基于光照调整和特征曲线的全景图拼接

图像拼接是生成全景图的关键技术之一。针对传统图像拼接方法只能处理光照一致图像的问题,笔者提出了一种对环境光照鲁棒的全景图拼接方法。该方法运用同态滤波、特征点自动提取、特征曲线匹配等技术,有效地解决了图像拼接中的光照差、区域精确匹配、噪声点及图像融合问题。实验表明对光照变化的图像采用该方法进行拼接可以获得满意的视觉效果。

Panorama Mosaics Based on Illumination Alignment and Characteristic Curve Match

Image mosaic is the key step for panorama, while existing algorithms focus on scenes with a same illumination. This paper presents a novel method for image mosaics with notable illumination difference. Using homomorphic filtering, feature points extraction and characteristic curves matching, our method gives a good solution for illumination difference, accurately match, noise points, etc problems in image mosaics. The results of experiment show that we can gain good visual effect by using this method in image mosaics with notable illumination difference.