An infrared small target detection method based on graph structure analysis

Abstract

The application discloses an infrared small target detection method based on graph structure analysis, and the infrared target detection has important application value in the fields of military, security and air defense, but in practical application, it is difficult to distinguish real targets from various environmental interferences. The core idea of the application mainly embodies three aspects: firstly, the details of real targets and environmental interferences are strengthened by analyzing the node features of candidate targets; secondly, the overall difference between targets and interferences is obtained by using a node aggregation analysis module to extract convergence features; finally, based on the connection law of the graph, the node label set of adjacent nodes after sorting is used to expand the node label, and the expanded label is compressed into a reasoning module composed of new labels to analyze the global correlation of target and interference information, so that the recognition accuracy is further improved. The method can effectively distinguish target signals from interference signals, is suitable for infrared target detection tasks in complex scenes, and has high practicability and anti-interference ability.

Images