A novel framework combining band selection algorithm and improved 3D prototypical network for tree species classification using airborne hyperspectral images
Authors:
- Jing WuJWJing Wu
- Long ChenLCLong Chen
- Jiaqi WangJWJiaqi Wang
- Yunfan LiYLYunfan Li
- Erxue ChenECErxue Chen
- Xiaoli ZhangXZXiaoli Zhang
- 8 March 2024
- journal article
- research article
- Published by Elsevier in Computers and Electronics in Agriculture
- Vol. 219
Abstract
No abstract availableKeywords
This publication has 27 references indexed in Scilit:
- Dry bean cultivars classification using deep cnn features and salp swarm algorithm based extreme learning machineComputers and Electronics in Agriculture, 2022
- Digital mapping of coffee ripeness using UAV-based multispectral imageryComputers and Electronics in Agriculture, 2022
- A deep learning image segmentation model for agricultural irrigation system classificationComputers and Electronics in Agriculture, 2022
- Tree species classification from airborne hyperspectral and LiDAR data using 3D convolutional neural networksRemote Sensing of Environment, 2021
- Genetic algorithm-based method for forest type classification using multi-temporal NDVI from Landsat TM imageryAnnals of GIS, 2018
- A novel approach for vegetation classification using UAV-based hyperspectral imagingComputers and Electronics in Agriculture, 2018
- Convolutional neural networks for hyperspectral image classificationNeurocomputing, 2017
- Learning multiscale and deep representations for classifying remotely sensed imageryISPRS Journal of Photogrammetry and Remote Sensing, 2016
- Principal component analysisWIREs Computational Statistics, 2010
- A joint band prioritization and band-decorrelation approach to band selection for hyperspectral image classificationIEEE Transactions on Geoscience and Remote Sensing, 1999