattern Anal. Mach. Intellig. 32 (9), 1582–1596 (2010).
J. Zou, C.-C. Liu, Y. Zhang, and G.-F. Lu, “Object recognition using Gabor co-occurrence similarity,” Pattern Recogn. 46 (1), 434–448 (2013).
H. Wang, K. Yuan, W. Zou, and Y. Peng, “Real-time obstacle detection with a single camera,” in Proc. 2005 IEEE Int. Conf. on Industrial Technology (ICIT) (Hong Kong, Dec. 2005), pp. 92–96.
K. Yamaguchi, T. Kato, and Y. Ninomiya, “Moving obstacle detection using monocular vision,” in Proc. 2006 IEEE Intelligent Vehicles Symposium (Tokyo, June 2006), pp. 288–293.
B. Jia, R. Liu, and M. Zhu, “Real-time obstacle detection with motion features using monocular vision,” Visual Comput. 31 (3), 281–293 (2015).
G. Panahandeh, N. Mohammadiha, and M. Jansson, “Ground plane feature detection in mobile visionaided inertial navigation,” in Proc.2012 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS) (Vilamoura, Portugal, Oct. 2012), pp. 3607–3611.
M. Knorr, W. Niehsen, and C. Stiller, “Robust ground plane induced homography estimation for wide angle fisheye cameras,” in 2014 IEEE Intelligent Vehicle Symposium Proc. (Dearborn, MI, June 2014), pp. 1288–1293.
A. Datta, S. Dutta, S. K. Pal, R. Sen, and S. Mukhopadhyay, “Texture analysis of turned surface images using grey level co-occurrence technique,” Adv. Mater. Res. 365, 38–43 (2012).
K. R. Krishnan and S. Radhakrishnan, “Focal and diffused liver disease classification from ultrasound images based on isocontour segmentation,” IET Image Process. 9 (4), 261–270 (2015).
Z. Zhang, Y. Huang, C. Li, and Y. Kang, “Monocular vision simultaneous localization and mapping using SURF,” in Proc. 2008 7th World Congress on Intelligent Control and Automation (WCICA) (Chongqing, China, June 2008), IEEE, pp. 1651–1656.
Y. Pang, W. Li, Y. Yuan, and J. Pan, “Fully affine invariant SURF for image matching,” Neurocomputing 85, 6–10 (2012).
T. F. Chan and L. A. Vese, “Active contours without edges,” IEEE Trans. Image Process. 10 (2), 266–277 (2001).
R. M. Haralick, K. Shanmugam, and I. Dinstein, “Textural features for image classification,” IEEE Trans. Syst., Man Cybern. SMC-3 (6), 610–621 (1973).
L.-K. Soh and C. Tsatsoulis, “Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices,” IEEE Trans. Geosci. Remote Sens. 37 (2), 780–795 (1999).
M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, and I. H. Witten, “The WEKA data mining software: an update,” ACM SIGKDD Explorations Newsletters 11 (1), 10–18 (2009).
Caltech ETH Dataset. Available: http://www.vision.caltech.edu/Image_Datasets/CaltechPedestrians/datasets/ETH/
M. Enzweiler and D. M. Gavrila. “Monocular pedestrian detection: Survey and experiments,” IEEE Trans. Pattern Anal. Mach. Intellig. 31 (12), 2179–2195 (2009).
A. Ess, B. Leibe, K. Schindler, and L. van Gool, A mobile vision system for robust multi-person tracking, in Proc. 2008 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2008) (Anchorage, AK, USA, June 2008), pp. 1–8.
Author information
Authors and Affiliations
Corresponding author
Additional information
The article is published in the original.
Anish Jindal received the B. Tech. degree from Punjab Technical University in 2012 and M.E. degree from University Institute of Engineering and Technology, Panjab University in 2014, both in Computer Science Engineering. He has successfully qualified GATE, NET and JRF examinations held by IIT, UGC and CSIR respectively. His research interests include image processing, ad-hoc networking and data analytics. He is also the member of IEEE and ACM.
Naveen Aggarwal is actively working in the area of Computer Vision and Data Mining. He did his PhD from GGSIPU, Delhi in year 2011 and M. Tech. in Computer Science and Engineering from IIT, Kharagpur. Dr. Aggarwal has been awarded with Faculty Innovation award from the Infosys foundations. Different Effort Estimation Model developed by Dr. Aggarwal are appreciated and being used by Axede Corporation, USA and Birlasoft Corp. India. He has over 18 publications in International journals and 55 publications in international and national conferences. He has joined PU as Asstt. professor in Computer Science and Engineering at UIET in February 2005. Earlier, he has worked for three years from 2002 to 2005 in Punjab Engineering College, Chandigarh.
Savita Gupta received the B. Tech. degree from TITS, Bhiwani (Haryana), in 1992, M.E. degree from TIET, Patiala, Punjab, in 1998 both in computer science and engineering. She obtained her PhD degree from PTU, Jalandhar in 2007 in the field of ultrasound image processing. She has been in the teaching profession since 1992. Presently, she is working as professor in the Department of CSE, University Institute of Engineering and Technology, Panjab University, Chandigarh. Her research interests include image processing, image compression and denoising, and wavelet applications.
Rights and permissions
About this article
Cite this article
Jindal, A., Aggarwal, N. & Gupta, S. An Obstacle Detection Method for Visually Impaired Persons by Ground Plane Removal Using Speeded-Up Robust Features and Gray Level Co-Occurrence Matrix. Pattern Recognit. Image Anal. 28, 288–300 (2018). https://doi.org/10.1134/S1054661818020086
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661818020086