Accurate drone corner position estimation in complex backgrounds with boundary classification
This study develops an efficient approach for precise channel frame detection in complex backgrounds, addressing the critical need for accurate drone navigation. Leveraging YOLACT and group regression, our method outperforms conventional techniques that rely solely on color information. We conducted...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-04-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024041422 |
| _version_ | 1797226653667033088 |
|---|---|
| author | Yu-Shiuan Tsai Cheng-Sheng Lin Guan-Yi Li |
| author_facet | Yu-Shiuan Tsai Cheng-Sheng Lin Guan-Yi Li |
| author_sort | Yu-Shiuan Tsai |
| collection | DOAJ |
| description | This study develops an efficient approach for precise channel frame detection in complex backgrounds, addressing the critical need for accurate drone navigation. Leveraging YOLACT and group regression, our method outperforms conventional techniques that rely solely on color information. We conducted extensive experiments involving channel frames placed at various angles and within intricate backgrounds, training the algorithm to effectively recognize them. The process involves initial edge image detection, noise reduction through binarization and erosion, segmentation of channel frame line segments using the Hough Transform algorithm, and subsequent classification via the K-means algorithm. Ultimately, we obtain the regression line segment through linear regression, enabling precise positioning by identifying intersection points. Experimental validations validate the robustness of our approach across diverse angles and challenging backgrounds, making significant advancements in UAV applications. |
| first_indexed | 2024-04-24T14:28:20Z |
| format | Article |
| id | doaj.art-cf39c887d91d4e0ca9f70c8d97ed0f0b |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-04-24T14:28:20Z |
| publishDate | 2024-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-cf39c887d91d4e0ca9f70c8d97ed0f0b2024-04-03T04:26:54ZengElsevierHeliyon2405-84402024-04-01107e28111Accurate drone corner position estimation in complex backgrounds with boundary classificationYu-Shiuan Tsai0Cheng-Sheng Lin1Guan-Yi Li2Corresponding author.; Dept. of Computer Science and Engineering, National Taiwan Ocean University, Zhongzheng District, Keelung, TaiwanDept. of Computer Science and Engineering, National Taiwan Ocean University, Zhongzheng District, Keelung, TaiwanDept. of Computer Science and Engineering, National Taiwan Ocean University, Zhongzheng District, Keelung, TaiwanThis study develops an efficient approach for precise channel frame detection in complex backgrounds, addressing the critical need for accurate drone navigation. Leveraging YOLACT and group regression, our method outperforms conventional techniques that rely solely on color information. We conducted extensive experiments involving channel frames placed at various angles and within intricate backgrounds, training the algorithm to effectively recognize them. The process involves initial edge image detection, noise reduction through binarization and erosion, segmentation of channel frame line segments using the Hough Transform algorithm, and subsequent classification via the K-means algorithm. Ultimately, we obtain the regression line segment through linear regression, enabling precise positioning by identifying intersection points. Experimental validations validate the robustness of our approach across diverse angles and challenging backgrounds, making significant advancements in UAV applications.http://www.sciencedirect.com/science/article/pii/S2405844024041422Boundary classificationDeep learningObject segmentationChannel frame detectionYOLACT |
| spellingShingle | Yu-Shiuan Tsai Cheng-Sheng Lin Guan-Yi Li Accurate drone corner position estimation in complex backgrounds with boundary classification Heliyon Boundary classification Deep learning Object segmentation Channel frame detection YOLACT |
| title | Accurate drone corner position estimation in complex backgrounds with boundary classification |
| title_full | Accurate drone corner position estimation in complex backgrounds with boundary classification |
| title_fullStr | Accurate drone corner position estimation in complex backgrounds with boundary classification |
| title_full_unstemmed | Accurate drone corner position estimation in complex backgrounds with boundary classification |
| title_short | Accurate drone corner position estimation in complex backgrounds with boundary classification |
| title_sort | accurate drone corner position estimation in complex backgrounds with boundary classification |
| topic | Boundary classification Deep learning Object segmentation Channel frame detection YOLACT |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024041422 |
| work_keys_str_mv | AT yushiuantsai accuratedronecornerpositionestimationincomplexbackgroundswithboundaryclassification AT chengshenglin accuratedronecornerpositionestimationincomplexbackgroundswithboundaryclassification AT guanyili accuratedronecornerpositionestimationincomplexbackgroundswithboundaryclassification |