一种面向目标跟踪性能的红外图像自适应增强方法

针对光照突变或强辐射源干扰条件下由于目标能量变化引起跟踪不稳定且易丢失的问题,提出了一种可适应目标能量突变的自适应红外图像增强预处理算法.首先通过最大极值稳定区域方法对目标进行检测,实时计算目标区域平均灰度,并通过最小二乘对下一帧目标均值进行预测,当检测到实时目标能量与预测均值能量突变超过一定阈值后,使用自适应增强方法重新预处理目标图像,使突变前后目标及其附近背景区域对比度保持稳定,然后通过核相关跟踪算法对目标能量变化前后的目标进行跟踪.实验结果证明,该增强算法能有效改善目标能量突变情况下目标跟踪的稳定性和准确性.

An Adaptive Enhancement Method for Infrared Image Based on Target Tracking Performance

Under radical change of illumination or strong radiation interference,target tracking is unstable and easy to be lost due to the change of target energy.In this paper,an infrared image enhancement preprocessing algorithm adapted to sudden change of target energy is proposed.Firstly,the target is detected by maximum extreme stability region and the average gray of target area is calculated in real time,at the same time,the mean value of the next frame is predicted by the least square method.When the change of real time target energy and predicted mean energy exceeds a certain threshold,the target image is reprocessed by adaptive enhancement method,keeping the contrast between the target and its surrounding background area stable before and after the change.Then the target before and after the change of energy is tracked by the kernel correlation tracking algorithm.Experimental results show that the proposed enhancement method can effectively improve the stability and accuracy of target tracking under the condition of radical change of target energy.