红外与可见光图像融合的汽车抗晕光系统

发布时间：2018-04-06 00:21

  本文选题：抗晕光　切入点：图像融合　出处：《红外与激光工程》2017年08期

【摘要】：针对夜间汽车晕光现象引起的交通安全问题,从规避碰撞物的角度出发,设计了一种红外与可见光图像融合的视频抗晕光系统。系统通过对可见光图像和红外图像做MSR图像增强,解决了夜间可见光图像亮度低,暗处信息不易获取的问题,并提高了红外图像对比度,提升了融合图像的清晰度;通过YUV与小波变换结合的方式对增强后的可见光图像和红外图像进行融合,消除了晕光现象。实验结果的主客观分析表明:该融合算法比YUV与小波融合算法在熵、均值、平均梯度、标准差上分别提高了1.6%、13.5%、25.3%、0.6%,该系统不仅能有效消除晕光,还对融合后图像的亮度和暗处细节信息有较大提升,提高了夜间驾驶安全性。
[Abstract]:Aiming at the traffic safety problem caused by the phenomenon of vehicle halo at night, a video anti-halo system based on the fusion of infrared and visible images is designed from the point of view of avoiding collision objects.By enhancing the visible and infrared images with MSR, the system solves the problems of low brightness of the night visible images and difficult to obtain the information in the dark, and improves the contrast of infrared images and the sharpness of the fused images.Through the combination of YUV and wavelet transform, the enhanced visible and infrared images are fused and the halo phenomenon is eliminated.The subjective and objective analysis of the experimental results shows that the proposed fusion algorithm can improve the entropy, mean value, average gradient and standard deviation of the YUV and wavelet fusion algorithm by 1.6 and 13.5and 25.30.The system can not only effectively eliminate the halo, but also can eliminate the halo effectively.It also improves the brightness and dark details of the fused image and improves the safety of night driving.
【作者单位】： 西安工业大学电子信息工程学院;
【基金】：陕西省教育厅科研计划(11JK0989)
【分类号】：TP391.41;U463.6
，

本文编号：1717136