机构地区: 北京科技大学自动化学院
出 处: 《中南大学学报(自然科学版)》 2013年第S2期28-32,共5页
摘 要: 利用逆深度参数化方法研究Kinect摄像机在未知环境下的同时定位与地图构建问题。利用SURF特征提取和扩展卡尔曼滤波实现摄像机的位置和环境地图的更新,从而提高算法的精确度和鲁棒性;在此基础上有效融合Kinect摄像机采集的图像深度信息,加快滤波算法的收敛速度。实验结果证明了所提方法的有效性和可用性。 A method for Kinect sensor was presented based on SLAM(simultaneous localization and mapping) problem via inverse depth parameterization model,where the depth of features from Kinect was employed to improve the convergence of method.To further improve the accuracy and robustness,SURF(speed up robust features) feature detection operator was adopted to extract image features,and extended Kalman filter(EKF) was used to estimate the trajectory of camera and the position of features.Experimental results are given to demonstrate the effectiveness and applicability of the proposed method.