复杂场景下基于c-shot特征的3d物体识别与位姿估计.pdfVIP

第29 卷 第 5 期 计算机辅助设计与图形学学报 Vol. 29 No.5 2017 年5 月 Journal of Computer-Aided Design Computer Graphics May 2017 复杂场景下基于C-SHOT 特征的3D 物体识别与位姿估计 * 张凯霖, 张 良 ( 中国民航大学智能信号与图像处理天津市重点实验室 天津 300300) ) : 为了准确地同时识别复杂点云中的多个目标, 提出一种基于法矢改进点云特征C-SHOT 的3D 物体识别方法. 首先, 在估计RGB-D 数据的点云法矢时将邻域点距离信息考虑在内, 计算带距离权重的协方差矩阵得到更精确的点 云法矢; 其次根据特征点处法矢与邻域法矢的夹角余弦构造点云形状直方图, 同时统计点云纹理直方图并与形状直 方图融合成 C-SHOT 描述符; 最后对场景与模板分别提取 C-SHOT 特征, 利用Kd 树快速求得对应对, 引入3D 霍夫 投票机制, 并结合点云局部坐标系克服噪声遮挡问题完成多目标初识别. 基于LM-ICP 实现精确定位及位姿估计, 画 出目标包围盒, 采用基准数据库CVLab 以及采集实验室真实数据进行实验, 结果验证了该方法的有效性与精确性. ：三维物体识别; 位姿估计; 点云配准; 迭代最近点算法; 霍夫变换 ：TP391.41 3D Object Recognition and 6DoF Pose Estimation in Scenes with Occlusions and Clutter Based on C-SHOT 3D Descriptor * Zhang Kailin and Zhang Liang (Key Laboratory of Advanced Signal and Image Processing, Civil Aviation University of China, Tianjin 300300) Abstract: A 3D object detection and recognition method is proposed in this paper. The method achieves pose estimations of multiple object instances in 3D scenes with some occlusions and clutter. First, the normal vector of point is estimated by computing the distance between the neighboring points and the feature one within the local spherical support domain. The longer the distance is, the smaller the weight is. Next, we encode the 3D descriptor called color signatures of histogram of orientations (C-SHOT) based on improved normal vector. Then we match 3D feature correspondences between scenes and models to prove the existence of the objects being sought on 3D hough voting space. Finally