Multiscale infrared target adaptive detection method based on visual reception field

Abstract

The invention discloses a multiscale infrared target adaptive detection method based on the visual reception field, relates to a multiscale infrared target adaptive detection method, and belongs to the technical field of machine vision. A calculation differential operator of an edge detector is used to calculate the gradient direction theta of an image, and an orientation information distribution map of pixel points is obtained; a local background is predicted according to background information similar to local characteristic in the infrared image; a mathematical model Gabor filter in the simple cell reception field is used to filter an object image, an object is detected preliminarily, and a direction parameter theta of the Gabor filter is determined adaptively by orientation information distribution of the pixel points; and the gray scales of the pixel points are adjusted to obtain a background inhibited and object enhanced image, and the detection precision is improved. According to the invention, the robustness, anti-interference capability and adaptability, to different scales of object, of the infrared object detection method can be improved, and the operand is low.

Description

technical field [0001] The invention relates to a multi-scale infrared target adaptive detection method, in particular to a multi-scale infrared target adaptive detection method based on a visual receptive field, and belongs to the technical field of computer vision. Background technique [0002] In the field of infrared target detection, there are currently two main problems: (1) Due to the interference of smoke, clouds, the relative movement of the target and the carrier, and human factors, the background clutter in the infrared image is becoming more and more complex. (2) In general, when the target distance is far away, it appears as a small target, and when the target distance is relatively close, it appears as a surface target. Therefore, in order to accurately identify and track infrared targets under moving conditions, the infrared target detection algorithm needs to be applicable to both small targets and area targets. However, the current conventional infrared tar...

AI Technical Summary

Problems solved by technology

[0002] In the field of infrared target detection, there are currently two main problems: (1) Due to the interference of smoke, clouds, the relative movement of the target and the carrier, and human factors, the background clutter in the infrared image is increasingly complex

[0003] Although the existing target detection algorithms based on human vision mechanism have made significant progress in improving the robustness of infrared target detection algorithms, background clutter and noise suppression capabilities, there are still some limitations.

For example: the document "Infrared dim target detection based on visual attention, InfraredPhys.Technol.55, 513-521 (2012)" proposes a method for detecting weak and small infrared targets based on the visual attention mechanism. Although the detection accuracy and speed are high, this method only It is suitable for small infrared targets and cannot detect surface targets

The literature "Small target detection utilizing robust methods of the human visual system for IRST, J Infrared Millim Terahertz Waves. 30, 994–1011 (2009)" proposed a target detection method based on the Human Visual System (HVS) contrast mechanism, although compared to Traditional detection algorithms have made some progress, but their robustness in detecting infrared targets in complex backgrounds is poor

Images