移动相机的宽基线图像快速准确三维重建

Fast and Accurate Three-dimension Reconstruction Using Wide Baseline Capturing Images by Moving Camera

针对使用移动卷帘相机拍摄的图像会使三维重建不准确,以及宽基线图像的视觉连接较弱等问题,提出一种改进的宽基线图像三维重建方法。提出的方法优化了光束平差法的目标函数。通过合并GPS和INS的读数,在邻近方位间加入额外的光滑度以抵消漂移效果,去除了环闭合差的较大误差。同时为了提高卷帘立体扫描的速度,提出分段二次插值,先处理目标图像中的每一个像素点,再用目标图像中每一个像素点的反射线求出平面交叉的曝光值。实验结果表明,提出的方法的三维稀疏重建既清晰又连贯。三维稠密重建中,与其他类似方法相比,该方法保持了准确性,但重建速度明显提升。

As capturing images with a moving rolling shutter camera may case inaccuracies to 3D reconstructions, and the visual connection of wide baseline images is weak, an improved 3D reconstruction method for wide baseline images is proposed. The proposed method optimizes the objective function of the bundle adjustment method. By combining the GPS and INS readings and adding extra smoothness between adjacent positions to counteract the drift effect, larger error of the ring closure error is removed. At the same time, in order to improve the speed of rolling three-dimensional scanning, subsection interpolation of two square is proposed. Firstly, deal with each pixel in the target image, then each pixel of the reflection line in the target image is used to determine the exposure value in the cross plane. Experimental results show that three-dimensional sparse reconstruction of the proposed method is both clear and coherent. Compared with other similar methods, the reconstruction speed is significantly improved, and the proposed method also maintains the accuracy of 3D reconstruction.