CAJ | 학술논문

为了提高大雾天气下采集图像的对比度和能见度，提出一种基于域变换递归滤波的图像复原方法。该方法在大气散射模型的基础上，对大气耗散函数的约束条件进行空间域的变换以实现维数降低，然后经过递归滤波之后获取较准确的结果，最后求解雾图成像方程，并对复原结果进行局部的线性映射调整，获得理想的清晰图像。该方法在场景深度跳变的边缘处可以获得更自然的复原效果，而且能很好地突出图像中的细节信息。实验结果表明，通过该方法得到的结果相比于传统的单幅图像去雾方法，视觉效果更佳、执行速度更快，并且该方法可以并行计算，因此采用GPU进一步加速能够满足实时处理视频的需求。
위료제고대무천기하채집도상적대비도화능견도，제출일충기우역변환체귀려파적도상복원방법。해방법재대기산사모형적기출상，대대기모산함수적약속조건진행공간역적변환이실현유수강저，연후경과체귀려파지후획취교준학적결과，최후구해무도성상방정，병대복원결과진행국부적선성영사조정，획득이상적청석도상。해방법재장경심도도변적변연처가이획득경자연적복원효과，이차능흔호지돌출도상중적세절신식。실험결과표명，통과해방법득도적결과상비우전통적단폭도상거무방법，시각효과경가、집행속도경쾌，병차해방법가이병행계산，인차채용GPU진일보가속능구만족실시처리시빈적수구。
In order to improve contrast and visibility of haze image captured in the foggy weather,this paper proposed an image restoration algorithm using domain transform recursive filter.Based on the atmospheric scattering model,the proposed method firstly reduced the image dimensions of physical constraint through domain transform,and then obtained the accurate atmos-pheric veil by performing the recursive filter.Finally the clear image was recovered by solving the physical equation of haze image and enhanced by a local linear mapping.The proposed algorithm not only got more natural effectiveness at the edge of places where scene depth changed abruptly,but also effectively highlighted detail information of recovered image.Experimental results show that comparing with traditional single image haze removal methods,the proposed method has better visual effect and faster execution speed.Furthermore,the algorithm can be performed in parallel,so it can be accelerated using GPU and satisfy real-time applications.