Journal article
Hierarchical Multi-Scale Convolutional Neural Networks for Hyperspectral Image Classification
Sensors (Basel, Switzerland), Vol.19(7), p.1714
04/01/2019
DOI: 10.3390/s19071714
PMCID: PMC6480716
PMID: 30974816
Abstract
Deep learning models combining spectral and spatial features have been proven to be effective for hyperspectral image (HSI) classification. However, most spatial feature integration methods only consider a single input spatial scale regardless of various shapes and sizes of objects over the image plane, leading to missing scale-dependent information. In this paper, we propose a hierarchical multi-scale convolutional neural networks (CNNs) with auxiliary classifiers (HMCNN-AC) to learn hierarchical multi-scale spectral-spatial features for HSI classification. First, to better exploit the spatial information, multi-scale image patches for each pixel are generated at different spatial scales. These multi-scale patches are all centered at the same central spectrum but with shrunken spatial scales. Then, we apply multi-scale CNNs to extract spectral-spatial features from each scale patch. The obtained multi-scale convolutional features are considered as structured sequential data with spectral-spatial dependency, and a bidirectional LSTM is proposed to capture the correlation and extract a hierarchical representation for each pixel. To better train the whole network, weighted auxiliary classifiers are employed for the multi-scale CNNs and optimized together with the main loss function. Experimental results on three public HSI datasets demonstrate the superiority of our proposed framework over some state-of-the-art methods.
Details
- Title: Subtitle
- Hierarchical Multi-Scale Convolutional Neural Networks for Hyperspectral Image Classification
- Creators
- Simin Li - Tsinghua UniversityXueyu Zhu - University of IowaJie Bao - Tsinghua University
- Resource Type
- Journal article
- Publication Details
- Sensors (Basel, Switzerland), Vol.19(7), p.1714
- DOI
- 10.3390/s19071714
- PMID
- 30974816
- PMCID
- PMC6480716
- NLM abbreviation
- Sensors (Basel)
- ISSN
- 1424-8220
- eISSN
- 1424-8220
- Publisher
- MDPI
- Number of pages
- 20
- Grant note
- Beijing Innovation Center for Future Chips Beijing National Research Center for Information Science and Technology
- Language
- English
- Date published
- 04/01/2019
- Academic Unit
- Mathematics
- Record Identifier
- 9984241040302771
Metrics
25 Record Views