As SIFT features are invariant to rotation and scaling, we employ SIFT to extract feature points.
由于SIFT特征对旋转和缩放具有不变性,该算法利用SIFT提取图像的特征点。
Moreover, the precision of object recognition can be improved effectively by the combination of SIFT features and normalized DLT algorithm.
结合SIFT特征和正交DLT算法,给出一种较为精确的物体识别方法。
SLAM is completed by fusing the information of SIFT features and robot information with EKF.
应用扩展卡尔曼滤波器融合SIFT特征信息与机器人位姿信息完成SLAM。