Object detection is an important application of optical satellite remote sensing imagery interpretation. Since the objects of interest, such as aircraft, ships, and vehicles, are small in size with obscure contour and texture, it is difficult for object detection in satellite images. The spatial resolution of aerial images is higher than satellite images, and the object detection model can achieve higher precision. Knowledge distillation has been validated as an effective technique by learning the common features of aerial and satellite images to improve the precision of object detection in satellite images. It means that a teacher model pre-trained on aerial image datasets guides the training of a compact student model on satellite image datasets. However, there are data distribution differences between aerial images and satellite images. The distribution differences may cause the teacher model to give guidance signals that deviate from the ground truth, thus leading to sub-optimization of the student model. In this paper, we proposed a new distillation scheme, termed DC-KD, which updates the teacher model using the predictions of the teacher model that are inconsistent with the ground truth, and the rest are used to guide the training of the student model. We achieved a 3.88% mAP50 improvement on the xView dataset based on the YOLOX-S model.
Because of the problem that the large amount of remote sensing data and the difficulty of feature selection lead to inaccurate land classification, we proposed a land classification algorithm based on attention u2net using hyperspectral technology. To solve the problem of a large amount of hyperspectral image data and high dimensionality, we adopted the LDA method for dimensionality reduction. To solve the problem that the traditional deep learning network does not focus enough on key areas, an attention u2net algorithm model is proposed, which uses an attention mechanism to strengthen the network’s learning on key areas to obtain better classification accuracy. We conducted experiments based on the existing three mainstream databases, and the results showed that the algorithm achieved an accuracy of 86.6% on the Indian Pines dataset, 95.2% on the Urban dataset, and 82.7% on the Fanglu dataset. Compared with other deep learning algorithms, the average improvement was 2.5%.
A Doppler asymmetric spatial heterodyne (DASH) interferometer was designed to measure atmospheric winds at a height of 60 to 80 km by observing the airglow emission line of molecular oxygen at 867 nm. The designed monolithic DASH interferometer exhibited decent thermal stability. The phase thermal drift of the fabricated interferometer obtained from thermal performance measurements was 0.376 rad / ° C. To accurately model and minimize the thermal drift performance of an interferometer in the design phase, it is necessary to include the influence of thermal distortion of the monolithic interferometer components. Therefore, an optical–structural–thermal integrated analysis method based on Zernike polynomials was proposed to accurately calculate the phase thermal drift of the interferometer. The optical model modified by the finite-element method calculated the phase thermal drift to be 0.420 rad / ° C, which agreed with the experimental result within 11.7%. This analysis method can accurately calculate and optimize thermal stability during the design of a DASH interferometer.
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.