Abstract
Autonomous systems are generally equipped with multiple sensor (such as radar, ultrasonic, IMU (Inertial Measurement Units), cameras, and GPS) assembly. Under complex scenarios, control of unmanned systems in GPS denied environment that depends on a quick estimate of their current position in space using cameras. Cameras provide information similar to human vision with an advantage of small construction space at low cost. Thus, estimating a camera’s egomotion from an image sequence helps to overcome these practical difficulties of autonomous camera control. The main disadvantage of using cameras under dynamic environments includes unwanted movement and jittering in the captured data, which causes a consequence in embedded vision applications. In this paper, we described an algorithm of feature-based high frame rate egomotion estimation with gradient projection and Gabor wavelet transform, which is capable of computing real-time computer vision applications. Here, the reliable singularity points were extracted through gradient projection for reducing the processing time, and egomotion was derived by applying RANSAC. The simulation was carried out in OpenCV environment, and the results demonstrate the efficiency of the proposed technique.
This is a preview of subscription content, log in via an institution.
References
Wolf W, Ozer B, Lv, T (2002) Smart cameras as embedded systems. Computer 35:48–53 (Long. Beach. Calif)
Borenstein J, Everett HR, Feng L, Wehe D (1997) Mobile robot positioning: sensors and techniques. J Robot Syst 14:231–249
Zanni L (2006) An improved gradient projection-based decomposition technique for support vector machines. Comput Manag Sci 3:131–145
Jiang W, Shen, TZ, Zhang J, Hu Y, Wang XY (2008) Gabor wavelets for image processing. In: Proceeding-ISECS international colloquium on computer, communication control, and management CCCM 2008, vol 1, pp 110–114
Fischler MA, Bolles, RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24:381–395
Beauchemin SS, Barron JL (1995) The computation of optical flow. ACM Comput Surv 27:433–466
Spies H, Scharr H (2001) Accurate optical flow in noisy image sequences. In: Eighth IEEE international conference on computer vision 1, vol 1, pp 587–592
Rutkowski AJ, Miller MM, Quinn RD, Willis MA (2011) Egomotion estimation with optic flow and air velocity sensors. Biol Cybern 104:351–367
Raudies F, Neumann H (2009) An efficient linear method for the estimation of ego-motion from optical flow. In: Lecture notes in computer science (including subseries lecture notes artificial intelligence Lecture Notes Bioinformatics), vol 5748 LNCS, pp 11–20
Grabe V, Bulthoff HH, Robuffo Giordano P (2012) Robust optical-flow based self-motion estimation for a quadrotor UAV. In: IEEE international conference on intelligent robots and systems, pp 2153–2159
Dahmen H, Franz M, Krapp H (2001) Extracting egomotion from optic flow: limits of accuracy and neural matched filters. In: Motion vision, pp 143–168
Brooks MJ, Baumela L, Chojnacki W (1997) Egomotion from optical flow with an uncalibrated camera. In: Proceeding SPIE-international society for optics engineering, vol 3024, pp 220–228
Scaramuzza D, Fraundorfer F (2011) Visual odometry part II. IEEE Robot Autom Mag 18:80–92
Nister D, Bergen J (2004) Visual odometry. In: Proceedings of the 2004 IEEE computer society conference on computer vision pattern recognition, CVPR 2004
Black MJ, Anandan P A framework for the robust estimation of optical flow. In: IEEE international conference on computer vision, pp 231–236
Wildes RP (1993) On the qualitative structure of temporally visual motion fields, pp 844–849
Gupta NC, Kanal LN (1995) 3-D motion estimation from motion field. J Artif Intel 78:45–86
Szeliski R (2006) Image alignment and stitching: a tutorial. Found Trends® Comput. Graph Vis 2:1–104
Lowe DG (1999) Object recognition from local scale-invariant features. In: Proceedings of the seventh IEEE international conference on computer vision, vol 2, pp 1150–1157
Nister D (2004) An efficient solution to the five-point relative pose problem. IEEE Trans Pattern Anal Mach Intell 26:756–770
Pollefeys M, Nistér D, Frahm J-M (2008) Detailed real-time urban 3D reconstruction from video. Int J Comput Vis 78:1–43
Se S, Lowe D, Little J (2002) Global localization using distinctive visual features. In: Intelligent robots and systems, IEEE/RSJ, pp 226–231
Nister D (2003) Preemptive RANSAC for live structure and motion estimation, Proc Ninth IEEE Intl Conf on Comput Vis 1:199–206
Nister D (2004) Automatic passive recovery of 3D from images and video. In: 3D data processing, visualization and transmission. 3DPVT 2004. Proceedings. 2nd international symposium, pp 438–445
Bay H, Ess A, Tuytelaars T, Van Gool L (2008) Speeded-up robust features (SURF). Comput Vis Image Underst 110:346–359
Trajkovii M, Hedley M, Trajkovic M, Hedley M (1998) Fast corner detection. Image Vis Comput 16:75–87
Rublee E, Bradski G (2011) ORB—an efficient alternative to SIFT or SURF, In: International Conference on Computer Vision (ICCV), pp 2564–2571
Pradeep V (2010) Egomotion using assorted features, Intl J Comput Vis 98(2):202-216
Lourenco M, Baretto JP, Malti A (2010) Feature detection and matching in images with radial distortion. In: IEEE International Conference on Robotics and Automation, pp 1028–1034
Kobayashi T, Hidaka A, Kurita T (2008) Selection of histograms of oriented gradients features for pedestrian detection. In: Lecture notes in computer science (including subseries lecture notes artificial intelligence lecture notes bioinformatics), 4985 LNCS, pp 598–607
Chen Y, Yeh T (2009) A method for extraction and recognition of isolated license plate characters. J Comput Sci 5:1–10
An Y, Rasheed W, Park S, Park J (2011) Feature extraction through generalization of histogram refinement technique for local region-based object attributes. Int J Imaging Syst Technol 21:298–306
Jemaa YB, Khanfir S (2009) Automatic local Gabor features extraction for face recognition. Int J Comput Sci Inform Secur 3(1):1–10
Kamarainen JK, Kyrki V, Kälviäinen H (2006) Invariance properties of Gabor filter-based features—overview and applications. IEEE Trans Image Process 15:1088–1099
Lee TS (1996) Image representation using 2D Gabor wavelets. IEEE Trans Pattern Anal Mach Intell 18:959–971
Pang WM (2010) Towards fast gabor wavelet feature extraction for texture segmentation by filter approximation. In: Proceeding-9th IEEE/ACIS international conference on computer and information science ICIS 2010, pp 252–257
Nestares O (1998) Efficient spatial-domain implementation of a multiscale image representation based on Gabor functions. J Electron Imaging 7:166
Yang S-W, Wang C-C (2009) Multiple-model RANSAC for ego-motion estimation in highly dynamic environments. In: IEEE international conference on robotics and automation, pp 3531–3538
Hong S, Ye C (2014) A fast egomotion estimation method based on visual feature tracking and iterative closest point. In: IEEE 11th international conference on networking, sensing and control (ICNSC), pp 114–119
Del-Blanco CR, Jaureguizar F, Salgad L, García N (2008) Motion estimation through efficient matching of a reduced number of reliable singular points. In: Proceeding, vol 6811, pp 68110 N–68110 N–12
Soman KP, Ramanathan R (2016) Digital signal and image processing. pp 408–416
Wei C, Li Y, Li C Effective extraction of Gabor features. IEEE International Conference on Multimedia and Expo. pp 1503–1506
Daugman JG (1985) Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. J Opt Soc Am A 2:1160–1169
Amayeh G, Tavakkoli A, Bebis G (2009) Accurate and efficient computation of Gabor features in real-time applications. In: Lecture notes in computer science (including subseries lecture notes artificial intelligence lecture notes bioinformatics), vol 5875 LNCS, pp 243–252
Brown M, Lowe DG (2007) Automatic panoramic image stitching using invariant features. Int J Comput Vis 74:59–73
Wisetphanichkij S, Dejhan K (2005) Fast fourier transform technique and affine transform estimation-based high precision image registration method. GESTS Int Trans Comput Sci Eng 20:179–191
Acknowledgements
The authors are grateful to the Department of Science and Technology for the award of a DST-INSPIRE Fellowship to carry out this research work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sharmila Bakthavachalam, Damodaran, N. (2018). Egomotion Estimation Using Background Feature Point Matching in OpenCV Environment. In: Bhuvaneswari, M., Saxena, J. (eds) Intelligent and Efficient Electrical Systems. Lecture Notes in Electrical Engineering, vol 446. Springer, Singapore. https://doi.org/10.1007/978-981-10-4852-4_22
Download citation
DOI: https://doi.org/10.1007/978-981-10-4852-4_22
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-4851-7
Online ISBN: 978-981-10-4852-4
eBook Packages: EngineeringEngineering (R0)