中国科学院机构知识库网格系统: 检索

A Novel Divide and Conquer Solution for Long-term Video Salient Object Detection 期刊论文 OAI收割
Machine Intelligence Research, 2024, 卷号: 21, 期号: 4, 页码: 684-703
作者: Yun-Xiao Li; Cheng-Li-Zhao Chen; Shuai Li; Ai-Min Hao; Hong Qin

|

收藏 | 浏览/下载：12/0 | 提交时间：2024/07/18

Video salient object detection background consistency analysis weakly supervised learning long-term information background shift

The Propagation Background in Social Networks: Simulating and Modeling 期刊论文 OAI收割
International Journal of Automation and Computing, 2020, 卷号: 17, 期号: 3, 页码: 353-363
作者: Kai Li

|

收藏 | 浏览/下载：18/0 | 提交时间：2021/02/22

Social network information overload propagation background simulating modeling.

The Propagation Background in Social Networks:Simulating and Modeling 期刊论文 OAI收割
国际自动化与计算杂志:英文版, 2020, 卷号: 17.0, 期号: 003, 页码: 353
作者: Kai Li; Tong Xu; Shuai Feng; LiSheng Qiao; HuaWei Shen

|

收藏 | 浏览/下载：7/0 | 提交时间：2023/12/04

Social network information overload propagation background simulating modeling

The distribution characteristics of halogen elements in soil under the impacts of geographical backgrounds and human disturbances 期刊论文 OAI收割
GEODERMA, 2017, 卷号: 305, 页码: 236-249
作者: Yu, Huan; Kong, Bo; Du, Rong-Xiang; Shi, Ze-Ming; He, Zheng-Wei

|

收藏 | 浏览/下载：21/0 | 提交时间：2017/07/01

Geographic Information System Geographical Background Halogen Elements Human Activity Spatial Distribution

视频中的人体跟踪和行为识别方法研究 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, 2012
作者: 王恒

收藏 | 浏览/下载：97/0 | 提交时间：2015/09/02

背景信息半监督鉴别跟踪行为识别稠密轨迹运动边界特征融合 background information semi-supervised discriminant tracking action recognition dense trajectories motion boundary feature combination

A simple and fast moving object segmentation based on H.264 compressed domain information (EI CONFERENCE) 会议论文 OAI收割
4th International Conference on Computational and Information Sciences, ICCIS 2012, August 17, 2012 - August 19, 2012, Chongqing, China
作者: Chen X.; Chen X.; Chen X.; Sun L.

收藏 | 浏览/下载：15/0 | 提交时间：2013/03/25

The paper presents a simple and fast approach for moving object segmentation based on H.264 compressed domain information for the application of indoor video surveillance with static camera. Due to the characteristics of indoor video surveillance the proposed method of segmentation avoids complicated background model like Gaussian Mixture background model. On the contrary it chooses some simple information like the type of Macroblock etc.. Experimental results of several specific H.264 compressed video sequences demonstrate the good segmentation quality of the proposed approach. 2012 IEEE.

Research of ballistic missile early warning system (EI CONFERENCE) 会议论文 OAI收割
2nd International Conference on Advanced Engineering Materials and Technology, AEMT 2012, July 6, 2012 - July 8, 2012, Zhuhai, China
Zhang M.-H.; Zhang Y.-Y.

收藏 | 浏览/下载：34/0 | 提交时间：2013/03/25

To develop a lift early warning infrared device as a part of land or boat (ship) early warning system the system has the ability to target pre-discovery and instructions invasion. Methods: In support of distant air situation alerts the enemy aircraft missiles and other long-range goals obtain the target type and preliminary judgment of grade deliver the alarm information to the command system. The infrared alarm device detects the target's own infrared radiation passively alarms the incoming targets at low altitude and low altitude remote when radar and other equipment is out of work. Results: The accuracy of entire system reached 20 according the analysis. Conclusions: The device has a full range of complex background with high sensitivity high resolution anti-jamming fast response time and other characteristics. (2012) Trans Tech Publications Switzerland.

The new approach for infrared target tracking based on the particle filter algorithm (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: Sun H.; Han H.-X.

收藏 | 浏览/下载：60/0 | 提交时间：2013/03/25

Target tracking on the complex background in the infrared image sequence is hot research field. It provides the important basis in some fields such as video monitoring precision and video compression human-computer interaction. As a typical algorithms in the target tracking framework based on filtering and data connection the particle filter with non-parameter estimation characteristic have ability to deal with nonlinear and non-Gaussian problems so it were widely used. There are various forms of density in the particle filter algorithm to make it valid when target occlusion occurred or recover tracking back from failure in track procedure but in order to capture the change of the state space it need a certain amount of particles to ensure samples is enough and this number will increase in accompany with dimension and increase exponentially this led to the increased amount of calculation is presented. In this paper particle filter algorithm and the Mean shift will be combined. Aiming at deficiencies of the classic mean shift Tracking algorithm easily trapped into local minima and Unable to get global optimal under the complex background. From these two perspectives that "adaptive multiple information fusion" and "with particle filter framework combining" we expand the classic Mean Shift tracking framework.Based on the previous perspective we proposed an improved Mean Shift infrared target tracking algorithm based on multiple information fusion. In the analysis of the infrared characteristics of target basis Algorithm firstly extracted target gray and edge character and Proposed to guide the above two characteristics by the moving of the target information thus we can get new sports guide grayscale characteristics and motion guide border feature. Then proposes a new adaptive fusion mechanism used these two new information adaptive to integrate into the Mean Shift tracking framework. Finally we designed a kind of automatic target model updating strategy to further improve tracking performance. Experimental results show that this algorithm can compensate shortcoming of the particle filter has too much computation and can effectively overcome the fault that mean shift is easy to fall into local extreme value instead of global maximum value.Last because of the gray and fusion target motion information this approach also inhibit interference from the background ultimately improve the stability and the real-time of the target track. 2011 Copyright Society of Photo-Optical Instrumentation Engineers (SPIE).

Conditional random field for text segmentation from images with complex background 期刊论文 OAI收割
PATTERN RECOGNITION LETTERS, 2010, 卷号: 31, 期号: 14, 页码: 2295-2308
作者: Li, Minhua; Bai, Meng; Wang, Chunheng; Xiao, Baihua

收藏 | 浏览/下载：26/0 | 提交时间：2015/08/12

Conditional random field (CRF) Text segmentation Complex background Local information Contextual label information

Adaptive resolution storage system based on LOG-POLAR transform for multi-target trackers (EI CONFERENCE) 会议论文 OAI收割
2010 International Conference on Computer Application and System Modeling, ICCASM 2010, October 22, 2010 - October 24, 2010, Shanxi, Taiyuan, China
作者: Zhang Y.

收藏 | 浏览/下载：22/0 | 提交时间：2013/03/25

The main constrained problem of the video monitoring and storage system is the contradiction between large field of view and storage space limitations. Not all of the video information introduced by the image sensors need to be recorded especially for some tracking system which has appointed functions to track specifically kinds of targets. For instance the system not only works for single target if the monitor is appointed for human face tracking but also can work for multi-targets. High reconstruction resolution in the fovea region enables the successive application of recognition modules without sacrificing their performance the best system appears to be concentrating on human face only and all the others considered being background the low reconstruction resolution in the periphery helps to reduce the video data. 2010 IEEE. the background regions needn't to be recorded in detail. For this purpose this letter presents a real-time foveate storage system which efficiently represents the video image in log-polar coordinates with the foveate point centered on the target