MIR Project

Project Title   Multiple Image Registration
Project Acronym   MIR
Contractor(s)   NCC - Norwegian Computing Center (Norway)


Project Context
          How it Works


Context   Top

The study of time series of satellite images is an important task in many remote sensing applications where the objective is to study different environmental phenomena. For such applications a co-registration of the satellite images acquired at different times are important. This co-registration is often performed using a combination of manual and automatic registration techniques. However, for a multi-temporal problem where the number of images becomes large, manual correction of images is not feasible. Hence, a fully automatic procedure would be desirable.

Automatic techniques for performing each step of the process do exist, but there is no one registration technique that works equally well for all image types. The selection of the appropriate method depends on the application and the image specifics. Hence, a single registration scheme will generally not work for all different applications. Consequently there exists a large number of different automatic registration techniques, all of which essentially perform the same task, the only difference being that they are constrained to working with a very small range of images.

For a user that needs to work on different types of time series, it would be useful to have a more general tool for image registration, that could be used for several applications. It has been estimated that more than 90% of the studies in remote sensing that could have used automated approaches for registration of images, did not use it. The lack of a more general tool for helping in this process, may be one of the reasons for this.



Objectives   Top

The objective of the MIR-project is to develop a tool for automatic co-registration of homogeneous sequences of images, i.e. time series of images resulting from the same (or similar) sensor with comparable resolution. The tool is intended to be general. This means that it should be able to handle images from different sensors, with different contents and acquired under different conditions.

As each sensor has its specifics concerning which features that can be extracted, which distortions that may appear and which types of noise that can be expected, no single registration scheme will generally work satisfactorily for all cases. To provide an automatic and general tool it is therefore necessary to include a number of different methods and intelligence that enables the system to select the most appropriate methods based on image characteristics and/or prior information.

The process of co-registration involves several steps, and one of the objectives will be to select and integrate existing methods and tools for all the steps needed for the process. In addition, functionality for analysing the image characteristics and for automatically deciding on the appropriate set of methods to be applied for each problem will need to be developed. This latter functionality will be the key feature of the system.



Architecture   Top

The toolbox will be composed of several components. The list below gives a preliminary overview of the basic components:

     Image Control function and user interface
     Image Decision logic
     Image Feature extractor
     Image Feature matcher
     Image Transformation

The final architecture will be defined later in the project.



How it Works   Top

The MIR tool with perform the task of co-registering time series of images by registering a sensed image to a reference image. The co-registration will be performed automatically without manual intervention.

To be able to perform this task for different types of images, resulting from different sensors, the tool will contain a selection of different methods for image registration that accounts for different types of image characteristics. To be able to choose a suitable registration scheme for each time series of images, image characteristics will be analysed.

The software tool is intended to perform the following tasks:

  Image Analyse image characteristics and decide on the appropriate methods to be used for the problem.
  Image Use the identified methods to automatically extract tie-points from the image, and find the registration transform from the set of tie-points.
  Image Produce the co-registered images or displacement maps.


Output   Top

MIR will provide a prototype software tool for automatic image registration of time series of images. The tool is intended to include a small selection of different methods for image registration in addition to intelligence that enables automatic selection of the methods most appropriate for each time series. The image registration tool is intended for expert users, with a technical background and good understanding of remote sensing imagery and of the problem of image registration.

The MIR final presentation was held at ESRIN on June 28, 2005.


Contributors to this page: andreadv .

Page last modified on Wednesday 15 of December 2010 16:08:03 CET by andreadv.