1. NCCU Academic Hub
  2. Publications
  3. College of Informatics
  4. Proceedings
  5. Item

Publications-Proceedings

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 Real-Time Vision-Based River Detection and Lateral Shot Following for Autonomous UAVs
作者 劉吉軒
Jyi-Shane Liu
Huang, Yenting
Lee, Gongyi
Soong, Rutai
貢獻者 資科系
關鍵詞 Rivers ; Image segmentation ; Unmanned aerial vehicles ; Navigation ; Inspection ; Task analysis ; Image edge detection
日期 2020-09
上傳時間 4-Jun-2021 14:50:15 (UTC+8)
摘要 Most existing autonomous UAV inspection tasks focus on environment surroundings and facilities. The UAV often navigates above the inspected target and conducts inspection with the camera aiming downward on the target. However, in some scenarios, it is risky to allow UAVs to navigate above the inspected target. For example, when patrolling a river, the UAV may risk falling into the river. Similar risks also exist for scenarios such as railways and power lines. This research proposes a lateral shot following approach for UAVs to follow the river laterally while collecting image data with a front view camera. The proposed approach has been evaluated with different segments of river in real world environments. The experiments include two types of following method and two types of viewpoint to suit different task needs. Results show that our deep neural network can extract the river masks in real-time with high accuracy. With adaptive steering adjustments, the UAV can achieve accurate and robust following when handling geographical change of river segments. Performance comparison between human operators and our developed autonomous system shows that better following accuracy and consistency can be achieved by our autonomous system.
關聯 Proceedings of the 2020 IEEE International Conference on Real-time Computing and Robotics, IEEE
資料類型 conference
DOI https://doi.org/10.1109/RCAR49640.2020.9303263
dc.contributor 資科系
dc.creator (作者) 劉吉軒
dc.creator (作者) Jyi-Shane Liu
dc.creator (作者) Huang, Yenting
dc.creator (作者) Lee, Gongyi
dc.creator (作者) Soong, Rutai
dc.date (日期) 2020-09
dc.date.accessioned 4-Jun-2021 14:50:15 (UTC+8)-
dc.date.available 4-Jun-2021 14:50:15 (UTC+8)-
dc.date.issued (上傳時間) 4-Jun-2021 14:50:15 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/135538-
dc.description.abstract (摘要) Most existing autonomous UAV inspection tasks focus on environment surroundings and facilities. The UAV often navigates above the inspected target and conducts inspection with the camera aiming downward on the target. However, in some scenarios, it is risky to allow UAVs to navigate above the inspected target. For example, when patrolling a river, the UAV may risk falling into the river. Similar risks also exist for scenarios such as railways and power lines. This research proposes a lateral shot following approach for UAVs to follow the river laterally while collecting image data with a front view camera. The proposed approach has been evaluated with different segments of river in real world environments. The experiments include two types of following method and two types of viewpoint to suit different task needs. Results show that our deep neural network can extract the river masks in real-time with high accuracy. With adaptive steering adjustments, the UAV can achieve accurate and robust following when handling geographical change of river segments. Performance comparison between human operators and our developed autonomous system shows that better following accuracy and consistency can be achieved by our autonomous system.
dc.format.extent 1412871 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) Proceedings of the 2020 IEEE International Conference on Real-time Computing and Robotics, IEEE
dc.subject (關鍵詞) Rivers ; Image segmentation ; Unmanned aerial vehicles ; Navigation ; Inspection ; Task analysis ; Image edge detection
dc.title (題名) Real-Time Vision-Based River Detection and Lateral Shot Following for Autonomous UAVs
dc.type (資料類型) conference
dc.identifier.doi (DOI) 10.1109/RCAR49640.2020.9303263
dc.doi.uri (DOI) https://doi.org/10.1109/RCAR49640.2020.9303263