A Method for Detection, Tracking and Recognition of Small Infrared Targets

Abstract

The invention discloses an infrared small target detection tracking and identification method. Two different tree building methods of Max-tree and Min-tree are used for respectively detecting targetswith different brightness, the Max-tree mainly aims at a target of which the gray value is brighter than that of a background, and the Min-tree is mainly used for a target of which the gray value is darker than that of the background; two most significant features of the infrared small target, namely size information of the infrared small target and contrast information between the small target and the background, are extracted by using two attributes of an area attribute and a height attribute; and finally, tracking of the small target is realized through Mean-shift. The method has the following advantages: in the Max-tree and Min-tree, discontinuous pruning strategies are respectively used for two attributes, and results obtained by different pruning values under the same attribute and results obtained by different attributes are fused through different fusion strategies.

Description

technical field [0001] The present invention relates to the technical field of target detection, tracking and recognition of airborne photoelectric radar system, and in particular to a method based on multi-attribute morphology suitable for real-time and real-time monitoring of multiple types of targets collected by infrared sensors in the air, ground and sea on modern aircraft equipment. Accurate detection, tracking and identification methods. Background technique [0002] Modern aircraft are equipped with airborne optoelectronic systems, which include ultraviolet, visible light, near-infrared, short-wave infrared, medium / long-wave infrared, etc. in terms of spectral band division. The main functions of modern aircraft equipped with airborne optoelectronic systems are air target detection and tracking, ground target search and tracking, battlefield situation awareness, missile incoming warning, auxiliary navigation, takeoff and landing, etc. It mainly consists of the follo...

AI Technical Summary

Problems solved by technology

[0004] The inherent resolution of the infrared band and the effect of atmospheric absorption and scattering in the transmission process make the infrared image lack good contrast and resolution, and it is difficult to reflect the texture information of the target

The target area in the infrared image is small, limited by the physical performance of the infrared imaging equipment, so that the signal-to-noise ratio of the infrared small target image is usually low, and the feature information of the texture contour is less

At the same time, the background contains a lot of noise and clutter, and the target is easily submerged in the background noise and clutter, which brings many difficulties to detection, tracking and recognition.

At present, many algorithms have been proposed for the detection, tracking and recognition of small infrared targets, such as the algorithm that combines Top-hat algorithm, genetic algorithm and particle filter algorithm, but the design of the above algorithms is relatively simple, and the performance of target tracking is not good. ; According to the local characteristics of small infrared targets, a small target tracking algorithm based on PDAF and linear prediction is proposed. This method solves the problem of small target tracking failure due to noise interference or occlusion by objects, but the false alarm rate is still high ; Algorithms combining Probabilistic Multiple Hypothesis Tracking (PMHT) and Interactive Multiple Models (IMM) for tracking multiple maneuvering and non-maneuvering targets in infrared images; Proposed identification based on multi-sensor small target information fusion based on evidence theory method for identifying small objects

Although there are many algorithms, they are basically unable to completely solve the problems in the detection, tracking and identification of targets collected by infrared sensors on modern aircraft equipment. They can only be used for specific situations and cannot be widely used.

Images