公开(公告)号：US20150248579A1

公开(公告)日：2015-09-03

申请号：US14714232

申请日：2015-05-15

Applicant: Huazhong University of Science and Technology

Inventor： Tianxu ZHANG ,  Li ZHANG ,  Fan PENG ,  Heng YAO ,  Cen LU ,  Yayun ZHENG ,  Yaxun WEI ,  Cong XIAO

IPC: G06K9/00 ,  G06T7/00 ,  G06T7/60 ,  G06K9/32

CPC classification number: G06K9/00201 ,  G06K9/00208 ,  G06K9/0063 ,  G06K9/00637 ,  G06K9/00697 ,  G06K9/3241 ,  G06K9/40 ,  G06K9/6222 ,  G06T7/12 ,  G06T7/155 ,  G06T7/73 ,  G06T2207/10004 ,  G06T2207/10032 ,  G06T2207/20036 ,  G06T2207/30181 ,  G06T2207/30184 ,  G06T2207/30212

Abstract: A method for identifying and positioning a building using mountain-based outline region restraint, including steps of: (1) obtaining a real-time image, detecting a mountain-based outline of the real-time image, and extending the mountain-based outline thereby obtaining a mountain-based outline restraint region, (2) conducting morphological enhancement and background suppression on the image in the mountain-based outline restraint region, (3) conducting recursive segmentation in the mountain-based outline restraint region thereby transforming an image obtained in step (2) into a binary image, (4) extracting local regions of interest of a target building in the mountain-based outline restraint region according to the binary image, and (5) directly identifying and positioning the target building in the local regions of interest.

Abstract translation: 一种使用山地轮廓区域约束识别和定位建筑物的方法，包括以下步骤：（1）获得实时图像，检测实时图像的山地轮廓，并延伸山基轮廓 从而获得山基轮廓约束区域，（2）对山体轮廓约束区域中的图像进行形态学增强和背景抑制，（3）在山体轮廓约束区域进行递归分割，从而变换所获得的图像 在步骤（2）中成为二进制图像，（4）根据二值图像提取基于山体轮廓约束区域的目标建筑物的局部区域，并且（5）在目标建筑物中直接识别和定位 感兴趣的地区

公开(公告)号：US20170008650A1

公开(公告)日：2017-01-12

申请号：US15106690

申请日：2014-09-02

Applicant: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

Inventor： Tianxu ZHANG ,  Liangliang WANG ,  Gang ZHOU ,  Ming LI ,  Weidong YANG ,  Kuan LIU ,  Yayun ZHENG

IPC: B64G3/00 ,  G06K9/62 ,  G06K9/00 ,  G06K9/46 ,  G01C21/24 ,  G01C21/20

CPC classification number: B64G3/00 ,  B64G1/24 ,  B64G2001/245 ,  G01C21/20 ,  G01C21/24 ,  G06K9/00201 ,  G06K9/4604 ,  G06K9/6202 ,  G06T7/75 ,  G06T2207/10032

Abstract: An attitude estimation method for an on-orbit three-dimensional space object comprises an offline feature library construction step and an online attitude estimation step. The offline feature library construction step comprises: according to a space object three-dimensional model, acquiring multi-viewpoint characteristic views of the object, and extracting geometrical features therefrom to form a geometrical feature library, where the geometrical features comprise an object main body height-width ratio, an object longitudinal symmetry, an object horizontal symmetry, and an object main-axis inclination angle. The online attitude estimation step comprises: preprocessing an on-orbit object image to be tested and extracting features, and matching the extracted features in the geometrical feature library, where an object attitude characterized by a characteristic view corresponding to a matching result is an attitude estimation result. A dimension scale and position relationship between various components of an object are accurately acquired in a three-dimensional modeling stage, thereby ensuring subsequent relatively high matching precision. An attitude estimation system for an on-orbit three-dimensional space object is also provided.

Abstract translation: 轨道三维空间物体的姿态估计方法包括离线特征库构造步骤和在线姿态估计步骤。 离线特征库构建步骤包括：根据空间对象三维模型，获取对象的多视点特征视图，并从中提取几何特征以形成几何特征库，其中几何特征包括对象主体高度 物体纵向对称性，物体水平对称性和物体主轴倾斜角度。 在线姿态估计步骤包括：对要测试的轨道上物体图像进行预处理并提取特征，并且匹配几何特征库中提取的特征，其中以对应于匹配结果的特征视图为特征的对象姿态是姿态估计 结果。 在三维建模阶段中准确地获取对象的各个组件之间的尺度尺度和位置关系，从而确保随后的相对较高的匹配精度。 还提供了一种用于轨道上三维空间物体的姿态估计系统。

公开(公告)号：US20150242700A1

公开(公告)日：2015-08-27

申请号：US14711755

申请日：2015-05-13

Applicant: Huazhong University of Science and Technology

Inventor： Tianxu ZHANG ,  Sufei FAN ,  Yimeng CHEN ,  Yayun ZHENG ,  Changsheng CHEN ,  Zheng WANG ,  Huan WU ,  Xudong HE

IPC: G06K9/46 ,  G06T7/00 ,  G06K9/48

CPC classification number: G06K9/4604 ,  G06K9/481 ,  G06T7/269 ,  G06T7/66 ,  G06T2200/04 ,  G06T2207/10012 ,  G06T2207/10021 ,  G06T2207/30241

Abstract: A method for estimating a rotation axis and a mass center of a spatial target based on binocular optical flows. The method includes: extracting feature points from binocular image sequences sequentially and respectively, and calculating binocular optical flows formed thereby; removing areas ineffective for reconstructing a three-dimensional movement trajectory from the binocular optical flows of the feature points, whereby obtaining effective area-constrained binocular optical flows, and reconstructing a three-dimensional movement trajectory of a spatial target; and removing areas with comparatively large errors in reconstructing three-dimensional motion vectors from the optical flows by multiple iterations, estimating a rotation axis according to a three-dimensional motion vector sequence of each of the feature points obtained thereby, obtaining a spatial equation of an estimated rotation axis by weighted average of estimated results of the feature points, and obtaining spatial coordinates of a mass center of the target according to two estimated rotation axes.

Abstract translation: 一种用于基于双目光学流量估计空间目标的旋转轴线和质量中心的方法。 该方法包括：依次分别从双目图像序列中提取特征点，并计算由此形成的双目光学流; 从特征点的双目光流中去除重建三维运动轨迹的区域，从而获得有效面积约束的双目光学流，并重建空间目标的三维运动轨迹; 以及通过多次迭代从光流重建三维运动矢量中去除具有相对较大误差的区域，根据由其获得的每个特征点的三维运动矢量序列估计旋转轴，获得空间方程 通过估计结果的特征点的加权平均值估计旋转轴，并且根据两个估计的旋转轴获得目标的质心的空间坐标。