Next Article in Journal
Close-Range Photogrammetry and Infrared Imaging for Non-Invasive Honeybee Hive Population Assessment
Previous Article in Journal
Nesting Patterns of Loggerhead Sea Turtles (Caretta caretta): Development of a Multiple Regression Model Tested in North Carolina, USA
Open AccessArticle

Joint Alternate Small Convolution and Feature Reuse for Hyperspectral Image Classification

College of Computer and Information, Hohai University, Nanjing 211100, China
*
Author to whom correspondence should be addressed.
The author contributed equally to this work and should be considered co-first author.
ISPRS Int. J. Geo-Inf. 2018, 7(9), 349; https://doi.org/10.3390/ijgi7090349
Received: 15 July 2018 / Revised: 23 August 2018 / Accepted: 24 August 2018 / Published: 26 August 2018
  |  
PDF [9329 KB, uploaded 26 August 2018]
  |  

Abstract

A hyperspectral image (HSI) contains fine and rich spectral information and spatial information of ground objects, which has great potential in applications. It is also widely used in precision agriculture, marine monitoring, military reconnaissance and many other fields. In recent years, a convolutional neural network (CNN) has been successfully used in HSI classification and has provided it with outstanding capacity for improving classification effects. To get rid of the bondage of strong correlation among bands for HSI classification, an effective CNN architecture is proposed for HSI classification in this work. The proposed CNN architecture has several distinct advantages. First, each 1D spectral vector that corresponds to a pixel in an HSI is transformed into a 2D spectral feature matrix, thereby emphasizing the difference among samples. In addition, this architecture can not only weaken the influence of strong correlation among bands on classification, but can also fully utilize the spectral information of hyperspectral data. Furthermore, a 1 × 1 convolutional layer is adopted to better deal with HSI information. All the convolutional layers in the proposed CNN architecture are composed of small convolutional kernels. Moreover, cascaded composite layers of the architecture consist of 1 × 1 and 3 × 3 convolutional layers. The inputs and outputs of each composite layer are stitched as the inputs of the next composite layer, thereby accomplishing feature reuse. This special module with joint alternate small convolution and feature reuse can extract high-level features from hyperspectral data meticulously and comprehensively solve the overfitting problem to an extent, in order to obtain a considerable classification effect. Finally, global average pooling is used to replace the traditional fully connected layer to reduce the model parameters and extract high-dimensional features from the hyperspectral data at the end of the architecture. Experimental results on three benchmark HSI datasets show the high classification accuracy and effectiveness of the proposed method. View Full-Text
Keywords: hyperspectral image classification; strong correlation among bands; convolutional neural network; alternate small convolutions; feature reuse hyperspectral image classification; strong correlation among bands; convolutional neural network; alternate small convolutions; feature reuse
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Gao, H.; Yang, Y.; Li, C.; Zhou, H.; Qu, X. Joint Alternate Small Convolution and Feature Reuse for Hyperspectral Image Classification. ISPRS Int. J. Geo-Inf. 2018, 7, 349.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
ISPRS Int. J. Geo-Inf. EISSN 2220-9964 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top