中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共8条，第1-8条

帮助

条数/页：排序方式：
	面向海量监控视频的智能目标分析与管理系统设计与实现学位论文 OAI收割工程硕士, 中国科学院自动化研究所: 中国科学院大学, 2013 董纪超收藏 \| 浏览/下载：86/0 \| 提交时间：2015/09/02 视频分析目标检测目标跟踪目标提取目标管理 Video Analysis Object Detection Object Track Object Extraction Object Management
	Study on sub-pixel techniques for accurate image measurement of displacement (EI CONFERENCE) 会议论文 OAI收割 2011 2nd International Conference on Advanced Measurement and Test, AMT 2011, June 24, 2011 - June 26, 2011, Nanchang, China 作者: Zhang X.; Zhang X.; Zhang X. 收藏 \| 浏览/下载：35/0 \| 提交时间：2013/03/25 The high resolving power camera was often used to improve the precision of measuring system although its price is high because the accuracy of image measure was limited by the pixel resolving ability of camera. A method of one dimension gray level quadrature sub-pixel to detect edge was presented. This method was applied to measure the displacement of measuring head on 3-coordinate measuring machine. The data of test was shown that this system can distinguish displacement 0.001mm. it is higher accuracy than pixel level. So this method is convenient and fast fit to track and measure the moving object. It is obvious that this method can save the cost of hardware.
	Study particle filter tracking and detection algorithms based on DSP signal processors (EI CONFERENCE) 会议论文 OAI收割 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010, August 24, 2010 - August 26, 2010, Changchun, China Dong Y.; Chuan W. 收藏 \| 浏览/下载：39/0 \| 提交时间：2013/03/25 In Video tracking detection and tracking usually need two algorithms. The process is complex and need much time which detection and tracking are. In this paper a hybrid valued sequential state vector is formulated. The state vector is characterized by information of target appearance flag and of location. Particle filter-based method implements detection and tracking at one time. In order to reduce process time and think of pixel position in tracking field feature histogram of luminance is as observe vector and used posterior estimate. In this paper the luminance component is derived and target is recognized and tracked through image processor based on DSP in order to implementing real-time. The experimental results confirm that method can detect and track the object in real-time successfully when the number of particles is 160. The method is robust for rolling scale and partial occlusion. 2010 IEEE.
	Study on color image tracking and detection algorithms based on particle filter (EI CONFERENCE) 会议论文 OAI收割 International Symposium on Photoelectronic Detection and Imaging 2009: Advances in Infrared Imaging and Applications, June 17, 2009 - June 19, 2009, Beijing, China Wu C.; Sun H.-J.; Yang D. 收藏 \| 浏览/下载：40/0 \| 提交时间：2013/03/25 In Video tracking detection and tracking need two algorithms. The process is complex and need much time which detection and tracking is. In this paper a hybrid valued sequential state vector is formulated. The state vector is characterized by information of target appearance and of location. Particle filter-based method implements detection and tracking. In order to reduce process time and think of pixel position in tracking field feature histogram of color-based is as observe vector and used posterior estimate. The experimental results confirm that method can detect and track object in 17.68ms successfully when the number of particles is 160. The method is robust for rolling scale and partial occlusion. 2009 SPIE.
	Mean shift tracking combining SIFT (EI CONFERENCE) 会议论文 OAI收割 2008 9th International Conference on Signal Processing, ICSP 2008, October 26, 2008 - October 29, 2008, Beijing, China 作者: Xue C. 收藏 \| 浏览/下载：82/0 \| 提交时间：2013/03/25 A novel visual tracking algorithm to cope with occlusion and scale variation is proposed. This method combines mean shift and SIFT algorithm to track object. SIFT algorithm is invariant to rotation translation and scale variation. But it is a timeconsuming algorithm. The wasting time is related to image size. So the proposed algorithm first adopts mean shift to initially locate object position then SIFT operator is used to detect features in object area and model area lastly the proposed method matches features in these two areas and calculates the relationship between them using affine transform. According to affine transform parameters the state of object can be adjusted in time. In order to reduce process time an improved feature matching algorithm is proposed in this paper. Experiments show that the proposed algorithm deals with occlusion successfully and can adjust object size in time. 2008 IEEE.
	Study of high speed photography measuring instrument (EI CONFERENCE) 会议论文 OAI收割 27th International Congress on High-Speed Photography and Photonics, September 17, 2006 - September 22, 2006, Xi'an, China Zhang Z.; Sun J.; Wu K. 收藏 \| 浏览/下载：52/0 \| 提交时间：2013/03/25 High speed photograph measuring instrument is mainly used to measure and track the exterior ballistics which can measure the flying position of the missile in the initial phase and trajectory. A new high speed photograph measuring instrument is presented in this paper. High speed photography measuring system records the parameters of object real-time and then acquires the flying position and trajectory data of the missile in the initial phase. The detection distance of high speed photography is more than 4.5km and the least detection distance is 450m under the condition of well-balanced angular velocity and angular acceleration program pilot track error less than 5. This instrument also can measure and record the flying trail and trajectory parameters of plane aero naval missile.
	Intersectant multi-target serial number fuzzy match by multi-parameters (EI CONFERENCE) 会议论文 OAI收割 ICO20: Optical Information Processing, August 21, 2005 - August 26, 2005, Changchun, China 作者: Wang Y.-J. 收藏 \| 浏览/下载：267/0 \| 提交时间：2013/03/25 In order to match the intersectant targets' tab when these objects separate a kind of method that makes use of fuzzy multi-parameter to match targets is proposed. Multi-parameters include the forecasted position after targets separate target speed target size and geometry shape and different parameter corresponds to different influence coefficient evaluate the integrated matching coefficient that every observation target corresponds to forecasted target and the corresponding relationship that matching coefficient is the biggest is the best matching result. In order to locate the position and speed of forecasted target a new method of track forecast is proposed firstly Hough transform is used to the object's track before objects intersect by this the object's positions that the warp between forecasted location and observation location is large enough is eliminated then least square method is used for track forecast by the remainder valid positions and get hold of the forecasted position when objects separate. The experiment results show: when tracking the bulky objects which intersect and separate the right identification probability of traditional least square method is 87.5% and the right identification probability of fuzzy match by multi-parameters can attain 96% the reliability improves in evidence.
	High-accuracy real-time automatic thresholding for centroid tracker (EI CONFERENCE) 会议论文 OAI收割 ICO20: Optical Information Processing, August 21, 2005 - August 26, 2005, Changchun, China 作者: Wang Y.; Wang Y.; Wang Y.; Wang Y.; Zhang Y. 收藏 \| 浏览/下载：51/0 \| 提交时间：2013/03/25 Many of the video image trackers today use the centroid as the tracking point. In engineering we can get several key pairs of peaks which can include the target and the background around it and use the method of Otsu to get intensity thresholds from them. According to the thresholds it give a great help for us to get a glancing size a target's centroid is computed from a binary image to reduce the processing time. Hence thresholding of gray level image to binary image is a decisive step in centroid tracking. How to choose the feat thresholds in clutter is still an intractability problem unsolved today. This paper introduces a high-accuracy real-time automatic thresholding method for centroid tracker. It works well for variety types of target tracking in clutter. The core of this method is to get the entire information contained in the histogram we can gain the binary image and get the centroid from it. To track the target so that we can compare the size of the object in the current frame with the former. If the change is little such as the number of the peaks the paper also suggests subjoining an eyeshot-window we consider the object has been tracked well. Otherwise their height just like our eyes focus on a target if the change is bigger than usual position and other properties in the histogram. Combine with this histogram analysis we will not miss it unless it is out of our eyeshot we should analyze the inflection in the histogram to find out what happened to the object. In general the impression will help us to extract the target in clutter and track it and we will wait its emergence since it has been covered. To obtain the impression what we have to do is turning the analysis into codes for the tracker to determine a feat threshold. The paper will show the steps in detail. The paper also discusses the hardware architecture which can meet the speed requirement. the paper offers a idea comes from the method of Snakes