ANALYSIS OF DYNAMICAL CHANGES FROM LARGE SET OF REMOTE SENSING IMAGES

Basic elements of changes on the multi-temporal satellite image and their basic sets of dynamic objects are formulated and defined, for which the main characteristics define the dynamic object as an area of motion. Such dependents of objects are inherited not only between objects and their dynamic groups. In such a case, the concept of dynamic objects in a multi-temporal sequence of satellite images has been developed based on the formalization of processes occurring on a change stream. A specific methodology has been developed to select a dynamic object from a dynamic group based on the analysis of the changing characteristics of the object's environment. It means that objects in a group have similar changing for separate characteristics. Such objects are included in specified ranges and are combined into dynamic groups. Characteristics dynamic group is characterized by changing every object of it. The monitoring is performed for such a group. The technique includes six stages: image acquisition and pre-processing, image scene segmentation and selection of regions, image scene analysis for segmented areas, control of compliance with the conditions for behavioral characteristics, and classification of the behavioral line of objects in the region. As a result, it is possible to describe the properties of the group's behavior and objects in the group as separate characteristics. The control of fulfillment of conditions for the behavioral characteristic is carried out to control the object as a dynamic group element. Thus, monitoring is carried out as a control for the motion of many objects rather than images.