Using UAVRS and deep learning to conduct resource surveys of threatened Tibetan medicinal plants in the Qinghai-Tibet Plateau
Gentiana szechenyii Kanitz. and Gentiana veitchiorum Hemsl. are two wild medicinal plants widely used in Tibetan medicine. In recent decades, their wild populations have declined rapidly due to persistent over-harvesting of their flowers. Because their flowers are small and dense, it is difficult to...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-06-01
|
| Series: | Global Ecology and Conservation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S235198942400088X |
| _version_ | 1797267801504743424 |
|---|---|
| author | Chenghui Wang Ziyi Li Rong Ding Jiawei Luo Yu Liang Rui Gu Shihong Zhong |
| author_facet | Chenghui Wang Ziyi Li Rong Ding Jiawei Luo Yu Liang Rui Gu Shihong Zhong |
| author_sort | Chenghui Wang |
| collection | DOAJ |
| description | Gentiana szechenyii Kanitz. and Gentiana veitchiorum Hemsl. are two wild medicinal plants widely used in Tibetan medicine. In recent decades, their wild populations have declined rapidly due to persistent over-harvesting of their flowers. Because their flowers are small and dense, it is difficult to rely on manual counting under wild conditions. The combination of deep learning and unmanned aerial vehicle remote sensing (UAVRS) is a new method for plant surveys. We trained 12 of the most advanced or widely used YOLO models on a custom dataset to achieve quantitative detection of both plant flowers in UAVRS images. The accuracy, precision and recall of G. szechenyii Flower (GSF) detection can reach 97.00%, 90.40% and 95.40%, respectively (based on YOLOv7). Similarly, those of G. veitchiorum Flower (GVF) detection can reach 93.40%, 91.30% and 90.60%, respectively (based on YOLOv5n), and the highest mAP can reach 94.90% (based on YOLOv5m). Based on the detection results, it is calculated that the total yield of dried GSF and GVF that can be harvested as medicinal materials in study area ranges from 1.88 to 2.10 g·m−2 and 4.42–4.62 g·m−2, respectively. The results show that deep learning and UAVRS can be used for quantitative detection of GSF and GVF, which is helpful for further research and protection of these two plants. |
| first_indexed | 2024-04-25T01:22:21Z |
| format | Article |
| id | doaj.art-4fd9456dc7fc4407bae9a09b1f5a90ea |
| institution | Directory Open Access Journal |
| issn | 2351-9894 |
| language | English |
| last_indexed | 2024-04-25T01:22:21Z |
| publishDate | 2024-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Global Ecology and Conservation |
| spelling | doaj.art-4fd9456dc7fc4407bae9a09b1f5a90ea2024-03-09T09:25:05ZengElsevierGlobal Ecology and Conservation2351-98942024-06-0151e02884Using UAVRS and deep learning to conduct resource surveys of threatened Tibetan medicinal plants in the Qinghai-Tibet PlateauChenghui Wang0Ziyi Li1Rong Ding2Jiawei Luo3Yu Liang4Rui Gu5Shihong Zhong6School of Pharmacy, Southwest Minzu University, Chengdu 610041, China; School of Ethnic Medicine, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, ChinaSchool of Ethnic Medicine, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, ChinaSchool of Pharmacy, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, ChinaWest China Biomedical Big Data Center, West China Hospital/West China School of Medicine, Sichuan Uni-versity, Chengdu 610044, ChinaSchool of Ethnic Medicine, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, ChinaSchool of Ethnic Medicine, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China; State Key Laboratory of Southwestern Chinese Medicine Resources, School of Pharmacy, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China; Corresponding author at: School of Ethnic Medicine, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China.School of Pharmacy, Southwest Minzu University, Chengdu 610041, China; Corresponding author.Gentiana szechenyii Kanitz. and Gentiana veitchiorum Hemsl. are two wild medicinal plants widely used in Tibetan medicine. In recent decades, their wild populations have declined rapidly due to persistent over-harvesting of their flowers. Because their flowers are small and dense, it is difficult to rely on manual counting under wild conditions. The combination of deep learning and unmanned aerial vehicle remote sensing (UAVRS) is a new method for plant surveys. We trained 12 of the most advanced or widely used YOLO models on a custom dataset to achieve quantitative detection of both plant flowers in UAVRS images. The accuracy, precision and recall of G. szechenyii Flower (GSF) detection can reach 97.00%, 90.40% and 95.40%, respectively (based on YOLOv7). Similarly, those of G. veitchiorum Flower (GVF) detection can reach 93.40%, 91.30% and 90.60%, respectively (based on YOLOv5n), and the highest mAP can reach 94.90% (based on YOLOv5m). Based on the detection results, it is calculated that the total yield of dried GSF and GVF that can be harvested as medicinal materials in study area ranges from 1.88 to 2.10 g·m−2 and 4.42–4.62 g·m−2, respectively. The results show that deep learning and UAVRS can be used for quantitative detection of GSF and GVF, which is helpful for further research and protection of these two plants.http://www.sciencedirect.com/science/article/pii/S235198942400088XGentiana szechenyiiGentiana veitchiorumUnmanned aerial vehicle remote sensing (UAVRS)Deep learningMedicinal plant |
| spellingShingle | Chenghui Wang Ziyi Li Rong Ding Jiawei Luo Yu Liang Rui Gu Shihong Zhong Using UAVRS and deep learning to conduct resource surveys of threatened Tibetan medicinal plants in the Qinghai-Tibet Plateau Global Ecology and Conservation Gentiana szechenyii Gentiana veitchiorum Unmanned aerial vehicle remote sensing (UAVRS) Deep learning Medicinal plant |
| title | Using UAVRS and deep learning to conduct resource surveys of threatened Tibetan medicinal plants in the Qinghai-Tibet Plateau |
| title_full | Using UAVRS and deep learning to conduct resource surveys of threatened Tibetan medicinal plants in the Qinghai-Tibet Plateau |
| title_fullStr | Using UAVRS and deep learning to conduct resource surveys of threatened Tibetan medicinal plants in the Qinghai-Tibet Plateau |
| title_full_unstemmed | Using UAVRS and deep learning to conduct resource surveys of threatened Tibetan medicinal plants in the Qinghai-Tibet Plateau |
| title_short | Using UAVRS and deep learning to conduct resource surveys of threatened Tibetan medicinal plants in the Qinghai-Tibet Plateau |
| title_sort | using uavrs and deep learning to conduct resource surveys of threatened tibetan medicinal plants in the qinghai tibet plateau |
| topic | Gentiana szechenyii Gentiana veitchiorum Unmanned aerial vehicle remote sensing (UAVRS) Deep learning Medicinal plant |
| url | http://www.sciencedirect.com/science/article/pii/S235198942400088X |
| work_keys_str_mv | AT chenghuiwang usinguavrsanddeeplearningtoconductresourcesurveysofthreatenedtibetanmedicinalplantsintheqinghaitibetplateau AT ziyili usinguavrsanddeeplearningtoconductresourcesurveysofthreatenedtibetanmedicinalplantsintheqinghaitibetplateau AT rongding usinguavrsanddeeplearningtoconductresourcesurveysofthreatenedtibetanmedicinalplantsintheqinghaitibetplateau AT jiaweiluo usinguavrsanddeeplearningtoconductresourcesurveysofthreatenedtibetanmedicinalplantsintheqinghaitibetplateau AT yuliang usinguavrsanddeeplearningtoconductresourcesurveysofthreatenedtibetanmedicinalplantsintheqinghaitibetplateau AT ruigu usinguavrsanddeeplearningtoconductresourcesurveysofthreatenedtibetanmedicinalplantsintheqinghaitibetplateau AT shihongzhong usinguavrsanddeeplearningtoconductresourcesurveysofthreatenedtibetanmedicinalplantsintheqinghaitibetplateau |