基于双目视觉的移动机器人动态目标识别与定位

Dynamic Object Recognition and Localization of Mobile Robot Based on Binocular Vision

提出了一种双目移动机器人实时动态目标识别与定位方法。该算法首先采用SIFT(Scale Invariant Features Transforms)算法提取目标特征,并结合双目视差特征进行目标匹配;然后通过区域增长方法进行目标区域的提取;最后结合双目视觉标定的模型对目标进行定位。实验结果表明:该方法在摄像机运动-目标运动情况下,能对局部特征未知或特征不明显的动态目标进行有效的识别与定位。

A real-time dynamic object recognition using binocular vision. Firstly, the SIFT operator and localization method is presented for mobile robot is applied to object features extraction and object matching with the disparity features of binocular vision. Then, the object area is extracted through region growing method. Finally, according to the binocular vision calibration model, the object＇s location is obtained. Experiments show that in the case of both camera moving and object moving, the proposed method can effectively recognize and locate the dynamic object with unknown or obscure object local feature.