Obstacle detection for Unmanned Aerial Vehicle (UAV)
This study aims to develop an obstacle detection system for unmanned aerial vehicles utilising the ORB feature extraction. In the past, small unmanned aerial vehicles (UAV) were typically equipped with vision-based or range-based sensors. Each sensor in the sensor-based technique possesses diffe...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit UTHM
2022
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/8114/ http://eprints.uthm.edu.my/8114/1/J14841_aa59537113306d1920cdbeb2e18502c2.pdf |
| _version_ | 1848889303927619584 |
|---|---|
| author | Abdul Khaliq, Nor Aizatul Nabila Ramli, Muhammad Faiz |
| author_facet | Abdul Khaliq, Nor Aizatul Nabila Ramli, Muhammad Faiz |
| author_sort | Abdul Khaliq, Nor Aizatul Nabila |
| building | UTHM Institutional Repository |
| collection | Online Access |
| description | This study aims to develop an obstacle detection system for unmanned aerial vehicles utilising the ORB
feature extraction. In the past, small unmanned aerial vehicles (UAV) were typically equipped with vision-based or
range-based sensors. Each sensor in the sensor-based technique possesses different advantages and disadvantages.
As a result, the small unmanned aerial vehicle is unable to determine the obstacle's distance or bearing precisely.
Due to physical size restrictions and payload capacity, the lightweight Pi Camera and TF Luna LiDAR sensor were
selected as the most suitable sensors for integration. In algorithm development and filtration is used to improve the
accuracy of the feature matching process, which is required for classifying the obstacle region and free region of any
texture obstacle. The experiment was under the environment of OpenCV and Spyder. In real-time experiment, the
success rate for good texture (40%), poor texture (55%) and texture-less (45%) The findings indicate that the
recommended method works well for detecting textures-less obstacle even though the success rate is only 40%
because out of 10 test only one test is fail on detecting free region. The sensor calibration and constructing convex
hull for obstacle detection is recommended in future works to improve the efficiency of the obstacle detection system
and classified the free region and obstacle region to create safe avoidance path. |
| first_indexed | 2025-11-15T20:24:02Z |
| format | Article |
| id | uthm-8114 |
| institution | Universiti Tun Hussein Onn Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T20:24:02Z |
| publishDate | 2022 |
| publisher | Penerbit UTHM |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | uthm-81142022-12-18T02:59:25Z http://eprints.uthm.edu.my/8114/ Obstacle detection for Unmanned Aerial Vehicle (UAV) Abdul Khaliq, Nor Aizatul Nabila Ramli, Muhammad Faiz T Technology (General) This study aims to develop an obstacle detection system for unmanned aerial vehicles utilising the ORB feature extraction. In the past, small unmanned aerial vehicles (UAV) were typically equipped with vision-based or range-based sensors. Each sensor in the sensor-based technique possesses different advantages and disadvantages. As a result, the small unmanned aerial vehicle is unable to determine the obstacle's distance or bearing precisely. Due to physical size restrictions and payload capacity, the lightweight Pi Camera and TF Luna LiDAR sensor were selected as the most suitable sensors for integration. In algorithm development and filtration is used to improve the accuracy of the feature matching process, which is required for classifying the obstacle region and free region of any texture obstacle. The experiment was under the environment of OpenCV and Spyder. In real-time experiment, the success rate for good texture (40%), poor texture (55%) and texture-less (45%) The findings indicate that the recommended method works well for detecting textures-less obstacle even though the success rate is only 40% because out of 10 test only one test is fail on detecting free region. The sensor calibration and constructing convex hull for obstacle detection is recommended in future works to improve the efficiency of the obstacle detection system and classified the free region and obstacle region to create safe avoidance path. Penerbit UTHM 2022 Article PeerReviewed text en http://eprints.uthm.edu.my/8114/1/J14841_aa59537113306d1920cdbeb2e18502c2.pdf Abdul Khaliq, Nor Aizatul Nabila and Ramli, Muhammad Faiz (2022) Obstacle detection for Unmanned Aerial Vehicle (UAV). PROGRESS IN AEROSPACE AND AVIATION TECHNOLOGY, 2 (1). pp. 53-64. https://doi.org/10.30880/paat.2022.02.01.007 |
| spellingShingle | T Technology (General) Abdul Khaliq, Nor Aizatul Nabila Ramli, Muhammad Faiz Obstacle detection for Unmanned Aerial Vehicle (UAV) |
| title | Obstacle detection for Unmanned Aerial Vehicle (UAV) |
| title_full | Obstacle detection for Unmanned Aerial Vehicle (UAV) |
| title_fullStr | Obstacle detection for Unmanned Aerial Vehicle (UAV) |
| title_full_unstemmed | Obstacle detection for Unmanned Aerial Vehicle (UAV) |
| title_short | Obstacle detection for Unmanned Aerial Vehicle (UAV) |
| title_sort | obstacle detection for unmanned aerial vehicle (uav) |
| topic | T Technology (General) |
| url | http://eprints.uthm.edu.my/8114/ http://eprints.uthm.edu.my/8114/ http://eprints.uthm.edu.my/8114/1/J14841_aa59537113306d1920cdbeb2e18502c2.pdf |