Hyperspectral image (HSI) classification methods based on three-dimensional convolutional neural network (3DCNN) have problems of overfitting the in-sample training process and difficulty in highlighting the role of discriminant features, which reduce the classification accuracy. To solve the above problems, an HSI classification method based on M-3DCNN-Attention is proposed. First, the Mixup algorithm is used to construct HSI virtual samples to expand the original data set. The sample size of the expanded data set is twice that of the original data set, which greatly alleviates the overfitting phenomenon caused by the small sample of HSI. Second, the structure of 3DCNN is improved. A convolutional block attention module (CBAM) is added between each 3D convolutional layer and ReLU layer, and a total of three CBAMs are used so as to highlight the discriminant features in spectral and spatial dimensions of HSI and suppress the nondiscriminant features. Finally, the spectral–spatial features are transferred to the Softmax classifier to obtain the final classification results. The comparative experiments are conducted on three hyperspectral data sets (Indian Pines, University of PaviaU, and Salinas), and the overall accuracy of M-3DCNN-Attention is 99.90%, 99.93%, and 99.36%, respectively, which is better than the comparative methods.
KEYWORDS: Calibration, Temperature metrology, Pyrometry, Precision calibration, Black bodies, Solids, Sun, Signal to noise ratio, Aerospace engineering, Astronomical engineering
At present, Multi-spectral pyrometer (MSP) used in high-temperature measurement has already had
high resolution and high signal to noise ratio. However, the non-source temperature (higher than 3000°C) calibration falls far behind the development of MSP and has already seriously hindered the
precision and application range of the pyrometer. In order to break through the limitation of calibration
of non-source temperature, a new calibration method has been put forward in this paper. The
temperature-voltage (T-U) model is formed based on power function where output voltage U of the
MSP is derived from its corresponding known temperature point. Based on the model, Derivative least
square method is used to obtain the parameters of the model to realize the non-source temperature
calibration. Both theoretical and experimental data have proved the efficiency and precision of the
calibration method. In addition, within the spectral range of high-temperature measurement pyrometer
(0.4um~1.1um), the theoretical aberration within 1800°C extrapolation range is less than 13.54°C.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.