FPGA-based infrared salient object detection method

Abstract

The invention provides an FPGA-based infrared salient object detection method. The method comprises the following steps of: 1, acquiring an image A1; 2, carrying out threshold value segmentation on the acquired image to obtain an image A2; 3, carrying out edge detection on A2 to obtain an image A3; 4, marking a connected domain on A3 to obtain an image A4; 4, for the connected domain in A4, obtaining a feature matrix which takes borders of the connected domain as features; 6, judging whether the feature matrix corresponding to the connected domain is a salient object or not through a restriction manner, the restriction manner comprises field of view restriction, grayscale restriction and duty cycle restriction; 7 carrying cross merging on the connected domain which passes through the restriction to obtain a new connected domain feature matrix; and 8, outputting images in a border value corresponding to the cross merged connected domain feature matrix. The method provided by the invention is capable of detecting salient objects in complicated scenes, so as to improve the detection precision while ensuring the timeliness and stability.

Description

technical field [0001] The invention relates to an infrared image processing technology, in particular to an FPGA-based infrared prominent object detection method. Background technique [0002] Infrared imaging has the advantages of good penetrating ability, strong anti-interference ability, and can work day and night. The salient object detection technology based on infrared imaging is widely used in military systems such as guidance, tracking, and early warning. The real-time performance, stability and precision of salient object detection methods will directly affect the reliability of military systems. However, the infrared image information is single, the contrast is low, and there are situations such as weak signal and complex background, which cause great difficulties for detection. Therefore, there is an urgent need to develop salient object detection systems and methods suitable for infrared images. [0003] The infrared target detection algorithm proposed by Wu Y...

AI Technical Summary

Problems solved by technology

[0003] The infrared target detection algorithm proposed by Wu Yanru et al. in the literature (Adaboost infrared target detection using KPCA feature extraction [J]. Infrared and Laser Engineering, 2011, 40(2): 338-343.) has better performance than traditional algorithms. Robustness and accuracy, but the complexity of the algorithm is high, and the implementation effect on the hardware platform needs to be verified

[0004] The target detection and tracking method proposed by Stolkin et al. (Particle filter tracking of camouflaged targets by adaptive fusion of thermal and visible spectrum camera data [J]. IEEE Transactions on Sensors Journal, 2013, 99:1-8.) is effective for camouflaged targets. Good detection effect, but this method is based on visible light and infrared fusion images. When implemented on a hardware platform, the complexity of the system is high and the stability is difficult to guarantee

[0005] CN201310031758.7 adopts DSP processor, although it can realize moving target detection, but because a single DSP does not possess parallel processing capability, the processing time is relatively long, and the system structure based on DSP is complicated, and the power consumption is high, which is unfavorable for being applied in the military system

[0006] CN201410450244.X adopts an infrared target detection method based on FPGA, which can improve the real-time performance of the detection system, but only for small target detection, it is difficult to detect each significant object in a complex scene, and it is not universal

Images