Infrared image vehicle detection method based on auxiliary road information and significance detection

Abstract

The invention relates to an infrared image vehicle detection method based on auxiliary road information and significance detection. According to the method, at first, a gauss pyramid is used for carrying out background evaluation on a source image, and high-frequency information obtained by subtracting a background evaluation image from the source image comprises targets and background clutter; OTSU threshold segmentation is carried out on the source image to obtain a binary image to serve as estimation of the road information; an interest area can be obtained through collation operation of the high-frequency information and the road information; the significance detection is carried out on the center and the peripheral area of the interest area; track relevance is carried out on the candidate targets, and therefore the vehicle targets can be well extracted.

Description

technical field [0001] The invention relates to an infrared image vehicle detection method based on road auxiliary information and saliency detection. Background technique [0002] Infrared target detection has always been the core technology of infrared detection systems, and it is also a hot spot and difficulty in infrared image processing. Its research mainly includes two aspects: one is from the aspect of system; the other is from the aspect of image processing. In the infrared target detection algorithm, the detection algorithm should have a high detection probability and a low false alarm probability; it should meet the real-time requirements of signal detection. A branch of infrared target detection is infrared vehicle target detection. In an infrared surveillance system, if suspicious vehicles in the surveillance area can be automatically detected, it will greatly reduce the input of manpower and material resources. Therefore, this method has a strong application ba...

AI Technical Summary

Problems solved by technology

However, the optical flow method relies on the accuracy of optical flow estimation and has a large amount of calculation; the time difference method is fast, but generally cannot completely extract all the relevant feature pixels, and it is easy to produce holes inside the moving entity; the background subtraction method is not suitable for dynamic scenes. are particularly sensitive to changes in weather, light, and tree disturbances

[0005] To sum up, traditional target detection methods usually use global information and have some constraints while ignoring road information, or can only detect weak infrared targets, and cannot achieve better results in vehicle detection.

Images