欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
暗原色先验去雾方法在单幅图像去雾方面效果明显，但该方法算法复杂度高、处理耗时。针对该算法不足之处，在传统的暗原色先验去雾方法基础上，提出一种改进算法。改进算法通过高斯滤波和腐蚀对透射率图进行优化；同时，为避免原算法的冗余计算，采用了一种快速计算初始透射率方法；并且通过Gamma变换和对比度增强方法对去雾后图像进行亮度和对比度增强处理。实验结果显示，改进算法处理效果与原算法基本一致，算法效率得到显著提高，应用在视频增强领域，可以达到准实时。
英文摘要：
The dark channel prior method is effective in single image dehazing. However, it is complexity-high and time-consuming. To solve this problem ,an improved method is proposed based on the original dark channel prior method. The transmission map is refined using Gaussian filter and corrosion. A fast method to calculate the initial transmission rate is proposed to avoid the original algorithm redundancy computing. And the image luminance and contrast are enhanced using Gamma transformation and contrast enhancement method. Experimental results show that the improved algorithm processing effect and the original algorithm are basically the same. However, the proposed method is more effective and it can be applied to the field of video enhancement in quasi-real-time.
同期刊论文项目
同项目期刊论文
A pioneering video-to-video super-resolution reconstruction algorithm based on segmentation and spac
Motion Compensated Frame Rate Up-conversion Using Soft-decision Motion Estimation and Adaptive-weigh
Single Remote Sensing Image Supper-resolution based on Sparse Representation Theory with Self-traine
期刊信息
位置：