Crown Width Extraction of <i>Metasequoia glyptostroboides</i> Using Improved YOLOv7 Based on UAV Images
With the progress of computer vision and the development of unmanned aerial vehicles (UAVs), UAVs have been widely used in forest resource investigation and tree feature extraction. In the field of crown width measurement, the use of traditional manual measurement methods is time-consuming and costl...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/7/6/336 |
| _version_ | 1797595267074097152 |
|---|---|
| author | Chen Dong Chongyuan Cai Sheng Chen Hao Xu Laibang Yang Jingyong Ji Siqi Huang I-Kuai Hung Yuhui Weng Xiongwei Lou |
| author_facet | Chen Dong Chongyuan Cai Sheng Chen Hao Xu Laibang Yang Jingyong Ji Siqi Huang I-Kuai Hung Yuhui Weng Xiongwei Lou |
| author_sort | Chen Dong |
| collection | DOAJ |
| description | With the progress of computer vision and the development of unmanned aerial vehicles (UAVs), UAVs have been widely used in forest resource investigation and tree feature extraction. In the field of crown width measurement, the use of traditional manual measurement methods is time-consuming and costly and affects factors such as terrain and weather. Although the crown width extraction method based on the segmentation of UAV images that have recently risen in popularity extracts a large amount of information, it consumes long amounts of time for dataset establishment and segmentation. This paper proposes an improved YOLOv7 model designed to precisely extract the crown width of <i>Metasequoia glyptostroboides</i>. This species is distinguished by its well-developed terminal buds and distinct central trunk morphology. Taking the <i>M. glyptostroboides</i> forest in the Qingshan Lake National Forest Park in Lin’an District, Hangzhou City, Zhejiang Province, China, as the target sample plot, YOLOv7 was improved using the simple, parameter-free attention model (SimAM) attention and SIoU modules. The SimAM attention module was experimentally proved capable of reducing the attention to other irrelevant information in the training process and improving the model’s accuracy. The SIoU module can improve the tightness between the detection frame and the edge of the target crown during the detection process and effectively enhance the accuracy of crown width measurement. The experimental results reveal that the improved model achieves 94.34% mAP@0.5 in the task of crown detection, which is 5% higher than that achieved by the original model. In crown width measurement, the R<sup>2</sup> of the improved model reaches 0.837, which is 0.151 higher than that of the original model, thus verifying the effectiveness of the improved algorithm. |
| first_indexed | 2024-03-11T02:33:50Z |
| format | Article |
| id | doaj.art-8b82cc9a79f046fd959817a83ec99365 |
| institution | Directory Open Access Journal |
| issn | 2504-446X |
| language | English |
| last_indexed | 2024-03-11T02:33:50Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj.art-8b82cc9a79f046fd959817a83ec993652023-11-18T10:03:40ZengMDPI AGDrones2504-446X2023-05-017633610.3390/drones7060336Crown Width Extraction of <i>Metasequoia glyptostroboides</i> Using Improved YOLOv7 Based on UAV ImagesChen Dong0Chongyuan Cai1Sheng Chen2Hao Xu3Laibang Yang4Jingyong Ji5Siqi Huang6I-Kuai Hung7Yuhui Weng8Xiongwei Lou9College of Mathematics and Computer Science, Zhejiang A & F University, Hangzhou 311300, ChinaCollege of Mathematics and Computer Science, Zhejiang A & F University, Hangzhou 311300, ChinaCenter for Forest Resource Monitoring of Zhejiang Province, Hangzhou 310000, ChinaZhejiang Forestry Bureau, Hangzhou 310000, ChinaHangzhou Ganzhi Technology Co., Ltd., Hangzhou 311300, ChinaLongquan Forestry Bureau, Longquan 323700, ChinaLongquan Urban Forestry Workstation, Longquan 323700, ChinaCollege of Forestry and Agriculture, Stephen F. Austin State University, Nacogdoches, TX 75962, USACollege of Forestry and Agriculture, Stephen F. Austin State University, Nacogdoches, TX 75962, USACollege of Mathematics and Computer Science, Zhejiang A & F University, Hangzhou 311300, ChinaWith the progress of computer vision and the development of unmanned aerial vehicles (UAVs), UAVs have been widely used in forest resource investigation and tree feature extraction. In the field of crown width measurement, the use of traditional manual measurement methods is time-consuming and costly and affects factors such as terrain and weather. Although the crown width extraction method based on the segmentation of UAV images that have recently risen in popularity extracts a large amount of information, it consumes long amounts of time for dataset establishment and segmentation. This paper proposes an improved YOLOv7 model designed to precisely extract the crown width of <i>Metasequoia glyptostroboides</i>. This species is distinguished by its well-developed terminal buds and distinct central trunk morphology. Taking the <i>M. glyptostroboides</i> forest in the Qingshan Lake National Forest Park in Lin’an District, Hangzhou City, Zhejiang Province, China, as the target sample plot, YOLOv7 was improved using the simple, parameter-free attention model (SimAM) attention and SIoU modules. The SimAM attention module was experimentally proved capable of reducing the attention to other irrelevant information in the training process and improving the model’s accuracy. The SIoU module can improve the tightness between the detection frame and the edge of the target crown during the detection process and effectively enhance the accuracy of crown width measurement. The experimental results reveal that the improved model achieves 94.34% mAP@0.5 in the task of crown detection, which is 5% higher than that achieved by the original model. In crown width measurement, the R<sup>2</sup> of the improved model reaches 0.837, which is 0.151 higher than that of the original model, thus verifying the effectiveness of the improved algorithm.https://www.mdpi.com/2504-446X/7/6/336unmanned aerial vehicleforest resourcescrown widthYOLOv7attention module |
| spellingShingle | Chen Dong Chongyuan Cai Sheng Chen Hao Xu Laibang Yang Jingyong Ji Siqi Huang I-Kuai Hung Yuhui Weng Xiongwei Lou Crown Width Extraction of <i>Metasequoia glyptostroboides</i> Using Improved YOLOv7 Based on UAV Images Drones unmanned aerial vehicle forest resources crown width YOLOv7 attention module |
| title | Crown Width Extraction of <i>Metasequoia glyptostroboides</i> Using Improved YOLOv7 Based on UAV Images |
| title_full | Crown Width Extraction of <i>Metasequoia glyptostroboides</i> Using Improved YOLOv7 Based on UAV Images |
| title_fullStr | Crown Width Extraction of <i>Metasequoia glyptostroboides</i> Using Improved YOLOv7 Based on UAV Images |
| title_full_unstemmed | Crown Width Extraction of <i>Metasequoia glyptostroboides</i> Using Improved YOLOv7 Based on UAV Images |
| title_short | Crown Width Extraction of <i>Metasequoia glyptostroboides</i> Using Improved YOLOv7 Based on UAV Images |
| title_sort | crown width extraction of i metasequoia glyptostroboides i using improved yolov7 based on uav images |
| topic | unmanned aerial vehicle forest resources crown width YOLOv7 attention module |
| url | https://www.mdpi.com/2504-446X/7/6/336 |
| work_keys_str_mv | AT chendong crownwidthextractionofimetasequoiaglyptostroboidesiusingimprovedyolov7basedonuavimages AT chongyuancai crownwidthextractionofimetasequoiaglyptostroboidesiusingimprovedyolov7basedonuavimages AT shengchen crownwidthextractionofimetasequoiaglyptostroboidesiusingimprovedyolov7basedonuavimages AT haoxu crownwidthextractionofimetasequoiaglyptostroboidesiusingimprovedyolov7basedonuavimages AT laibangyang crownwidthextractionofimetasequoiaglyptostroboidesiusingimprovedyolov7basedonuavimages AT jingyongji crownwidthextractionofimetasequoiaglyptostroboidesiusingimprovedyolov7basedonuavimages AT siqihuang crownwidthextractionofimetasequoiaglyptostroboidesiusingimprovedyolov7basedonuavimages AT ikuaihung crownwidthextractionofimetasequoiaglyptostroboidesiusingimprovedyolov7basedonuavimages AT yuhuiweng crownwidthextractionofimetasequoiaglyptostroboidesiusingimprovedyolov7basedonuavimages AT xiongweilou crownwidthextractionofimetasequoiaglyptostroboidesiusingimprovedyolov7basedonuavimages |