Abstract：The existing visual obstacle localization algorithms can't locate the obstacles moving out of sight, and there are noises in localization. For these problems, an obstacle memory localization and denoising algorithm based on binocular ORB-SLAM (simultaneous localization and mapping system based on the oriented BRIEF feature) is proposed. Based on the detection results of the obstacle, the algorithm projects the obstacle points to the ground grid through the SLAM (simultaneous localization and mapping) map frame-by-frame firstly, calculates the number of standard obstacle projection points in the grid, and removes the localization noises by the Otsu method. So, the accurate obstacle memory position is obtained finally. The experimental results show that the obstacle can still be localized after moving out of sight, the denoising success rate of a single obstacle is 95.3%, and the average processing speed reaches 8 key frames per second. It is proved that the algorithm can realize the obstacle memory localization, and has good denoising performance and real-time performance.
[1] 王丽丽.电子导盲仪的发展现状与趋势[J].甘肃科技,2012,28(3):99-100.Wang L L. The present situation and tendency of electronic guide instrument[J]. Gansu Science and Technology, 2012, 28(3):99-100.
[2] Fernandes H, Costa P, Filipe V, et al. Stereo vision in blind navigation assistance[C]//World Automation Congress. Piscataway, USA:IEEE, 2010:6pp.
[3] Wise E, Li B H, Gallagher T, et al. Indoor navigation for the blind and vision impaired:Where are we and where are we going?[C]//International Conference on Indoor Positioning and Indoor Navigation. Piscataway, USA:IEEE, 2012:7pp.
[4] Shang W Q, Jiang W, Chu J. A machine vision based navigation system for the blind[C]//IEEE International Conference on Computer Science and Automation Engineering. Piscataway, USA:IEEE, 2011:81-85.
[5] Michels J, Saxena A, Ng A Y. High speed obstacle avoidance using monocular vision and reinforcement learning[C]//22nd International Conference on Machine Learning. New York, USA:ACM, 2005:593-600.
[6] Lin C H, Jiang S Y, Pu Y J, et al. Robust ground plane detection for obstacle avoidance of mobile robots using a monocular camera[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE, 2010:3706-3711.
[7] Lee Y H, Medioni G. Wearable RGBD indoor navigation system for the blind[C]//13th European Conference on Computer Vision. Berlin, Germany:Springer, 2015:493-508.
[8] Yue H S, Chen W H, Wu X M, et al. Kinect based real time obstacle detection for legged robots in complex environments[C]//8th IEEE Conference on Industrial Electronics and Applications. Piscataway, USA:IEEE, 2013:205-210.
[9] Zhang K H, Wang S P, Yin X H, et al. Blind navigation aid system with Kinect sensor in complex indoor environments[J]. Optics and Precision Engineering, 2015, 23(8):2419-2427.
[10] Sabe K, Fukuchi M, Gutmann J S, et al. Obstacle avoidance and path planning for humanoid robots using stereo vision[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2004:592-597.
[11] Nalpantidis L, Kostavelis I, Gasteratos A. Stereovision-based algorithm for obstacle avoidance[C]//2nd International Conference on Intelligent Robotics and Applications. Berlin, Germany:Springer, 2009:195-204.
[12] Kumar S. Binocular stereo vision based obstacle avoidance algorithm for autonomous mobile robots[C]//IEEE International Advance Computing Conference. Piscataway, USA:IEEE, 2009:254-259.
[13] Mur-Artal R, Tardos J D. ORB-SLAM2:An open-source SLAM system for monocular, stereo, and RGB-D cameras[J]. IEEE Transactions on Robotics:doi:10.1109/TRO.2017.2705103.
[14] Feng J X, Wei T. Wearable guide system for obstacle avoidance based on stereo computer vision[C]//6th International Conference on Manufacturing Science and Engineering. Paris, France:Atlantis Press, 2016:1811-1817.
[15] Otsu N. Threshold selection method from gray-level histo-grams[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1):62-66.
