Ground Obstacle Detection Technology Based on Fusion of RGB-D and Inertial Sensors

被引：0
作者：
He J. [1 ,2 ]
Liu X. [1 ]
机构：
[1] Faculty of Information Technology, Beijing University of Technology, Beijing
[2] Beijing Engineering Research Center for IOT Software and Systems, Beijing
来源：
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics | 2022年 / 34卷 / 02期
关键词：
Depth map; Inertial sensors; Obstacle detection; Region of interest; Visually impaired person assistance;
D O I：
10.3724/SP.J.1089.2022.18870
中图分类号：
学科分类号：
摘要：
Aiming at the real-time detection of ground obstacles in the passable area for the visually impaired, a ground ob-stacle detection technology based on the fusion of RGB-D and inertial sensor is proposed. Firstly, the spatial model of the ground obstacle is established, and the inertial sensor parameters are fused to calculate the camera inclination to correct the world coordinates of the ground obstacle. Secondly, according to the actual scenes and needs of the visually impaired, the remote detection pixels in the depth image are removed by threshold segmen-tation algorithm, and the depth map is divided into 4 regions, and the dynamic division of ROI is realized by fus-ing inertial sensor data. Finally, an obstacle detection algorithm is designed by improved RANSAC algorithm based on the growth of ground area algorithm, and collected real data for experimental verification. The experi-mental results show that the accuracy and recall rates of the proposed technology reach 90.87% and 89.33%, and better than the existing detection algorithms in the time efficiency of execution, which meets the real-time re-quirements of the algorithm for the visually impaired. © 2022, Beijing China Science Journal Publishing Co. Ltd. All right reserved.
引用
收藏
页码：254 / 263
页数：9
相关论文
共 27 条
  • [1] Xu S C, Yang C Y, Ge W H, Et al., Virtual PAVING: rendering a smooth path for people with visual impairment through vibrotactile and audio feedback, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 4, 3, (2020)
  • [2] Wei Tong, Zhou Yinhe, Blind sidewalk image location based on machine learning recognition and marked watershed segmentation, Optics and Precision Engineering, 27, 1, pp. 201-210, (2019)
  • [3] Jiao Yang, Gong Jiangtao, Shi Yuanchun, Et al., The research on interactive experiences of graphical tactile displays for the visually impaired, Journal of Computer-Aided Design & Computer Graphics, 28, 9, pp. 1571-1576, (2016)
  • [4] Chen L, Yang J, Kong H., Lidar-histogram for fast road and obstacle detection, Proceedings of the IEEE International Conference on Robotics and Automation, pp. 1343-1348, (2017)
  • [5] Petsiuk A L, Pearce J M., Low-cost open source ultrasound-sensing based navigational support for the visually impaired, Sensors, 19, 17, (2019)
  • [6] Pham H H, Le T L, Vuillerme N., Real-time obstacle detection system in indoor environment for the visually impaired using Microsoft Kinect sensor, Journal of Sensors, 2016, (2016)
  • [7] Ghani M F A, Sahari K S M., Detecting negative obstacle using Kinect sensor, International Journal of Advanced Robotic Systems, 14, 3, (2017)
  • [8] Lee T J, Yi D H, Cho D I., A monocular vision sensor-based obstacle detection algorithm for autonomous robots, Sensors, 16, 3, (2016)
  • [9] Jiang B, Yang J C, Lv Z H, Et al., Wearable vision assistance system based on binocular sensors for visually impaired users, IEEE Internet of Things Journal, 6, 2, pp. 1375-1383, (2018)
  • [10] Wang Zheng, Zhao Xiao, She Hongjie, Et al., Obstacle detection and obstacle avoidance of AGV based on binocular vision, Computer Integrated Manufacturing Systems, 24, 2, pp. 400-409, (2018)
123