The semantic segmentation technology of remote sensing image refers to labeling the semantic information of pixel-level of the image to complete the classification, namely, terrain classification. It is widely used in intelligent maps, smart cities and other aspects. With the increase of satellite image resolution and the development video communication moonlet, its application and scenes are greatly broadened. The traditional remote sensing image semantic segmentation method mainly uses statistical machine learning methods, which cannot take into account the spectral features and the context semantic relationship of pixels, and has a bottleneck in improving the accuracy of classification. In deep learning method, Using the convolutional neural networks to extract features can achieve classification results of remote sensing images with higher classification accuracy. Aiming at the problems of existing deep learning methods in multi-spectral image semantic segmentation, to make full use of the information of multi-spectral images, this paper proposes a semantic segmentation algorithm for multispectral remote sensing images based on deep learning and verified the method on open data sets.
Electrostatic potential testing is an important parameter for characterization of the electrostatic source. A non-contact electrostatic potential test device is designed for zreo-point drift, interference effect, narrow frequency range and other common problems in the current non-contact electrostatic potential test device in this paper. The above problems such as zreo-point drift, interference effect and narrow frequency range are solved. The basic principle of non-contact electrostatic potential test is introduced. The hardware and software design and implementation process of non-contact electrostatic potential test device are described in detail. The test verification and application of the device are given. Finally the key technical problems solved in the design implementation process are summarized.
The problem of the reconstructed of different scene depth was analyzed in single-step holographic stereogram printing based on effective perspective images’ segmentation and mosaicking (EPISM). The reconstructed quality of short scene depth is bad. the causes of flipping effect in holographic stereogram are studied in detail, and the influence of flipping effect on image quality is alleviated by reducing the size of holographic element (Hogel). The curvature distortion of holographic stereogram is analyzed. The effect of curvature distortion on the reconstructed quality of holographic stereogram is verified by changing the distance of object protruding sampling plane. The theoretical analysis was verified experimentally with different scene depth. The reconstructed image of high quality and short scene depth was obtained, and the practicability of EPISM was improved.
Producing of conventional optical reflection hologram can be classified into one-step method and two-step method. In one-step method, only the diverging light of the object could be recorded, and the reconstructed scene is a virtual one behind the recording medium. In two-step method, the diverging light or the converging light could be recorded alternatively. However, the process is complicated considering double exposures. We propose a novel method of one-step reflection hologram. The object is first imaged by a 4f optical system, then the interference fringes are recorded by single exposure. The reconstructed image can be either a virtual image behind the recording medium, or a real image in front of the recording medium. The ideal imaging properties of 4f optical system have been demonstrated theoretically and the proposed method has been verified experimentally.
A spatial frequency index method is proposed to cull the occlusion in computer generated hologram. The object points with the same spatial frequency are put into a set, and only the point closest to the hologram is contributed to the hologram because of their mutual occlusion. The phases of corresponded spatial frequency are precomputed and stored in a table. The phases on the hologram are obtained from the table according to the spatial frequency of object point. Experiments are performed and the results demonstrate that the proposed method can cull the hidden surfaces of 3-D scene correctly. The occlusion effect can be well reproduced along with the speeding up of the calculation.
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.