Issue |
MATEC Web Conf.
Volume 139, 2017
2017 3rd International Conference on Mechanical, Electronic and Information Technology Engineering (ICMITE 2017)
|
|
---|---|---|
Article Number | 00042 | |
Number of page(s) | 6 | |
DOI | https://doi.org/10.1051/matecconf/201713900042 | |
Published online | 05 December 2017 |
Study on Autonomous Obstacle Avoidance Based On Guidance
1 School of Mechanical Engineering, Southwest Jiaotong University, No.999 Xi’an Road, Chengdu, China
2 School of Information Science and Technology, Southwest Jiaotong University, No.999 Xi’an Road, Chengdu, China
* Corresponding author: kevinhoo@my.swjtu.edu.cn
DJI Guidance is an entirely new visual sensor navigation system, which has a function of real-time transmission of the depth of field images and other data. It is a robust optical sensing platform which significantly promotes the development of unmanned aerial vehicle (hereinafter referred to as UAV). On this basis, we have further studied and developed Guidance in application to the field of UAVs to also cut a striking figure, by applying the threshold and binaryzation to the single frame of a static image generated from Guidance. Utilizing OpenCV’s contour detection algorithm, we find all the closed contour information and re-plan the feasible region. Also, we specially re-project the depth information to achieve three-dimensional reconstruction of the image. Then combining the re-planed feasible domain with three-dimensional reconstruction, we can perform real-time obstacle avoidance and mapping. The results demonstrate that our improvement can efficiently complete the obstacle avoidance and real-time mapping in the specific circumstances.
© The Authors, published by EDP Sciences, 2017
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (http://creativecommons.org/licenses/by/4.0/).
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.