基于三维激光扫描技术的全局优化多视图立体重建系统

Globally optimized multi-view stereo reconstruction system based on 3D laser scanning technology

以往使用的全局优化多视图重建系统面对相机动作过快的情况,难以处理高分辨率的图像,造成细节丢失,重建效果不理想。为此,设计基于三维激光扫描技术的全局优化多视图立体重建系统。在系统硬件设计中,应用UTM-30LX激光雷达,以STM32F103RBT6作为控制板,设计控制板集成电路,通过三维激光扫描技术获得点云数据;在系统软件设计上,配准点云数据,分割视图区域,计算分辨率层,对每一层执行视差估计,达到全局优化的目的,在此基础上,采用全局恢复重建算法实现场景点云重建。实验结果表明:设计的重建系统标准方根误差与1相近,并且目标重建效果与实际目标更接近。

In the past,the global optimized multi-view reconstruction system used to face the situation of too fast camera movement,it is difficult to process high-resolution images,resulting in loss of details,and the reconstruction effect is not ideal.To this end,a globally optimized multi-view stereo reconstruction system based on 3D laser scanning technology is designed.In the system hardware design,the UTM-30 LX lidar is used,STM32 F103 RBT6 is used as the control board,the control board integrated circuit is designed,and the point cloud data is obtained through the three-dimensional laser scanning technology;in the system software design,the point cloud data is registered,the view area is divided,Calculate the resolution layer and perform parallax estimation on each layer to achieve the purpose of global optimization.On this basis,a global recovery and reconstruction algorithm is used to achieve scene point cloud reconstruction.The experimental results show that the standard square root error of the designed reconstruction system is close to 1,and the target reconstruction effect is closer to the actual target.