PDF
Full
Outline
Coconut is an important economic crop in tropics. The area of coconut palm in Hainan Island accounts for 90% of the total production area in China. Up-to-date maps of coconut palm are essential for the industrial planning of tropical agriculture. In this study, an object-oriented image analysis method was used for mapping coconut palms based on high spatial resolution imagery of Gaofen-2. Dongjiao town in Wenchang was selected as the study area. An optimal segmentation scale of Gaofen-2 imagery was obtained using the fractal evolution approach. Then, a combined layer of four original bands, five vegetation indices and 32 gray-level co-occurrence (GLCM) texture indices were used as input features. Four different sets of features (including only original bands, original bands and textures indices, original bands and vegetation indices, and all features) were applied in object-based classification. The overall accuracy (OA) and user’s accuracy (UA) of pixel-based method achieved 87.05% and 85.21%, respectively. Compared with the pixel-based method, the object-based approaches significantly increased overall accuracy (OA) between 5.51%-8.72%. The OA and user’s accuracy (UA) reached 95.77% and 97.15% respectively, which was the optimal classification result, when the combination of original bands and textural features were used in coconut palms classifying. In addition, the combination of original bands and vegetation indexes achieved a satisfactory accuracy (OA=94.88% and UA=94.42%). While the combination of original bands, vegetation indexes and textural indexes performed a lower accuracy (OA=94.67% and UA=94.17%) in comparison with that of above two combination. Generally, our researches indicate that Gaofen-2 imagery has a good potential for coconut palms classification in complex tropical regions, and the textural indexes are very useful for identifying coconut palms at object-based level. The results would provide a reference framework for tropical agriculture decision management.
PDF
132
70
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62199257
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
