The performance of environmental monitoring heavily depends on the availability of consecutive observation data and it
turns out an increasing demand in remote sensing community for satellite image data in the sufficient resolution with
respect to both spatial and temporal requirements, which appear to be conflictive and hard to tune tradeoffs. Multiple
constellations could be a solution if without concerning cost, and thus it is so far interesting but very challenging to
develop a method which can simultaneously improve both spatial and temporal details. There are some research efforts
to deal with the problem from various aspects, a type of approaches is to enhance the spatial resolution using techniques
of super resolution, pan-sharpen etc. which can produce good visual effects, but mostly cannot preserve spectral
signatures and result in losing analytical value. Another type is to fill temporal frequency gaps by adopting time
interpolation, which actually doesn't increase informative context at all. In this paper we presented a novel method to
generate satellite images in higher spatial and temporal details, which further enables satellite image time series
simulation. Our method starts with a pair of high-low resolution data set, and then a spatial registration is done by
introducing LDA model to map high and low resolution pixels correspondingly. Afterwards, temporal change
information is captured through a comparison of low resolution time series data, and the temporal change is then
projected onto high resolution data plane and assigned to each high resolution pixel referring the predefined temporal
change patterns of each type of ground objects to generate a simulated high resolution data. A preliminary experiment
shows that our method can simulate a high resolution data with a good accuracy. We consider the contribution of our
method is to enable timely monitoring of temporal changes through analysis of low resolution images time series only,
and usage of costly high resolution data can be reduced as much as possible, and it presents an efficient solution with
great cost performance to build up an economically operational monitoring service for environment, agriculture, forest,
land use investigation, and other applications.
|