Dataset List


Data Details

Bayberry Tree Recognition Dataset Based on the Aerial Photos and Deep Learning Model

WANG Dongliang1LUO Wei2
1 Key Laboratory of Land Surface Pattern and Simulation,Institute of Geographic Sciences and Natural Resources Research,Chinese Academy of Sciences,Beijing 100101,China2 Center for Intelligent Manufacturing Electronics,Institute of Microelectronics,Chinese Academy of sciences,Beijing 100029,China


Published:Jul. 2019

Visitors:11192       Data Files Downloaded:5816      
Data Downloaded:2153430.45 MB      Citations:

Key Words:

Bayberry tree,recognition,aerial photos,Mask RCNN


Bayberry (Myrica rubra) is an evergreen tree with 5-15 meters high; the diameter of the tree is about 60 cm at breast height and a crown of more than 5 meters. Bayberry tree is widely distributed in the southern of the Yangtze River Basin of China. Bayberry tree grows in acid red soil below 1500 meters above sea level and sunny mountain slopes. Its fruit is a special fruit with geographical characteristics in the southern of the Yangtze River Basin. The authors used the DJI Phantom 4 unmanned aerial systems (UAS) to take the aerial photography in Dayangshan Forest Park, Yongjia County, Zhejiang Province from January 23 to 24, 2019. Polygonal markers of Bayberry trees were then labeled before using a deep learning model, Mask RCNN (Mask Region Convolutional Neural Networks), to automatic identify the Bayberry trees. The recognized results were validated by visual interpretation method. The experimental results show that Mask RCNN has a high accuracy in bayberry tree recognition. The overall true positive rate is 90.08%, the false positive rate is 9.62%, and the loss positive rate is 9.92%. The experimental dataset of the presented bayberry tree recognition depth learning model includes: (1) 3080 UAS images captured in Dayangshan Forest Park, Yongjia County, Zhejiang Province, with an image size of 5472 x 3648; (2) Marked bayberry tree samples, including 298 image tiles; and (3) bayberry tree recognition results by the deep learning model, including 14 image tiles. The dataset is archived in .jpg and .json data formats, consists of 3690 data files with data size of 25.6 GB (Compressed to 71 files with data size of 25.5 GB).

Foundation Item:

Chinese Academy of Sciences (XDA23100200); Ministry of Science and Technology of P. R. China (2017YFC0506505, 2017YFB0503005)

Data Citation:

WANG Dongliang, LUO Wei. Bayberry Tree Recognition Dataset Based on the Aerial Photos and Deep Learning Model[J/DB/OL]. Digital Journal of Global Change Data Repository, 2019.

Wang, D. L., Luo, W. Bayberry tree recognition dataset based on the aerial photos and deep learning model [J]. Journal of Global Change Data & Discovery, 2019, 3(3): 290–296. DOI: 10.3974/geodp.2019.03.10.

Data Product:

ID Data Name Data Size Operation
1 2019012301DJI_0001_0045.rar 390148.71KB
2 2019012301DJI_0046_0090.rar 386880.60KB
3 2019012301DJI_0091_0135.rar 383433.07KB
4 2019012301DJI_0136_0180.rar 385836.97KB
5 2019012301DJI_0181_0225.rar 384990.89KB
6 2019012301DJI_0226_0270.rar 385843.81KB
7 2019012301DJI_0271_0315.rar 384423.68KB
8 2019012301DJI_0316_0360.rar 382506.70KB
9 2019012301DJI_0361_0405.rar 391586.20KB
10 2019012301DJI_0406_0450.rar 381119.18KB
11 2019012301DJI_0451_0495.rar 392540.71KB
12 2019012301DJI_0496_0540.rar 380082.59KB
13 2019012301DJI_0541_0585.rar 384477.90KB
14 2019012301DJI_0586_0630.rar 387799.41KB
15 2019012301DJI_0631_0675.rar 391076.25KB
16 2019012301DJI_0676_0706.rar 265366.62KB
17 2019012302DJI_0001_0045.rar 389837.42KB
18 2019012302DJI_0046_0090.rar 389554.29KB
19 2019012302DJI_0091_0135.rar 384170.83KB
20 2019012302DJI_0136_0180.rar 389633.20KB
21 2019012302DJI_0181_0225.rar 388971.57KB
22 2019012302DJI_0226_0270.rar 392062.79KB
23 2019012302DJI_0271_0315.rar 378904.41KB
24 2019012302DJI_0316_1037.rar 366883.68KB
25 2019012303DJI_0348_0395.rar 402468.34KB
26 2019012303DJI_0396_0440.rar 380138.07KB
27 2019012303DJI_0441_0485.rar 390461.77KB
28 2019012303DJI_0486_0530.rar 383887.29KB
29 2019012303DJI_0531_0575.rar 387327.38KB
30 2019012303DJI_0576_0620.rar 388411.67KB
31 2019012303DJI_0621_0665.rar 385966.48KB
32 2019012303DJI_0666_0710.rar 380282.63KB
33 2019012303DJI_0711_0755.rar 386078.51KB
34 2019012303DJI_0756_0800.rar 385972.48KB
35 2019012303DJI_0801_0845.rar 386370.12KB
36 2019012303DJI_0846_0890.rar 388559.26KB
37 2019012303DJI_0891_0935.rar 392699.23KB
38 2019012303DJI_0936_0980.rar 389068.46KB
39 2019012303DJI_0981_1026.rar 390316.57KB
40 2019012404DJI_0001_0045.rar 392582.51KB
41 2019012404DJI_0046_0090.rar 383983.56KB
42 2019012404DJI_0091_0135.rar 383928.67KB
43 2019012404DJI_0136_0180.rar 387807.10KB
44 2019012404DJI_0181_0225.rar 386374.58KB
45 2019012404DJI_0226_0270.rar 384787.39KB
46 2019012404DJI_0271_0315.rar 389367.76KB
47 2019012404DJI_0316_0360.rar 383759.72KB
48 2019012404DJI_0361_0405.rar 381986.68KB
49 2019012404DJI_0406_0450.rar 382063.79KB
50 2019012404DJI_0451_0495.rar 387724.90KB
51 2019012404DJI_0496_0517.rar 189437.64KB
52 2019012404DJI_c_0456_0500.rar 387512.15KB
53 2019012404DJI_c_0501_0545.rar 384850.90KB
54 2019012404DJI_c_0546_0590.rar 377279.56KB
55 2019012404DJI_c_0591_0635.rar 386890.12KB
56 2019012404DJI_c_0636_0680.rar 382878.41KB
57 2019012404DJI_c_0681_0725.rar 386443.59KB
58 2019012404DJI_c_0726_0770.rar 383997.82KB
59 2019012404DJI_c_0771_0815.rar 386824.22KB
60 2019012404DJI_c_0816_0860.rar 383287.71KB
61 2019012404DJI_c_0861_0905.rar 387484.28KB
62 2019012404DJI_c_0906_0950.rar 382200.85KB
63 2019012404DJI_c_0951_0999.rar 419955.56KB
64 2019012404DJI_s_0001_0046.rar 393235.43KB
65 2019012404DJI_s_0047_0092.rar 392265.50KB
66 2019012404DJI_s_0093_0138.rar 390232.41KB
67 2019012404DJI_s_0139_0184.rar 396945.60KB
68 2019012404DJI_s_0185_0230.rar 402081.64KB
69 2019012404DJI_s_0231_0277.rar 404442.44KB
70 Results_DLM.rar 14520.33KB
71 TrainingSamples.rar 348666.71KB