基于多视图立体视觉的沙堆三维尺寸测量研究

利用从运动中恢复结构方法(SFM),提出了一种基于多视图立体视觉的沙堆三维重建及三维尺寸测量方法。首先根据SFM方法的求解不稳定特点,结合光束平差法对SFM求解过程进行分析及优化;其次针对SFM重建结果为稀疏点云的问题,利用基于面片的稠密重建算法重新生成稠密的三维点云,再利用泊松算法对密集点云进行三维曲面重建;最后获得模型的三维尺寸信息。对某建筑工地的沙堆进行了三维尺寸的测量实验,实验结果验证了该方法的有效及可行性,提高了重建能力及精度,同时考虑了目标实际测量误差与重建误差,能够满足实际智能测量的应用需求。

Research on 3D Measurement of Sand Pile Based on Multi View Stereo Vision

Based on the structure from motion (SFM), a 3D reconstruction and measurement method based on multi view stereo vision is proposed. Firstly, according to the unstable characteristics of the SFM method, the SFM solution process is analyzed and optimized by the bundle adjustment method. Secondly, the SFM reconstruction result is sparse point cloud, and the patch-based dense reconstruction algorithm is used to regenerate the dense 3D points. The cloud is then reconstructed by a Poisson algorithm for a 3D surface of a dense point cloud. Finally, the 3D size information of the model is obtained. The 3D measurement experiment of the sand pile at a construction site is carried out. The experimental results verify the effectiveness and feasibility of the method, improve the reconstruction ability and accuracy, and consider the actual measurement error and reconstruction error of the target, which can meet the requirements of actual intelligent measurement applications.