中国科学院机构知识库网格系统: 检索

Continuous-time Distributed Heavy-ball Algorithm for Distributed Convex Optimization over Undirected and Directed Graphs 期刊论文 OAI收割
Machine Intelligence Research, 2022, 卷号: 19, 期号: 1, 页码: 75-88
作者: Hao-Ran Yang; Wei Ni

|

收藏 | 浏览/下载：12/0 | 提交时间：2024/04/23

Distributed convex optimization second-order distributed algorithm multi-agent systems gradient tracking directed graph

基于Mean Shift的背景梯度修正直方图跟踪算法 期刊论文 OAI收割
激光与光电子学进展, 2020, 卷号: 57
作者: 喻璐璐; 谭逢富; 陈修涛; 秦来安; 侯再红

|

收藏 | 浏览/下载：52/0 | 提交时间：2021/03/15

image processing target tracking background gradient background fluctuation background weighted histogram 图像处理目标跟踪背景梯度背景波动背景加权直方图

Efficient projected gradient methods for cardinality constrained optimization 期刊论文 OAI收割
SCIENCE CHINA-MATHEMATICS, 2019, 卷号: 62, 期号: 2, 页码: 245-268
作者: Xu, Fengmin; Dai, Yuhong; Zhao, Zhihu; Xu, Zongben

|

收藏 | 浏览/下载：55/0 | 提交时间：2019/04/02

sparse approximation projected gradient method global convergence signal recovery index tracking

Study on the deep neural network of intelligent image detection and the improvement of elastic momentum on image recognition 期刊论文 OAI收割
journal of computational and theoretical nanoscience, 2016, 卷号: 13, 期号: 5, 页码: 3326-3330
作者: Yue, Qi; Ma, Caiwen

收藏 | 浏览/下载：28/0 | 提交时间：2016/10/12

Gradient methods Image recognition Object recognition Target tracking

Numerical simulations on thermocapillary migrations of nondeformable droplets with large Marangoni numbers 期刊论文 OAI收割
PHYSICS OF FLUIDS, 2012, 卷号: 24, 期号: 9, 页码: 092101
作者: Yin ZH(尹兆华); Chang L(常磊); Hu WR(胡文瑞); Li QH(李巧红); Wang HY

收藏 | 浏览/下载：31/0 | 提交时间：2013/01/18

Reduced Gravity Temperature-Gradient Front-Tracking Bubbles Motion Drops Equations Reynolds Moderate

Online multiple instance gradient feature selection for robust visual tracking 期刊论文 OAI收割
PATTERN RECOGNITION LETTERS, 2012, 卷号: 33, 期号: 9, 页码: 1075-1082
作者: Xie, Yuan; Qu, Yanyun; Li, Cuihua; Zhang, Wensheng

收藏 | 浏览/下载：33/0 | 提交时间：2015/09/18

Gradient-based feature selection HOG Multiple Instance Learning Online object tracking

实时在线三维头部跟踪的研究及应用 学位论文 OAI收割
工学博士, 中国科学院自动化研究所: 中国科学院研究生院, 2011
作者: 王海波

收藏 | 浏览/下载：56/0 | 提交时间：2015/09/02

三维头部姿态跟踪基于梯度的跟踪基于检测的跟踪特征匹配与学习颜色先验运动颤抖消除眼神估计虚拟现实 3D head pose tracking gradient-based tracking tracking by detection feature matching and learning color prior motion jitter removing gaze estimation virtual reality

Research on infrared dim-point target detection and tracking under sea-sky-line complex background (EI CONFERENCE) 会议论文 OAI收割
International Symposium on Photoelectronic Detection and Imaging 2011: Advances in Infrared Imaging and Applications, May 24, 2011 - May 24, 2011, Beijing, China
作者: Dong Y.-X.; Zhang H.-B.; Li Y.; Li Y.; Li Y.

收藏 | 浏览/下载：116/0 | 提交时间：2013/03/25

Target detection and tracking technology in infrared image is an important part of modern military defense system. Infrared dim-point targets detection and recognition under complex background is a difficulty and important strategic value and challenging research topic. The main objects that carrier-borne infrared vigilance system detected are sea-skimming aircrafts and missiles. Due to the characteristics of wide field of view of vigilance system the target is usually under the sea clutter. Detection and recognition of the target will be taken great difficulties.There are some traditional point target detection algorithms such as adaptive background prediction detecting method. When background has dispersion-decreasing structure the traditional target detection algorithms would be more useful. But when the background has large gray gradient such as sea-sky-line sea waves etc.The bigger false-alarm rate will be taken in these local area.It could not obtain satisfactory results. Because dim-point target itself does not have obvious geometry or texture feature in our opinion from the perspective of mathematics the detection of dim-point targets in image is about singular function analysis.And from the perspective image processing analysis the judgment of isolated singularity in the image is key problem. The foregoing points for dim-point targets detection its essence is a separation of target and background of different singularity characteristics.The image from infrared sensor usually accompanied by different kinds of noise. These external noises could be caused by the complicated background or from the sensor itself. The noise might affect target detection and tracking. Therefore the purpose of the image preprocessing is to reduce the effects from noise also to raise the SNR of image and to increase the contrast of target and background. According to the low sea-skimming infrared flying small target characteristics the median filter is used to eliminate noise improve signal-to-noise ratio then the multi-point multi-storey vertical Sobel algorithm will be used to detect the sea-sky-line so that we can segment sea and sky in the image. Finally using centroid tracking method to capture and trace target. This method has been successfully used to trace target under the sea-sky complex background. 2011 Copyright Society of Photo-Optical Instrumentation Engineers (SPIE).

Thermocapillary migration and interaction of two nondeformable drops 期刊论文 OAI收割
Applied Mathematics and Mechanics-English Edition, 2011, 卷号: 32, 期号: 7, 页码: 811-824
作者: Yin ZH(尹兆华); Chang L(常磊); Hu WR(胡文瑞); Gao P(高鹏)

收藏 | 浏览/下载：33/0 | 提交时间：2012/04/01

Interaction Of Two Drops Thermocapillary Motion Front Tracking Method Temperature-Gradient Thermal-Gradient Viscous-Fluid Motion Bubbles Spheres Reynolds

Thermocapillary Migration Of Nondeformable Drops 期刊论文 OAI收割
Physics of Fluids, 2008
作者: Yin ZH(尹兆华); Gao P(高鹏); Hu WR(胡文瑞); Chang L(常磊)

收藏 | 浏览/下载：584/40 | 提交时间：2009/08/03

Large Marangoni Numbers Vertical Temperature-Gradient Front-Tracking Method Gas Bubble Numerical-Simulation Thermal-Gradient Reduced Gravity Motion Droplets Microgravity