Pipeline Scene Reconstruction Based on Image Mosaicing

Robots should be able to perceive the surroundings in the complicated and unknown environment before carrying out further navigation. Consequently, environmental reconstruction is the premise for the robot autonomous operations. In this paper, a pipeline scene reconstruction method based on image mosaicing is proposed for cylindrical pipeline environment. With a wide-angle camera, the image sequence of the pipeline environment is captured. In order to obtain intuitional environmental information around the pipeline, an unwrapped model is proposed to unfold the distorted raw image to corrected flat surface image. By utilizing ORB (Oriented FAST and Rotated BRIEF) and weighted smoothing blending algorithm, image mosaicing with sequence frames are performed to realize scene reconstruction. The experimental results demonstrate that the proposed algorithm can achieve seamless stitching of pipeline image, and the number of keypoints is prominently decreased in comparison to that of FAST operator, while the quality of keypoints is improved. Compared with the classical SIFT and SURF operator, the time-consuming of the algorithm is improved about 2.5 times, which is more suitable for real-time environmental reconstruction.

[1]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[2]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[3]  Ting-En Tseng,et al.  Real-time people detection and tracking for indoor surveillance using multiple top-view depth cameras , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  P. Ramana Reddy,et al.  A critical review on Image Mosaicing , 2016, 2016 International Conference on Computer Communication and Informatics (ICCCI).

[5]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.

[6]  Hiroshi Kawasaki,et al.  Super resolution of fisheye images captured by on-vehicle camera for visibility support , 2015, 2015 IEEE International Conference on Vehicular Electronics and Safety (ICVES).

[7]  Edward Jones,et al.  Equidistant Fish-Eye Calibration and Rectification by Vanishing Point Extraction , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Paul A. Viola,et al.  Alignment by Maximization of Mutual Information , 1997, International Journal of Computer Vision.

[9]  Mohammad H. Mahoor,et al.  Fast image blending using watersheds and graph cuts , 2009, Image Vis. Comput..

[10]  Cao Zuo-liang,et al.  Omni-Directional Vision Parameter Calibration and Rectification Based on Fish-Eye Lens , 2011 .

[11]  Juho Kannala,et al.  A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[13]  Mohammad H. Mahoor,et al.  Fast image blending using watersheds and graph cuts , 2009, Image Vis. Comput..

[14]  M. Tech,et al.  A Survey on Image Mosaicing Techniques , 2013 .

[15]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[16]  M M Moghaddam,et al.  ON THE IN-PIPE INSPECTION ROBOTS TRAVERSING THROUGH ELBOWS , 2015 .