Detection of maize tassels for UAV remote sensing image with an improved YOLOX Model
Maize tassel detection is essential for future agronomic management in maize planting and breeding, with application in yield estimation, growth monitoring, intelligent picking, and disease detection. However, detecting maize tassels in the field poses prominent challenges as they are often obscured...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-06-01
|
| Series: | Journal of Integrative Agriculture |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2095311922002465 |
| _version_ | 1797807030174482432 |
|---|---|
| author | Chao-yu SONG Fan ZHANG Jian-sheng LI Jin-yi XIE Chen YANG Hang ZHOU Jun-xiong ZHANG |
| author_facet | Chao-yu SONG Fan ZHANG Jian-sheng LI Jin-yi XIE Chen YANG Hang ZHOU Jun-xiong ZHANG |
| author_sort | Chao-yu SONG |
| collection | DOAJ |
| description | Maize tassel detection is essential for future agronomic management in maize planting and breeding, with application in yield estimation, growth monitoring, intelligent picking, and disease detection. However, detecting maize tassels in the field poses prominent challenges as they are often obscured by widespread occlusions and differ in size and morphological color at different growth stages. This study proposes the SEYOLOX-tiny Model that more accurately and robustly detects maize tassels in the field. Firstly, the data acquisition method ensures the balance between the image quality and image acquisition efficiency and obtains maize tassel images from different periods to enrich the dataset by unmanned aerial vehicle (UAV). Moreover, the robust detection network extends YOLOX by embedding an attention mechanism to realize the extraction of critical features and suppressing the noise caused by adverse factors (e.g., occlusions and overlaps), which could be more suitable and robust for operation in complex natural environments. Experimental results verify the research hypothesis and show a mean average precision (mAP@0.5) of 95.0%. The mAP@0.5, mAP@0.5–0.95, mAP@0.5–0.95 (area=small), and mAP@0.5–0.95 (area=medium) average values increased by 1.5, 1.8, 5.3, and 1.7%, respectively, compared to the original model. The proposed method can effectively meet the precision and robustness requirements of the vision system in maize tassel detection. |
| first_indexed | 2024-03-13T06:16:23Z |
| format | Article |
| id | doaj.art-2a4db4c84c474407a90f5f4ad13b6ad1 |
| institution | Directory Open Access Journal |
| issn | 2095-3119 |
| language | English |
| last_indexed | 2024-03-13T06:16:23Z |
| publishDate | 2023-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Integrative Agriculture |
| spelling | doaj.art-2a4db4c84c474407a90f5f4ad13b6ad12023-06-11T04:14:22ZengElsevierJournal of Integrative Agriculture2095-31192023-06-0122616711683Detection of maize tassels for UAV remote sensing image with an improved YOLOX ModelChao-yu SONG0Fan ZHANG1Jian-sheng LI2Jin-yi XIE3Chen YANG4Hang ZHOU5Jun-xiong ZHANG6College of Engineering, China Agricultural University, Beijing 100083, P.R.ChinaCollege of Engineering, China Agricultural University, Beijing 100083, P.R.ChinaCollege of Agronomy and Biotechnology, China Agricultural University, Beijing 100083, P.R.ChinaCollege of Engineering, China Agricultural University, Beijing 100083, P.R.ChinaCollege of Engineering, China Agricultural University, Beijing 100083, P.R.ChinaCollege of Engineering, China Agricultural University, Beijing 100083, P.R.ChinaCollege of Engineering, China Agricultural University, Beijing 100083, P.R.China; Correspondence ZHANG Jun-xiongMaize tassel detection is essential for future agronomic management in maize planting and breeding, with application in yield estimation, growth monitoring, intelligent picking, and disease detection. However, detecting maize tassels in the field poses prominent challenges as they are often obscured by widespread occlusions and differ in size and morphological color at different growth stages. This study proposes the SEYOLOX-tiny Model that more accurately and robustly detects maize tassels in the field. Firstly, the data acquisition method ensures the balance between the image quality and image acquisition efficiency and obtains maize tassel images from different periods to enrich the dataset by unmanned aerial vehicle (UAV). Moreover, the robust detection network extends YOLOX by embedding an attention mechanism to realize the extraction of critical features and suppressing the noise caused by adverse factors (e.g., occlusions and overlaps), which could be more suitable and robust for operation in complex natural environments. Experimental results verify the research hypothesis and show a mean average precision (mAP@0.5) of 95.0%. The mAP@0.5, mAP@0.5–0.95, mAP@0.5–0.95 (area=small), and mAP@0.5–0.95 (area=medium) average values increased by 1.5, 1.8, 5.3, and 1.7%, respectively, compared to the original model. The proposed method can effectively meet the precision and robustness requirements of the vision system in maize tassel detection.http://www.sciencedirect.com/science/article/pii/S2095311922002465maizetassel detectionremote sensingdeep learningattention mechanism |
| spellingShingle | Chao-yu SONG Fan ZHANG Jian-sheng LI Jin-yi XIE Chen YANG Hang ZHOU Jun-xiong ZHANG Detection of maize tassels for UAV remote sensing image with an improved YOLOX Model Journal of Integrative Agriculture maize tassel detection remote sensing deep learning attention mechanism |
| title | Detection of maize tassels for UAV remote sensing image with an improved YOLOX Model |
| title_full | Detection of maize tassels for UAV remote sensing image with an improved YOLOX Model |
| title_fullStr | Detection of maize tassels for UAV remote sensing image with an improved YOLOX Model |
| title_full_unstemmed | Detection of maize tassels for UAV remote sensing image with an improved YOLOX Model |
| title_short | Detection of maize tassels for UAV remote sensing image with an improved YOLOX Model |
| title_sort | detection of maize tassels for uav remote sensing image with an improved yolox model |
| topic | maize tassel detection remote sensing deep learning attention mechanism |
| url | http://www.sciencedirect.com/science/article/pii/S2095311922002465 |
| work_keys_str_mv | AT chaoyusong detectionofmaizetasselsforuavremotesensingimagewithanimprovedyoloxmodel AT fanzhang detectionofmaizetasselsforuavremotesensingimagewithanimprovedyoloxmodel AT jianshengli detectionofmaizetasselsforuavremotesensingimagewithanimprovedyoloxmodel AT jinyixie detectionofmaizetasselsforuavremotesensingimagewithanimprovedyoloxmodel AT chenyang detectionofmaizetasselsforuavremotesensingimagewithanimprovedyoloxmodel AT hangzhou detectionofmaizetasselsforuavremotesensingimagewithanimprovedyoloxmodel AT junxiongzhang detectionofmaizetasselsforuavremotesensingimagewithanimprovedyoloxmodel |