Based on the characteristics that human eyes are sensitive to brightness and color, the lightness information of visible image and degree of linear polarization and polarization angle were fused in hue-saturation- va...Based on the characteristics that human eyes are sensitive to brightness and color, the lightness information of visible image and degree of linear polarization and polarization angle were fused in hue-saturation- value（HSV） space. To meet the observation of human eyes, hue adjustment based on color transfer was carried out to the fused image and hue was adjusted by polynomial fitting method. Hue adjustment method was improved considering the complicated real mapping relationship between hue gray scale of fused image and reference template image. The result shows that the color fusion method presented in this paper is superior to the traditional pseudo-color method and it is helpful to recognize the target from the environment correctly. The fusion result can reflect the difference of object＇s polarization characteristic, and get a natural fused image effect.展开更多
A novel feature fusion method is proposed for the edge detection of color images. Except for the typical features used in edge detection, the color contrast similarity and the orientation consistency are also selected...A novel feature fusion method is proposed for the edge detection of color images. Except for the typical features used in edge detection, the color contrast similarity and the orientation consistency are also selected as the features. The four features are combined together as a parameter to detect the edges of color images. Experimental results show that the method can inhibit noisy edges and facilitate the detection for weak edges. It has a better performance than conventional methods in noisy environments.展开更多
由于水的吸收和悬浮粒子的散射作用,水下图像出现色偏、对比度降低以及细节模糊等问题,影响水下视觉同步定位与地图构建(Simultaneous localization and mapping,SLAM)前端特征提取和特征匹配。针对上述问题,提出一种用于水下视觉SLAM...由于水的吸收和悬浮粒子的散射作用,水下图像出现色偏、对比度降低以及细节模糊等问题,影响水下视觉同步定位与地图构建(Simultaneous localization and mapping,SLAM)前端特征提取和特征匹配。针对上述问题,提出一种用于水下视觉SLAM前端的多尺度融合与细节突显的图像增强算法。首先,提出一种改进颜色通道补偿的颜色校正方法,用于校正水下图像色偏;其次,利用曝光融合框架对颜色校正的水下图像对比度进行增强;然后,将颜色校正图像和对比度增强图像进行多尺度融合;最后,采用非锐化掩模对融合图像进行细节突显,进而得到视觉效果较好的增强图像。实验结果表明,与其他算法相比,该算法处理后的水下图像在颜色平衡、对比度、细节以及清晰度等方面的效果较好,同时还增加了特征点和特征匹配对数,显著改善了水下视觉SLAM前端的特征提取和特征匹配。展开更多
基金Sponsored by the National High Technology Research and Development Program of China ("863"Program) (2006AA09Z207)
文摘Based on the characteristics that human eyes are sensitive to brightness and color, the lightness information of visible image and degree of linear polarization and polarization angle were fused in hue-saturation- value（HSV） space. To meet the observation of human eyes, hue adjustment based on color transfer was carried out to the fused image and hue was adjusted by polynomial fitting method. Hue adjustment method was improved considering the complicated real mapping relationship between hue gray scale of fused image and reference template image. The result shows that the color fusion method presented in this paper is superior to the traditional pseudo-color method and it is helpful to recognize the target from the environment correctly. The fusion result can reflect the difference of object＇s polarization characteristic, and get a natural fused image effect.
基金supported partly by the National Basic Research Program of China (2005CB724303)the National Natural Science Foundation of China (60671062) Shanghai Leading Academic Discipline Project (B112).
文摘A novel feature fusion method is proposed for the edge detection of color images. Except for the typical features used in edge detection, the color contrast similarity and the orientation consistency are also selected as the features. The four features are combined together as a parameter to detect the edges of color images. Experimental results show that the method can inhibit noisy edges and facilitate the detection for weak edges. It has a better performance than conventional methods in noisy environments.
文摘由于水的吸收和悬浮粒子的散射作用,水下图像出现色偏、对比度降低以及细节模糊等问题,影响水下视觉同步定位与地图构建(Simultaneous localization and mapping,SLAM)前端特征提取和特征匹配。针对上述问题,提出一种用于水下视觉SLAM前端的多尺度融合与细节突显的图像增强算法。首先,提出一种改进颜色通道补偿的颜色校正方法,用于校正水下图像色偏;其次,利用曝光融合框架对颜色校正的水下图像对比度进行增强;然后,将颜色校正图像和对比度增强图像进行多尺度融合;最后,采用非锐化掩模对融合图像进行细节突显,进而得到视觉效果较好的增强图像。实验结果表明,与其他算法相比,该算法处理后的水下图像在颜色平衡、对比度、细节以及清晰度等方面的效果较好,同时还增加了特征点和特征匹配对数,显著改善了水下视觉SLAM前端的特征提取和特征匹配。
