Implementation of UAV Automatic Landing Using Machine Vision
碩士 === 國立高雄應用科技大學 === 電機工程系博碩士班 === 104 === Unmanned Aerial Vehicle (UAV) has been widely used in various fields during the past decades. Using machine vision to achieve the automatic photographing and automatic landing becomes an active research area. In this thesis, we use Speeded-Up Robust Featur...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en_US |
| Published: |
2016
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/22095008425616605244 |
| Summary: | 碩士 === 國立高雄應用科技大學 === 電機工程系博碩士班 === 104 === Unmanned Aerial Vehicle (UAV) has been widely used in various fields during the past decades. Using machine vision to achieve the automatic photographing and automatic landing becomes an active research area. In this thesis, we use Speeded-Up Robust Features (SURF) to find the feature points of the heliport, and then use Random Sample Consensus (RANSAC) to find the affine transform model between template image and real-time image to find the heliport. In order to locate the heliport more accurately, we use contours finding and image thinning algorithms to reduce noises and use Hough transform to locate the heliport. Our method uses ROI to reduce the processing area, so the processing speed and detection rate can be improved. The results show that the proposed system has high processing speed and detection rate for real-time automatic landing system.
|
|---|