公开(公告)号：US09460363B2

公开(公告)日：2016-10-04

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: G06K9/00 ,  G06K9/46 ,  G06K9/48 ,  G06T7/00 ,  G06T7/20 ,  G06T7/60

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。

公开(公告)号：US09454692B2

公开(公告)日：2016-09-27

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: G06K9/34 ,  G06K9/00 ,  G06T7/00 ,  G06K9/32 ,  G06T7/60 ,  G06K9/40 ,  G06K9/62

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