Pomelo Tree Detection Method Based on Attention Mechanism and Cross-Layer Feature Fusion
Deep learning is the subject of increasing research for fruit tree detection. Previously developed deep-learning-based models are either too large to perform real-time tasks or too small to extract good enough features. Moreover, there has been scarce research on the detection of pomelo trees. This...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/16/3902 |
| _version_ | 1797442336030982144 |
|---|---|
| author | Haotian Yuan Kekun Huang Chuanxian Ren Yongzhu Xiong Jieli Duan Zhou Yang |
| author_facet | Haotian Yuan Kekun Huang Chuanxian Ren Yongzhu Xiong Jieli Duan Zhou Yang |
| author_sort | Haotian Yuan |
| collection | DOAJ |
| description | Deep learning is the subject of increasing research for fruit tree detection. Previously developed deep-learning-based models are either too large to perform real-time tasks or too small to extract good enough features. Moreover, there has been scarce research on the detection of pomelo trees. This paper proposes a pomelo tree-detection method that introduces the attention mechanism and a Ghost module into the lightweight model network, as well as a feature-fusion module to improve the feature-extraction ability and reduce computation. The proposed method was experimentally validated and showed better detection performance and fewer parameters than some state-of-the-art target-detection algorithms. The results indicate that our method is more suitable for pomelo tree detection. |
| first_indexed | 2024-03-09T12:41:24Z |
| format | Article |
| id | doaj.art-f29c28f3c2ab4b7aa0aee91d860efd22 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T12:41:24Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-f29c28f3c2ab4b7aa0aee91d860efd222023-11-30T22:18:57ZengMDPI AGRemote Sensing2072-42922022-08-011416390210.3390/rs14163902Pomelo Tree Detection Method Based on Attention Mechanism and Cross-Layer Feature FusionHaotian Yuan0Kekun Huang1Chuanxian Ren2Yongzhu Xiong3Jieli Duan4Zhou Yang5School of Engineering, South China Agricultural University, Guangzhou 510642, ChinaSchool of Mathematics, Jiaying University, Meizhou 514015, ChinaSchool of Mathematics, Sun Yat-sen University, Guangzhou 510275, ChinaGuangdong Provincial Key Laboratory of Conservation and Precision Utilization of Characteristic Agricultural Resources in Mountainous Areas, Jiaying University, Meizhou 514015, ChinaSchool of Engineering, South China Agricultural University, Guangzhou 510642, ChinaSchool of Engineering, South China Agricultural University, Guangzhou 510642, ChinaDeep learning is the subject of increasing research for fruit tree detection. Previously developed deep-learning-based models are either too large to perform real-time tasks or too small to extract good enough features. Moreover, there has been scarce research on the detection of pomelo trees. This paper proposes a pomelo tree-detection method that introduces the attention mechanism and a Ghost module into the lightweight model network, as well as a feature-fusion module to improve the feature-extraction ability and reduce computation. The proposed method was experimentally validated and showed better detection performance and fewer parameters than some state-of-the-art target-detection algorithms. The results indicate that our method is more suitable for pomelo tree detection.https://www.mdpi.com/2072-4292/14/16/3902convolutional neural networkobject detectionattention mechanismremote-sensing imagepomelo tree detection |
| spellingShingle | Haotian Yuan Kekun Huang Chuanxian Ren Yongzhu Xiong Jieli Duan Zhou Yang Pomelo Tree Detection Method Based on Attention Mechanism and Cross-Layer Feature Fusion Remote Sensing convolutional neural network object detection attention mechanism remote-sensing image pomelo tree detection |
| title | Pomelo Tree Detection Method Based on Attention Mechanism and Cross-Layer Feature Fusion |
| title_full | Pomelo Tree Detection Method Based on Attention Mechanism and Cross-Layer Feature Fusion |
| title_fullStr | Pomelo Tree Detection Method Based on Attention Mechanism and Cross-Layer Feature Fusion |
| title_full_unstemmed | Pomelo Tree Detection Method Based on Attention Mechanism and Cross-Layer Feature Fusion |
| title_short | Pomelo Tree Detection Method Based on Attention Mechanism and Cross-Layer Feature Fusion |
| title_sort | pomelo tree detection method based on attention mechanism and cross layer feature fusion |
| topic | convolutional neural network object detection attention mechanism remote-sensing image pomelo tree detection |
| url | https://www.mdpi.com/2072-4292/14/16/3902 |
| work_keys_str_mv | AT haotianyuan pomelotreedetectionmethodbasedonattentionmechanismandcrosslayerfeaturefusion AT kekunhuang pomelotreedetectionmethodbasedonattentionmechanismandcrosslayerfeaturefusion AT chuanxianren pomelotreedetectionmethodbasedonattentionmechanismandcrosslayerfeaturefusion AT yongzhuxiong pomelotreedetectionmethodbasedonattentionmechanismandcrosslayerfeaturefusion AT jieliduan pomelotreedetectionmethodbasedonattentionmechanismandcrosslayerfeaturefusion AT zhouyang pomelotreedetectionmethodbasedonattentionmechanismandcrosslayerfeaturefusion |