GREENHOUSE EXTRACTION FROM HIGH-RESOLUTION REMOTE SENSING IMAGERY WITH IMPROVED RANDOM FOREST
文献类型: 外文期刊
第一作者: Feng, Tianjing
作者: Feng, Tianjing;Cheng, Xinwen;Ma, Hairong
作者机构:
关键词: Random Forest; maximum voting entropy; generalized Euclidean distance; high-resolution remote sensing imagery; greenhouse identification
期刊名称:IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM
ISSN: 2153-6996
年卷期: 2020 年
页码:
收录情况: SCI
摘要: The timely and accurate acquisition of greenhouses and their distribution from remote sensing imagery is valuable for Chinese authorities seeking to optimize regional agricultural management and mitigate environmental pollution. However, greenhouses are uncommon background objects in such imagery, making them a minority class that traditional random forest (RF) methods struggle to classify accurately in unbalanced data sets. Herein, we propose and test an improved RF sample selection method. Equal sample numbers were randomly selected from minority and majority classes to build an original training set for RF modeling. High-quality samples were then automatically added to the training set according to the voting entropy and generalized Euclidean distance, which are based on sample characteristic parameters. The results demonstrate that our improved RF yields better results in identifying greenhouses than the traditional RF. In addition, our method can be utilized to identify other minority-class objects from remote sensing imagery.
分类号:
- 相关文献
作者其他论文 更多>>
-
Farmland parcel boundary extraction based on local feature extraction and sparse representation from remote sensing images
作者:Zheng, Mingxue;Chen, Pingting;Shen, Xiangcheng;Luo, Hongmei;Luo, Zhiqing;Ma, Hairong;Zheng, Mingxue;Huang, Fenghua;Zheng, Mingxue;Zheng, Mingxue;Luo, Hongmei;Huang, Fenghua
关键词:Feature extraction; sparse representation; farmland parcel boundary extraction; remote sensing images; agricultural application
-
A Knowledge-Based Multi-Scale Adaptive Classification Approach for Mobile Laser Scanning Point Clouds in Urban Scenes
作者:Zheng, Mingxue;Shen, Xiangcheng;Luo, Zhiqing;Chen, Pingting;Guan, Bo;Yi, Jicheng;Ma, Hairong
关键词:Geometrical Eigen-features; adaptive; multi-scale; knowledge; classification; MLS point cloud; urban scene; transfer learning
-
Greenhouse extraction with high-resolution remote sensing imagery using fused fully convolutional network and object-oriented image analysis
作者:Ma, Hairong;Shen, Xiangcheng;Luo, Zhiqing;Chen, Pingting;Guan, Bo;Feng, Tianjing
关键词:remote sensing; deep learning; fully convolutional network; object-oriented image analysis; greenhouse extraction
-
Land-cover classification of high-resolution remote sensing image based on multi-classifier fusion and the improved Dempster-Shafer evidence theory
作者:Feng, Tianjing;Cheng, Xinwen;Ma, Hairong
关键词:high-resolution remote sensing image; classifier fusion; Dempster-Shafer evidence theory; image classification
-
Calculation of the optimal segmentation scale in object-based multiresolution segmentation based on the scene complexity of high-resolution remote sensing images
作者:Feng, Tianjing;Cheng, Xinwen;Zhang, Hongping;Ma, Hairong
关键词:object-based image analysis; high-resolution remote sensing images; optimal segmentation scale; scene complexity