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%.
To realize the long-period and automated data collection of lunar radiation and eliminate the geometric errors of the lunar hyperspectral image during the observation process, this paper proposes a slit-type spectrometer observation method based on the rotating table of the equatorial mount. This method uses a wide field finder-scope to realize automatic moon tracking and positioning; at the same time, it corrects the drift angle and oversampling of the collected raw data. The results show that the full moon situation is the same as the non-full moon situation. This method can effectively find and track the position of the moon's sphere center, and it also corrects the drift and over-sampling of the moon image, realizes accurate and automated long-term observation of the moon, reduces observation errors, and saves observation costs.
In recent years, the commercialized low-cost rotor UAV equipped with small hyperspectral camera has become an emerging way to acquire hyperspectral remote sensing data due to its advantages of convenient data acquisition and low cost, and has been widely used in environmental monitoring, precision agriculture, ocean development and other fields. Due to its light weight, the flight process of the rotor UAV is vulnerable to the influence of air flow, which leads to the poor stability of the platform and resulting in the geometric distortion of the imaging. This situation is particularly prominent in the obvious air flow areas such as the lake and the sea, which restricts the application in related fields. In this paper, the geometric processing of UAV-borne hyperspectral measured data collected at a wharf in Qiandao Lake is studied. There are two major factors lead to geometric error. One is the longitude and latitude step error, the other is the frame frequency of the navigation data is lower than the image exposure frame frequency. In this situation, this paper proposes a step fitting method to perform geometric correction and error correction for the hyperspectral airstrip data. Compared with the traditional Kalman filtering method and the global linear fitting method, the proposed method can better correct the geometric distortion of hyperspectral image caused by the low-precision GPS/INS system, which provides a foundation for the subsequent quantitative application of lightweight UAV hyperspectral camera in various fields.
The polarization of water-leaving radiance (Lw) is more sensitive to microphysical properties (e.g. particles shapes, size distributions, compositions, and refractive index) of hydrosols than the unpolarised radiance. Hence, the polarized Lw can be used to extract additional information on oceanic constituents, which is complementary to the spectral and angular radiance measurements. In this study, the polarization characteristics of underwater upwelling radiance in turbid waters with respect to suspended particulate matters have been investigated. The full Stokes components of the underwater upwelling radiance in the visible spectrum are calculated using a radiative transfer model. And then, the influences of suspended particulate matter concentrations on the directional variations and the polarization of underwater upwelling radiance are examined. The results reveal that the polarization of underwater upwelling radiance (I, Q, U, DOP) shows significant multidirectional variations with respect to observation geometries, wavelengths, and solar zenith angles. Moreover, the polarization of underwater upwelling radiance is highly related to the suspended particulate matter concentrations. It demonstrates the potential of using the polarized signal to retrieve particle concentrations in coastal waters. Therefore, the development of in-situ instrumentations and next generation of ocean color sensors should able to measure the polarization properties of water-leaving radiance are recommended.
The inversion of total suspended particulate matter (TSM) from ocean color remote sensing data in coastal waters is still highly inaccurate due to contributions of various oceanic constituents and non-linear independently variation of each other. Since the absorption and scattering by molecules, aerosols, and hydrosols and reflection, transmission over the sea surface, the initially completely unpolarized sunlight becomes partially polarized after transmitting in the coupled atmosphere-ocean system (AOS). Hence, the polarization of the sunlight, which contains embedded information on atmospheric and water optical properties, has largely been neglected. In addition, the parallel polarization radiance (PPR) has two significant advantages in effectively diminishing the sun-glint contamination and enhancing the ocean color signal at the top-of-atmosphere (TOA). In this study, the directional variations in parallel polarized water-leaving radiance of suspended particulate matters in coastal waters, based on the vector radiative transfer simulations (RT), were examined. The simulations reveal that the traditional radiation intensity (I) and parallel polarization radiance (PPR) display significant multidirectional and spectral variations with respect to the observation geometries, and TSM concentrations. Moreover, the water-leaving (Lw) radiance for I and PPR have the same angular distribution pattern and magnitude under different bands. In addition, the relative fraction of Lw to Lt for PPR is large than I, indicating that the PPR can improve to retrieve the Lw radiance at the TOA. Furthermore, an exponent relationship between the Rrs_p and the TSM concentration has been established with low corresponding AD (1.258%) and RMSE (0.202). It demonstrates that the polarization of the Lw radiance is closely related to oceanic constituents, and has great potential for the retrieval of TSM concentrations.
Hangzhou Bay waters are often characterized by extremely high total suspended particulate matter (TSM) concentration due to terrestrial inputs, bottom sediment resuspension and human activities. The spatial-temporal variability of TSM directly contributes to the transport of carbon, nutrients, pollutants, and other materials. Therefore, it is essential to maintain and monitor sedimentary environment in coastal waters. Traditional field sampling methods limit observation capability for insufficient spatial-temporal resolution. Thus, it is difficult to synoptically monitor high diurnal dynamics of TSM. However, the in-orbit operation of the world’s first geostationary satellite ocean color sensor, GOCI, thoroughly changes this situation with hourly observations of covered area. Taking advantage of GOCI high spatial-temporal resolution, we generated TSM maps from GOCI Level-1B data after atmospheric correction based on six TSM empirical algorithms. Validation of GOCI-retrieved normalized water-leaving radiances and TSM concentration was presented in comparison with matched-up in-situ measurements. The mean absolute percentage differences of those six TSM regional algorithms were 24.52%, 163.93%, 195.50%, 70.50%, 121.02%, 82.72%, respectively. In addition, the discrepancy reasons were presented, taking more factors such as diversified satellite data, various study area, and different research season into consideration. It is effective and indispensable to monitor and catch the diurnal dynamics of TSM in Hangzhou Bay coastal waters, with hourly GOCI observations data and appropriate inversion algorithm.
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.