Scene Recognizability Analysis Method Based on Conditional Evidence Theory

Abstract

The invention relates to a scene recognizability analysis method based on conditional evidence theory. The steps include: obtaining the DSM and DOM of the target and the scene where it is located, and setting imaging parameters; selecting prominent features as the nodes of the scene; The degree of recognizability under different observation angles is used as the basic reliability distribution of each node in the scene; the conditional reliability function that characterizes the mutual support between each node is defined through the contour points of the ground object, and the evidence theory is used to reason and integrate each node. node information to obtain the recognizability analysis results of the entire scene. The present invention makes full use of a plurality of prominent features in the scene, can judge in a quantified form which perspective of the scene can achieve the best scene recognition effect, solves the problem of evaluating the recognizability of the scene, and has great significance for task planning. significance.

Description

technical field [0001] The invention belongs to the technical field of remote sensing applications, and in particular relates to a scene recognizability analysis method based on conditional evidence theory. Background technique [0002] The method based on template matching is widely used in optical image automatic target recognition, in which the template is the key to target matching and recognition. A common practice is to prepare the template required to complete the target and the task at one time according to the flight track, sensor parameters and the geographical location of the target during mission planning, and store it in the database for real-time calling. Therefore, the accuracy and validity of the template is of paramount importance. Evaluating the degree of recognizability of the target or scene at different angles is used to determine the flight path and the viewing angle of the sensor during mission planning, select an angle with a higher degree of recogni...

AI Technical Summary

Problems solved by technology

Existing methods generally only analyze the target or scene at a given angle, and do not analyze the difference in the degree of recognizability of the target or scene under different viewing angles.

Images