搜索结果: 1-3 共查到“工学 Training Samples”相关记录3条 . 查询时间(0.078 秒)
BUILDING CLASSIFICATION OF VHR AIRBORNE STEREO IMAGES USING FULLY CONVOLUTIONAL NETWORKS AND FREE TRAINING SAMPLES
Building Classification VHR Airborne Stereo Images FCN Base Map Mislabels Free Training Samples Fine Tuning Atrous Convolution
2018/11/9
Semantic segmentation, especially for buildings, from the very high resolution (VHR) airborne images is an important task in urban mapping applications. Nowadays, the deep learning has significantly i...
PURIFICATION OF TRAINING SAMPLES BASED ON SPECTRAL FEATURE AND SUPERPIXEL SEGMENTATION
Beijing-2 Satellite imagery Training Samples Purification Spectral Feature Superpixel Segmentation
2018/5/14
Remote sensing image classification is an effective way to extract information from large volumes of high-spatial resolution remote sensing images. Generally, supervised image classification relies on...
UNLABELED SELECTED SAMPLES IN FEATURE EXTRACTION FOR CLASSIFICATION OF HYPERSPECTRAL IMAGES WITH LIMITED TRAINING SAMPLES
Hyperspectral images feature extraction limited training samples unlabeled samples selection supervised classification
2016/1/15
Feature extraction plays a key role in hyperspectral images classification. Using unlabeled samples, often unlimitedly available, unsupervised and semisupervised feature extraction methods show better...