Learning a Transform Base for the Multi- to Hyperspectral Sensor Network with K-SVD

Abstract

A promising low-cost solution for monitoring spectral information, e.g., on agricultural fields, is that of wireless sensor networks. In contrast to remote sensing, these can achieve more continuous monitoring due to their long-term deployment and are less impacted by the atmosphere, making them a promising solution for the calibration of satellite data. In this paper, we explore an alternative approach for processing data from such a network. Hyperspectral sensors were found to be too complex for such a network. While previous work considered fusing the data from different multispectral sensors in order to derive hyperspectral data, we shift the assessment of the hyperspectral modeling in a separate preprocessing step based on machine learning. We then use the learned data as additional input while using identical multispectral sensors, further reducing the complexity of the sensors. Despite requiring careful parametrization, the approach delivers hyperspectral data of similar and in some cases even better quality.

Complementary Use of Ground-Based Proximal Sensing and Airborne/Spaceborne Remote Sensing Techniques in Precision Agriculture: A Systematic Review

“…The grouping helps to provide a summary of the challenge in a form that is quick and easy on the eye and captures how many works have mentioned it in the past. [142,159,160] Limitations due to the viewing angle [57] Future research More research on transforming image classification maps into application maps [121] Orthomosaic accuracy [161] Connectivity [142,148] Different device cooperation [142,162] Need to make satellites more approachable for farmers [155]…”

Design and Verification of Deep Submergence Rescue Vehicle Motion Control System

“…As shown in Figure 4 , the unit of filtering completes sparse representation and sparse reconstruction of data. In the unit of dictionary learning and training, the dictionary is constructed with learning and training via the K-singular value decomposition (K-SVD) algorithm [ 60 , 61 ]. The raw data are processed by sparse representation and reconstruction in accordance with the dictionary to realize data filtering.…”