Research on Vision-Based Navigation for Plant Protection UAV under the Near Color Background
GPS (Global Positioning System) navigation in agriculture is facing many challenges, such as weak signals in orchards and the high cost for small plots of farmland. With the reduction of camera cost and the emergence of excellent visual algorithms, visual navigation can solve the above problems. Vis...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-04-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/11/4/533 |
| _version_ | 1817989799876755456 |
|---|---|
| author | Hehu Zhang Xiushan Wang Ying Chen Guoqiang Jiang Shifeng Lin |
| author_facet | Hehu Zhang Xiushan Wang Ying Chen Guoqiang Jiang Shifeng Lin |
| author_sort | Hehu Zhang |
| collection | DOAJ |
| description | GPS (Global Positioning System) navigation in agriculture is facing many challenges, such as weak signals in orchards and the high cost for small plots of farmland. With the reduction of camera cost and the emergence of excellent visual algorithms, visual navigation can solve the above problems. Visual navigation is a navigation technology that uses cameras to sense environmental information as the basis of an aircraft flight. It is mainly divided into five parts: Image acquisition, landmark recognition, route planning, flight control, and obstacle avoidance. Here, landmarks are plant canopy, buildings, mountains, and rivers, with unique geographical characteristics in a place. During visual navigation, landmark location and route tracking are key links. When there are significant color-differences (for example, the differences among red, green, and blue) between a landmark and the background, the landmark can be recognized based on classical visual algorithms. However, in the case of non-significant color-differences (for example, the differences between dark green and vivid green) between a landmark and the background, there are no robust and high-precision methods for landmark identification. In view of the above problem, visual navigation in a maize field is studied. First, the block recognition method based on fine-tuned Inception-V3 is developed; then, the maize canopy landmark is recognized based on the above method; finally, local navigation lines are extracted from the landmarks based on the maize canopy grayscale gradient law. The results show that the accuracy is 0.9501. When the block number is 256, the block recognition method achieves the best segmentation. The average segmentation quality is 0.87, and time is 0.251 s. This study suggests that stable visual semantic navigation can be achieved under the near color background. It will be an important reference for the navigation of plant protection UAV (Unmanned Aerial Vehicle). |
| first_indexed | 2024-04-14T00:50:36Z |
| format | Article |
| id | doaj.art-48aef7ee5e9e4e8292e1660b25f6200a |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-04-14T00:50:36Z |
| publishDate | 2019-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-48aef7ee5e9e4e8292e1660b25f6200a2022-12-22T02:21:48ZengMDPI AGSymmetry2073-89942019-04-0111453310.3390/sym11040533sym11040533Research on Vision-Based Navigation for Plant Protection UAV under the Near Color BackgroundHehu Zhang0Xiushan Wang1Ying Chen2Guoqiang Jiang3Shifeng Lin4College of Mechanical & Electrical Engineering, Henan Agricultural University, Zhengzhou 450003, ChinaCollege of Mechanical & Electrical Engineering, Henan Agricultural University, Zhengzhou 450003, ChinaCollege of Humanity & Law, Henan Agricultural University, Zhengzhou 450003, ChinaCollege of Mechanical & Electrical Engineering, Henan Agricultural University, Zhengzhou 450003, ChinaFaculty of Engineering, University of New South Wales, Sydney 2052, AustraliaGPS (Global Positioning System) navigation in agriculture is facing many challenges, such as weak signals in orchards and the high cost for small plots of farmland. With the reduction of camera cost and the emergence of excellent visual algorithms, visual navigation can solve the above problems. Visual navigation is a navigation technology that uses cameras to sense environmental information as the basis of an aircraft flight. It is mainly divided into five parts: Image acquisition, landmark recognition, route planning, flight control, and obstacle avoidance. Here, landmarks are plant canopy, buildings, mountains, and rivers, with unique geographical characteristics in a place. During visual navigation, landmark location and route tracking are key links. When there are significant color-differences (for example, the differences among red, green, and blue) between a landmark and the background, the landmark can be recognized based on classical visual algorithms. However, in the case of non-significant color-differences (for example, the differences between dark green and vivid green) between a landmark and the background, there are no robust and high-precision methods for landmark identification. In view of the above problem, visual navigation in a maize field is studied. First, the block recognition method based on fine-tuned Inception-V3 is developed; then, the maize canopy landmark is recognized based on the above method; finally, local navigation lines are extracted from the landmarks based on the maize canopy grayscale gradient law. The results show that the accuracy is 0.9501. When the block number is 256, the block recognition method achieves the best segmentation. The average segmentation quality is 0.87, and time is 0.251 s. This study suggests that stable visual semantic navigation can be achieved under the near color background. It will be an important reference for the navigation of plant protection UAV (Unmanned Aerial Vehicle).https://www.mdpi.com/2073-8994/11/4/533landmark locationroute trackinginception-V3visual navigationgrayscale gradient law |
| spellingShingle | Hehu Zhang Xiushan Wang Ying Chen Guoqiang Jiang Shifeng Lin Research on Vision-Based Navigation for Plant Protection UAV under the Near Color Background Symmetry landmark location route tracking inception-V3 visual navigation grayscale gradient law |
| title | Research on Vision-Based Navigation for Plant Protection UAV under the Near Color Background |
| title_full | Research on Vision-Based Navigation for Plant Protection UAV under the Near Color Background |
| title_fullStr | Research on Vision-Based Navigation for Plant Protection UAV under the Near Color Background |
| title_full_unstemmed | Research on Vision-Based Navigation for Plant Protection UAV under the Near Color Background |
| title_short | Research on Vision-Based Navigation for Plant Protection UAV under the Near Color Background |
| title_sort | research on vision based navigation for plant protection uav under the near color background |
| topic | landmark location route tracking inception-V3 visual navigation grayscale gradient law |
| url | https://www.mdpi.com/2073-8994/11/4/533 |
| work_keys_str_mv | AT hehuzhang researchonvisionbasednavigationforplantprotectionuavunderthenearcolorbackground AT xiushanwang researchonvisionbasednavigationforplantprotectionuavunderthenearcolorbackground AT yingchen researchonvisionbasednavigationforplantprotectionuavunderthenearcolorbackground AT guoqiangjiang researchonvisionbasednavigationforplantprotectionuavunderthenearcolorbackground AT shifenglin researchonvisionbasednavigationforplantprotectionuavunderthenearcolorbackground |