物体坐标系曲面投影立体环视图像生成算法

Stereoscopic Panoramic Image Algorithm Based on Curved Surface Projection

针对立体环视图像拼接准确度的难点,提出了一种基于物体坐标系的曲面投影图像拼接算法.根据实际应用场合建立合适的三维模型,对图像进行基于物体坐标系的纹理映射,将三维模型划分为融合、非融合区域,将原始图像映射到非融合区域,对于拼接融合区域,结合模型特点,设计了一种基于角度信息的加权平均融合算法,对拼接后的图像进行颜色校正,消除光照不均、亮度及色度差异现象.算法通过车载立体环视图像的生成验证其有效性,实验结果表明,生成的立体环视图像能够以立体的形式显示车身周围环境,图像拼接准确度较高,视觉效果佳.

Aiming at improving the stitching accuracy of stereoscopic images, a surface projection image stitching algorithm based on an object coordinate system is proposed. According to the actual application, a suitable 3 D model is established, and the image is texture mapped based on the object coordinate system. The 3 D model is divided into fusion and non-fusion regions, and the original image is mapped to the non-fusion region. For the mosaic region, combined with the model features, a weighted average fusion algorithm based on angle information is designed to correct the color of the stitched image to eliminate uneven illumination and brightness. The effectiveness of the algorithm is verified with the generation of a car stereoscopic view image. The experimental results show that the generated stereoscopic view image can display the surrounding environment of the car body in a stereoscopic manner, with high image stitching accuracy and a good visual effect.