公开(公告)号：US20210065376A1

公开(公告)日：2021-03-04

申请号：US17086153

申请日：2020-10-30

申请人： CHINA INSTITUTE OF WATER RESOURCES AND HYDROPOWER RESEARCH

发明人： Wenlong SONG ,  Rui TANG ,  Juan LV ,  Jingxuan LU ,  Kun YANG ,  Zhicheng SU ,  Yuanyuan DUAN ,  Xuejun ZHANG ,  Lihua ZHAO ,  Yizhu LU ,  Hongjie LIU

IPC分类号： G06T7/187 ,  G06T7/12 ,  G06T7/11 ,  G06T7/40

摘要： A Region Merging image segmentation algorithm based on boundary extraction is disclosed, comprising the steps of calculating a gradient image, extracting a boundary and carrying out initial segmentation and Region Merging, wherein the initial segmentation can be omitted. In the Region Merging process, the ratio of the length of boundary extraction result lies on the adjacent edge between adjacent regions to the length of the adjacent edge is taken as the merging cost, the regions are merged according to the ascending order of the mean gradient value in the region, and a texture difference evaluation mechanism is introduced to remove the error segmentation. The algorithm solves the problems of the other current segmentation algorithms, such as over-segmentation, easy to be influenced by noise and illumination, large in computation and memory consumption, in need of a large number of samples being marked manually and the like. Besides, all regions or all categories achieve the best segmentation result on one final segmentation result. These advantageous features can reduce the computational resource consumption of subsequent tasks and improve their processing effect.

公开(公告)号：US20220301258A1

公开(公告)日：2022-09-22

申请号：US17826049

申请日：2022-05-26

申请人： CHINA INSTITUTE OF WATER RESOURCES AND HYDROPOWER RESEARCH

发明人： Wenlong SONG ,  Changjun LIU ,  Tao SUN ,  Rui TANG ,  Yuanyuan FU ,  Yizhu LU ,  Lang YU ,  Jie LIU ,  Yue WANG

IPC分类号： G06T15/10

摘要： Disclosed in the present invention is An improved rotated rectangular bounding box annotation method, used for taking as anchor boxes samples annotation and bounding box output at predicting of a target detection and tracking algorithm, wherein: coordinates of a central point C, a vector {right arrow over (CD)} from the coordinates of the central point C to any one vertex D, and a proportional coefficient of a vector {right arrow over (CP)} of a vector {right arrow over (CE)} on the vector {right arrow over (CD)} from the coordinates of the central point C to an adjacent vertex E of the vertex D, and a vector {right arrow over (CD)}; external constraints to be met: the vector {right arrow over (CP)} is in the same direction as the vector {right arrow over (CD)}, and the included angle from the vector {right arrow over (CD)} to the vector {right arrow over (CE)} is one of a clockwise direction or a counterclockwise direction; representation of an annotation vector {right arrow over (CD)}: the angle between the component of the annotation vector recorded at the first position and the vector is clockwise (or counterclockwise), and the value range of this angle is [0,90) degrees; the modulus value or another component of the annotation vector are recorded at the second position; the direction of the first component of the annotation vector is recorded at the third position, and this direction can be taken as X-axis direction or Y-axis direction; when the bounding box is square, either X-axis direction or Y-axis direction it can be taken. When the square bounding box and the general rectangular bounding box share the same constraints, recognition of the constraint by a machine learning algorithm is facilitated.