中国科学院机构知识库网格系统: 检索

|

收藏 | 浏览/下载：18/0 | 提交时间：2019/12/12

Content based image retrieval Geometric verification Region property space Spatial weighting

Beyond Joints: Learning Representations From Primitive Geometries for Skeleton-Based Action Recognition and Detection 期刊论文 OAI收割
IEEE Transactions on Image Processing, 2018, 卷号: 27, 期号: 9, 页码: 4382 - 4394
作者: Wang Hongsong(王洪松); Wang Liang(王亮)

|

收藏 | 浏览/下载：43/0 | 提交时间：2018/06/03

Skeleton-based Action Recognition Geometric Relations Viewpoint Transformation Action Detection

An over-segmentation method for single-touching Chinese handwriting with learning-based filtering 期刊论文 OAI收割
INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION, 2014, 卷号: 17, 期号: 1, 页码: 91-104
作者: Xu, Liang

收藏 | 浏览/下载：40/0 | 提交时间：2015/08/12

Single-touching strings Chinese handwriting Over-segmentation Learning-based filtering Geometric features

A line mapping based automatic registration algorithm of infrared and visible images 会议论文 OAI收割
5th International Symposium on Photoelectronic Detection and Imaging (ISPDI) - Infrared Imaging and Applications, Beijing, June 25-27, 2013
作者: Ai R(艾锐); Shi ZL(史泽林); Xu DJ(徐德江); Zhang CS(张程硕)

收藏 | 浏览/下载：36/0 | 提交时间：2013/12/26

There exist complex gray mapping relationships among infrared and visible images because of the different imaging mechanisms. The difficulty of infrared and visible image registration is to find a reasonable similarity definition. In this paper, we develop a novel image similarity called implicit linesegment similarity(ILS) and a registration algorithm of infrared and visible images based on ILS. Essentially, the algorithm achieves image registration by aligning the corresponding line segment features in two images. First, we extract line segment features and record their coordinate positions in one of the images, and map these line segments into the second image based on the geometric transformation model. Then we iteratively maximize the degree of similarity between the line segment features and correspondence regions in the second image to obtain the model parameters. The advantage of doing this is no need directly measuring the gray similarity between the two images. We adopt a multi-resolution analysis method to calculate the model parameters from coarse to fine on Gaussian scale space. The geometric transformation parameters are finally obtained by the improved Powell algorithm. Comparative experiments demonstrate that the proposed algorithm can effectively achieve the automatic registration for infrared and visible images, and under considerable accuracy it makes a more significant improvement on computational efficiency and anti-noise ability than previously proposed algorithms.

Multilevel SIFT Matching for Large-Size VHR Image Registration 期刊论文 OAI收割
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2012, 卷号: 9, 期号: 2, 页码: 171-175
作者: Huo, Chunlei; Pan, Chunhong

收藏 | 浏览/下载：32/0 | 提交时间：2015/08/12

Coarse-to-fine strategy geometric constraint large-size image registration parallel-based architecture

Effect of the sampling design of ground control points on the geometric correction of remotely sensed imagery 期刊论文 OAI收割
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2012, 卷号: 18, 页码: 91-100
Wang, JH(王江浩); Ge, Y; Heuvelink, GBM; Zhou, CH; Brus, D

收藏 | 浏览/下载：21/0 | 提交时间：2012/08/30

Geometric correction Spatial coverage sampling Universal kriging Variogram Model-based sampling

Effect of the sampling design of ground control points on the geometric correction of remotely sensed imagery SCI/SSCI论文 OAI收割
2012
作者: Ge Y.

收藏 | 浏览/下载：23/0 | 提交时间：2014/12/24

Geometric correction Spatial coverage sampling Universal kriging Variogram Model-based sampling resolution satellite imagery accuracy registration algorithm model

Optimum design of the carbon fiber thin-walled baffle for the space-based camera (EI CONFERENCE) 会议论文 OAI收割
International Symposium on Photoelectronic Detection and Imaging 2011: Space Exploration Technologies and Applications, May 24, 2011 - May 26, 2011, Beijing, China
Yan Y.; Gu S.; An Y.; Jin G.

收藏 | 浏览/下载：14/0 | 提交时间：2013/03/25

The thin-walled baffle design of the space-based camera is an important job in the lightweight space camera research task for its stringent quality requirement and harsh mechanical environment especially for the thin-walled baffle of the carbon fiber design. In the paper an especially thin-walled baffle of the carbon fiber design process was described and it is sound significant during the other thin-walled baffle design of the space camera. The designer obtained the design margin of the thin-walled baffle that structural stiffness and strength can tolerated belong to its development requirements through the appropriate use of the finite element analysis of the walled parameters influence sensitivity to its structural stiffness and strength. And the designer can determine the better optimization criterion of thin-walled baffle during the geometric parameter optimization process in such guiding principle. It sounds significant during the optimum design of the thin-walled baffle of the space camera. For structural stiffness and strength of the carbon fibers structure which can been designed the effect of the optimization will be more remarkable though the optional design of the parameters chose. Combination of manufacture process and design requirements the paper completed the thin-walled baffle structure scheme selection and optimized the specific carbon fiber fabrication technology though the FEM optimization and the processing cost and process cycle are retrenchment/saved effectively in the method. Meanwhile the weight of the thin-walled baffle reduced significantly in meet the design requirements under the premise of the structure. The engineering prediction had been adopted and the related result shows that the thin-walled baffle satisfied the space-based camera engineering practical needs very well its quality reduced about 20% the final assessment index of the thin-walled baffle were superior to the overall design requirements significantly. The design method is reasonable and efficient to the other thin-walled baffle that mass and work environment requirement is requirement harsh. 2011 SPIE.

Effect of gimbal point displacement on optical axis pointing precision in an image seeker (EI CONFERENCE) 会议论文 OAI收割
2011 International Conference on Electric Information and Control Engineering, ICEICE 2011, April 15, 2011 - April 17, 2011, Wuhan, China
作者: Zhang X.; Zhang X.; Zhang X.

收藏 | 浏览/下载：39/0 | 提交时间：2013/03/25

A concentric glass spherical dome was usually chosen as the transparent window mounted in front of the optical lens in an image seeker. However optical ray had to change its direction when propagating through the dome due to refraction unless passing through the center of the dome which demanded gimbal point coincide with the center of the dome exactly. In fact gimbal point displacement could not be eliminating due to fabrication assembly and vibration therefore the optical axis pointing error generated. In this paper the effect of gimbal point displacement on optical axis pointing precision in an image seeker was analyzed and the theoretical expression of the optical axis pointing error was derived based on geometric optics and the error dynamics was explored by numerical. Take a visible light image seeker as a case the thickness of concentric glass spherical dome was 8mm and the inner radius was 72mm and the optical axis pointing errors varying dynamically with the look angle and the gimbal point displacement were shown in graph. When the gimbal displacement was 0.11mm the maximum optical axis pointing error was 0.054mrad that is equal to the instantaneous field of view (IFOV) corresponding to the camera system whose focal length was 120mm and pixel size was 6.5m. Furthermore with the gimbal displacement increasing the optical axis pointing error increased linearly. The analyzed results provided a theoretical basis for the displacement range which had to be limited strictly in the gimbal design process. 2011 IEEE.

Automatic bridge extraction for optical images (EI CONFERENCE) 会议论文 OAI收割
6th International Conference on Image and Graphics, ICIG 2011, August 12, 2011 - August 15, 2011, Hefei, Anhui, China
Gu D.-Y.; Zhu C.-F.; Shen H.; Hu J.-Z.; Chang H.-X.

收藏 | 浏览/下载：30/0 | 提交时间：2013/03/25

This paper describes a novel hierarchy algorithm for extracting bridges over water in optical images. To reduce the omission of bridges by searching the edge we extract the river regions which the bridges are included in. Firstly we segment the optical image to get the coarse water bodies using iterative threshold eliminate the noise regions and add the missing regions based on k-means clustering with texture information and spatial coherence. Then the blanks are connected based on shape features and candidate bridge regions are segmented from river regions. Finally the bridges are verified by geometric information and the ubiety between bridges and river. The results show that this approach is efficient and effective for extracting bridges in satellite image from Google Earth and in aerial optical images acquired by unmanned aerial vehicle. 2011 IEEE.