论文部分内容阅读
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。
Aiming at the traffic safety problem caused by the car dusk at night, this paper designs a video anti-corona system based on infrared and visible light image fusion from the perspective of avoiding collisions. By doing MSR image enhancement on visible light images and infrared images, the system solves the problem that the nighttime visible light image has low brightness and the darkness information is not easily accessible, and improves the contrast of the infrared image and improves the definition of the fused image. By combining the YUV and wavelet transform Way to the enhanced visible image and infrared image fusion, eliminating the halo phenomenon. The subjective and objective analysis of the experimental results show that the fusion algorithm improves the entropy, mean value, average gradient and standard deviation by 1.6%, 13.5%, 25.3% and 0.6% respectively than the YUV and wavelet fusion algorithms. This system not only can effectively eliminate the halo Light, but also the fusion of the image brightness and dark details of the information has greatly improved, improve driving safety at night.