Tree-Level Chinese Fir Detection Using UAV RGB Imagery and YOLO-DCAM
Achieving the accurate and efficient monitoring of forests at the tree level can provide detailed information for precise and scientific forest management. However, the detection of individual trees under planted forests characterized by dense distribution, serious overlap, and complicated backgroun...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/2/335 |
| _version_ | 1797342575461400576 |
|---|---|
| author | Jiansen Wang Huaiqing Zhang Yang Liu Huacong Zhang Dongping Zheng |
| author_facet | Jiansen Wang Huaiqing Zhang Yang Liu Huacong Zhang Dongping Zheng |
| author_sort | Jiansen Wang |
| collection | DOAJ |
| description | Achieving the accurate and efficient monitoring of forests at the tree level can provide detailed information for precise and scientific forest management. However, the detection of individual trees under planted forests characterized by dense distribution, serious overlap, and complicated background information is still a challenge. A new deep learning network, YOLO-DCAM, has been developed to effectively promote individual tree detection amidst complex scenes. The YOLO-DCAM is constructed by leveraging the YOLOv5 network as the basis and further enhancing the network’s capability of extracting features by reasonably incorporating deformable convolutional layers into the backbone. Additionally, an efficient multi-scale attention module is integrated into the neck to enable the network to prioritize the tree crown features and reduce the interference of background information. The combination of these two modules can greatly enhance detection performance. The YOLO-DCAM achieved an impressive performance for the detection of Chinese fir instances within a comprehensive dataset comprising 978 images across four typical planted forest scenes, with model evaluation metrics of precision (96.1%), recall (93.0%), F1-score (94.5%), and AP@0.5 (97.3%), respectively. The comparative test showed that YOLO-DCAM has a good balance between model accuracy and efficiency compared with YOLOv5 and advanced detection models. Specifically, the precision increased by 2.6%, recall increased by 1.6%, F1-score increased by 2.1%, and AP@0.5 increased by 1.4% compared to YOLOv5. Across three supplementary plots, YOLO-DCAM consistently demonstrates strong robustness. These results illustrate the effectiveness of YOLO-DCAM for detecting individual trees in complex plantation environments. This study can serve as a reference for utilizing UAV-based RGB imagery to precisely detect individual trees, offering valuable implications for forest practical applications. |
| first_indexed | 2024-03-08T10:35:16Z |
| format | Article |
| id | doaj.art-39501f64d65d4f348caab78ed51e625f |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-08T10:35:16Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-39501f64d65d4f348caab78ed51e625f2024-01-26T18:18:33ZengMDPI AGRemote Sensing2072-42922024-01-0116233510.3390/rs16020335Tree-Level Chinese Fir Detection Using UAV RGB Imagery and YOLO-DCAMJiansen Wang0Huaiqing Zhang1Yang Liu2Huacong Zhang3Dongping Zheng4Institute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, ChinaInstitute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, ChinaInstitute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, ChinaInstitute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, ChinaDepartment of Second Language Studies, University of Hawai‘i at Mānoa, 1890 East-West Road, Honolulu, HI 96822, USAAchieving the accurate and efficient monitoring of forests at the tree level can provide detailed information for precise and scientific forest management. However, the detection of individual trees under planted forests characterized by dense distribution, serious overlap, and complicated background information is still a challenge. A new deep learning network, YOLO-DCAM, has been developed to effectively promote individual tree detection amidst complex scenes. The YOLO-DCAM is constructed by leveraging the YOLOv5 network as the basis and further enhancing the network’s capability of extracting features by reasonably incorporating deformable convolutional layers into the backbone. Additionally, an efficient multi-scale attention module is integrated into the neck to enable the network to prioritize the tree crown features and reduce the interference of background information. The combination of these two modules can greatly enhance detection performance. The YOLO-DCAM achieved an impressive performance for the detection of Chinese fir instances within a comprehensive dataset comprising 978 images across four typical planted forest scenes, with model evaluation metrics of precision (96.1%), recall (93.0%), F1-score (94.5%), and AP@0.5 (97.3%), respectively. The comparative test showed that YOLO-DCAM has a good balance between model accuracy and efficiency compared with YOLOv5 and advanced detection models. Specifically, the precision increased by 2.6%, recall increased by 1.6%, F1-score increased by 2.1%, and AP@0.5 increased by 1.4% compared to YOLOv5. Across three supplementary plots, YOLO-DCAM consistently demonstrates strong robustness. These results illustrate the effectiveness of YOLO-DCAM for detecting individual trees in complex plantation environments. This study can serve as a reference for utilizing UAV-based RGB imagery to precisely detect individual trees, offering valuable implications for forest practical applications.https://www.mdpi.com/2072-4292/16/2/335YOLOv5individual tree detectionplanted forestsChinese firdeformable convolutionattention mechanism |
| spellingShingle | Jiansen Wang Huaiqing Zhang Yang Liu Huacong Zhang Dongping Zheng Tree-Level Chinese Fir Detection Using UAV RGB Imagery and YOLO-DCAM Remote Sensing YOLOv5 individual tree detection planted forests Chinese fir deformable convolution attention mechanism |
| title | Tree-Level Chinese Fir Detection Using UAV RGB Imagery and YOLO-DCAM |
| title_full | Tree-Level Chinese Fir Detection Using UAV RGB Imagery and YOLO-DCAM |
| title_fullStr | Tree-Level Chinese Fir Detection Using UAV RGB Imagery and YOLO-DCAM |
| title_full_unstemmed | Tree-Level Chinese Fir Detection Using UAV RGB Imagery and YOLO-DCAM |
| title_short | Tree-Level Chinese Fir Detection Using UAV RGB Imagery and YOLO-DCAM |
| title_sort | tree level chinese fir detection using uav rgb imagery and yolo dcam |
| topic | YOLOv5 individual tree detection planted forests Chinese fir deformable convolution attention mechanism |
| url | https://www.mdpi.com/2072-4292/16/2/335 |
| work_keys_str_mv | AT jiansenwang treelevelchinesefirdetectionusinguavrgbimageryandyolodcam AT huaiqingzhang treelevelchinesefirdetectionusinguavrgbimageryandyolodcam AT yangliu treelevelchinesefirdetectionusinguavrgbimageryandyolodcam AT huacongzhang treelevelchinesefirdetectionusinguavrgbimageryandyolodcam AT dongpingzheng treelevelchinesefirdetectionusinguavrgbimageryandyolodcam |