一种新颖实用的基于视觉导航的三维重建算法  

A Novel Practical 3D Reconstruction Algorithm Based on Vision Navigation

作　　者：林强[1] 李宏东[1] 顾伟康[1] 

机构地区：[1]浙江大学信息与电子工程系,杭州310027

出　　处：《传感技术学报》2003年第4期401-405,共5页Chinese Journal of Sensors and Actuators

基　　金：国家自然科学基金项目 (No .6 0 10 5 0 0 3);浙江省自然科学基金项目 (No.6 0 0 0 2 5 )

摘　　要：根据立体视觉在视觉导航应用中的特点 ,提出了由视差图重建三维场景的整套算法。首先 ,推导视差图里各点在摄像机坐标系下的三维坐标。其次 ,建立摄像机坐标系与车体坐标系的转换关系 ,得到更有实际意义的在车体坐标系下各点的三维坐标。最后 ,通过分格显示地貌的算法 ,大大减少了数据量。实验结果表明 ,该算法计算量小、鲁棒性强 ,完全满足视觉导航中的实时性。From the specialties of the stereo vision applied in vision-based navigation, we propose a whole solution to reconstruct 3D scene from the disparity map. First, we discussed how to get the camera-based coordinates form the disparity map. Second, we developed the conversion from the camera-based to the vehicle-based coordinates, thus, more practical reconstruction result was obtained. Finally, the quantity of data was reduced greatly by subdividing whole scene into smaller subunits. The experiment results prove that our algorithm can meet the vision-based navigation's request for real-time and validity.

关 键 词：视觉导航 三维重建算法 三维坐标 机器人 摄像机 

分 类 号：TP242.62[自动化与计算机技术—检测技术与自动化装置]