摘要：【中文】一种联合最小二乘和三边定位的超宽带室内定位方法，属于信号处理领域。包括以下步骤：获取4个锚节点与标签间的距离信息；处理测距数据得到关于锚节点平面对称的2个坐标解；根据2个对称解得到标签精确的位置坐标；输出计算得到的标签位置坐标。本发明提出了一种联合最小二乘和三边定位的超宽带室内定位方法，该定位方法通过利用所获取到的距离信息，利用改进的最小二乘和三边定位的联合算法对测距结果进行两步解算处理，从而得到更加精确的定位结果，并且耗时较短。 【EN】An ultra-wideband indoor positioning method combining least square and trilateral positioning belongs to the field of signal processing. The method comprises the following steps: obtaining distance information between 4 anchor nodes and labels; processing the ranging data to obtain 2 coordinate solutions symmetrical about the anchor node plane; obtaining accurate position coordinates of the label according to the 2 symmetrical solutions; and outputting the calculated label position coordinates. The invention provides an ultra-wideband indoor positioning method combining least square positioning and trilateral positioning.

摘要：【中文】本发明提出一种基于VSLAM的稀疏三维点云图的视觉定位方法，本发明通过改动开源的ORB‑SLAM系统的输出，得到相机轨迹、相机坐标系与全局坐标系的转移矩阵以及全局坐标系下的稀疏三维点云图，三维点云为关键路标点的三维坐标，并基于获得的信息建立起初始的图像数据库，从而基于建立好的图像数据库实现用户定位，本发明提出利用建立好的稀疏三维点云图与用户输入图像进行匹配，从而减少重复匹配次数，提高定位速度。同时，基于此可以进一步对图像数据库进行压缩，降低图像数据库容量。 【EN】The invention provides a visual positioning method of a sparse three-dimensional point cloud image based on VSLAM, which obtains a camera track, a transfer matrix of a camera coordinate system and a global coordinate system and the sparse three-dimensional point cloud image under the global coordinate system by changing the output of an open-source ORB-SLAM system, wherein three-dimensional point cloud is the three-dimensional coordinate of a key road mark point, and an initial image database is established based on the obtained information, so that the user positioning is realized based on the established image database. Meanwhile, the image database can be further compressed based on the method, and the capacity of the image database is reduced.

摘要：【中文】本发明公开了一种联合灰色关联和神经网络的指纹定位方法。步骤1：得到比较序列，并根据比较序列得到新的均值矩阵；步骤2：从均值矩阵得到关联矩阵；步骤3：得到关联系数矩阵；步骤4：根据关联系数矩阵计算关联度，选择关联度最小的5个参考点形成圆将此圆所包含的所有参考点都作为BP神经网络的训练集；步骤5：将当前时刻值放入已经训练好的BP神经网络中，得到的结果为该测试点的位置坐标；步骤6：计算该位置距离该区域内圆心的距离d；步骤7：若d＜r说明所得到的位置坐标是正确的。灰色关联度对系统的发展态势进行了分析和比较，通过参考序列与比较序列各点之间的距离分析来确定各序列之间的接近性和差异性。 【EN】The invention discloses a fingerprint positioning method combining gray correlation and a neural network. Step 1: obtaining a comparison sequence, and obtaining a new mean value matrix according to the comparison sequence; step 2: obtaining a correlation matrix from the mean matrix; and step 3: obtaining a correlation coefficient matrix; and 4, step 4: calculating the correlation degree according to the correlation coefficient matrix, selecting 5 reference points with the minimum correlation degree to form a circle, and taking all the reference points contained in the circle as a training set of the BP neural network; and 5: putting the current time value into the trained BP neural network, and obtaining the result as the position coordinate of the test point; step 6: calculating the distance d between the position and the inner circle center of the area; and 7: if d < r, the resulting position coordinates are correct. The grey correlation degree analyzes and compares the development situation of the system, and determines the closeness and difference between each sequence through the distance analysis between each point of the reference sequence and the comparison sequence.

摘要：【中文】本发明提出一种用于专用融合网络中基于相对熵和理想解的垂直切换方法，所述方法所述方法包括步骤1、利用层次分析法计算网络属性的主观权重；步骤2、采用熵值法计算网络属性的客观权重；步骤3、基于相对熵和理想解相似排序法进行候选网络排序，根据候选网络排序顺序确定最佳切换网络；本发明提出的基于相对熵和理想解相似排序法的垂直切换方法比传统的简单加权法具有更好的切换判决性能。 【EN】The invention provides a vertical switching method based on relative entropy and ideal solution for a special fusion network, which comprises the following steps of 1, calculating subjective weight of network attributes by using an analytic hierarchy process; step 2, calculating objective weight of network attribute by adopting an entropy method; step 3, performing candidate network sorting based on a relative entropy and ideal solution similarity sorting method, and determining an optimal switching network according to the candidate network sorting sequence; compared with the traditional simple weighting method, the vertical switching method based on the relative entropy and ideal solution similarity ordering method provided by the invention has better switching judgment performance.

摘要：【中文】本发明是一种基于度量学习的指纹定位方法。所述方法为：在目标室内环境内设置多个参考点，建立笛卡尔坐标系，生成与室内物理空间相对应的二维欧几里得空间；在m个参考点上采集来自n个估计接入点AP的RSS数据；在每个预先部署的参考点RP采集到的RSS数据上加入位置标签，生成原始数据；对原始数据进行预处理，得到相似度度量矩阵，并根据RSS数据建立指纹地图库；将相似度度量矩阵和指纹地图库加载到KNN算法中，得到用户的估计位置。本发明充分利用物理空间到信号空间的映射信息，减少由于室内建筑结构复杂导致的定位精度下降，进一步提高室内定位的精度。 【EN】The invention relates to a fingerprint positioning method based on metric learning. The method comprises the following steps: setting a plurality of reference points in a target indoor environment, establishing a Cartesian coordinate system, and generating a two-dimensional Euclidean space corresponding to an indoor physical space; collecting RSS data from n estimation Access Points (AP) on m reference points; adding a position tag to RSS data acquired by each pre-deployed reference point RP to generate original data; preprocessing the original data to obtain a similarity measurement matrix, and establishing a fingerprint map library according to RSS data; and loading the similarity measurement matrix and the fingerprint map library into a KNN algorithm to obtain the estimated position of the user. The invention fully utilizes the mapping information from the physical space to the signal space, reduces the reduction of positioning precision caused by the complex indoor building structure and further improves the precision of indoor positioning.

摘要：【中文】本发明提出一种基于位置指纹的卫星集群分级定位方法，所述方法首先以较大的参考点间隔计算稀疏Radio Map，以使得其占用较小的存储空间，实现对成员星的粗定位；再以粗定位结果为中心，确定精定位区域，并对精定位区域进行精细的参考点划分，根据当前时刻计算精定位区域的Radio Map，对成员星进行精定位，以得到成员星最终的定位结果。该方法能够以增加在线计算时间来减小存储空间，并减小时间偏移对定位精度的影响。所述方法能够减小时间偏移对定位精度的影响同时极大地减小存储空间，能够更好地运用于实际工程中。 【EN】The invention provides a satellite cluster hierarchical positioning method based on position fingerprints, which comprises the steps of firstly calculating sparse Radio maps at a larger reference point interval so as to occupy a smaller storage space and realize coarse positioning of member satellites; and then, with the coarse positioning result as the center, determining a fine positioning area, finely dividing reference points of the fine positioning area, calculating a Radio Map of the fine positioning area according to the current time, and finely positioning the member satellites to obtain the final positioning result of the member satellites. The method can reduce the storage space by increasing the online calculation time, and reduce the influence of time offset on the positioning accuracy. The method can reduce the influence of time offset on positioning accuracy, greatly reduce storage space and be better applied to actual engineering.

摘要：【中文】本发明是一种基于Marching Cubes的CT图像三维重建方法。所述方法为选取三维重建的CT序列图像，建立立方体素与等值面相交关系索引表，确定等值面与立方体相交的边；设定三维数据场中的等值面的阈值，确定三维图像的立方体素；在相邻两层图片中取一顶点，遍历所有立方体素，得到等值点集合；缩小所述CT序列图像中顶点的距离，确定等值面与立方体素每条边的交点，遍历所有长度为1的立方体素，得到缩小后的等值点集合；根据缩小后的等值点集合，重新构建三角面片，输出等值面图像。本发明可以在保证精度的条件下大大缩短CT序列图像的三维重建时间。 【EN】The invention relates to a three-dimensional reconstruction method of a CT image based on Marching Cubes. Selecting a three-dimensional reconstructed CT sequence image, establishing an index table of the intersection relation between a cubic voxel and an isosurface, and determining the edge of the cube intersected by the isosurface; setting a threshold value of an isosurface in a three-dimensional data field, and determining a cubic voxel of a three-dimensional image; taking a vertex from two adjacent layers of pictures, and traversing all cubic voxels to obtain an equivalent point set; narrowing the distance of the vertex in the CT sequence image, determining the intersection point of the isosurface and each edge of the cubic voxel, traversing all the cubic voxels with the length of 1 to obtain a narrowed isopoint set; and reconstructing a triangular patch according to the reduced equivalent point set, and outputting an equivalent surface image. The invention can greatly shorten the three-dimensional reconstruction time of the CT sequence image under the condition of ensuring the precision.