CAJ | 학술논문

针对雾天图像降质带来的目标显著性检测难题，提出一种基于区域协方差特征的雾中目标显著性检测方法。该方法针对雾天图像的特点，提取亮度、梯度、空间位置以及对比度等信息形成协方差特征描述矩阵，通过不同尺度的分块对比获得局部显著子图。再将得到的局部子图结合得到最终的雾天图像显著图。实验表明相对于其它方法，论文方法对于雾天图像目标显著性检测具有很好的适应性、可拓展性和准确性。
침대무천도상강질대래적목표현저성검측난제，제출일충기우구역협방차특정적무중목표현저성검측방법。해방법침대무천도상적특점，제취량도、제도、공간위치이급대비도등신식형성협방차특정묘술구진，통과불동척도적분괴대비획득국부현저자도。재장득도적국부자도결합득도최종적무천도상현저도。실험표명상대우기타방법，논문방법대우무천도상목표현저성검측구유흔호적괄응성、가탁전성화준학성。
Aiming to saliency detection problem of degraded foggy images ,object saliency detection method of foggy images based on region covariance matrix is presented .In the method ,luminance ,gradient ,space and contrast information are extracted to form covariance feature description matrix according to characteristics of foggy images .Then local saliency sub-map is acquired by local contrast of different scale .Finally ,saliency map is combined with local saliency sub-map .Ex-periments show that compared with state-of-art methods ,the proposed method has better adaptability and accuracy to object saliency detection in foggy images .