中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共9条，第1-9条

帮助

条数/页：排序方式：
	An Improved Real-time Visual Tracking Method for Space Non-cooperate Target 会议论文 OAI收割 International Symposium on Infrared Technology and Application and the International Symposiums on Robot Sensing and Advanced Control, Beijing, May 9-11, 2016 作者: Zhang LM(张丽敏); Zhu F(朱枫); Hao YM(郝颖明) 收藏 \| 浏览/下载：36/0 \| 提交时间：2016/09/13 visual tracking space non-cooperate target 3D model false matches sampled points local region similarity
	Automatic Tracking Algorithm of Solar G-band Bright Points 会议论文 OAI收割 6th International Conference on Intelligent Networks and Intelligent Systems (ICINIS), Shenyang Inst Engn, Shenyang, PEOPLES R CHINA, 2013-11-01 作者: Yang, YF; Lin, JB; Deng LH(邓林华) 收藏 \| 浏览/下载：39/0 \| 提交时间：2016/04/06 tracking G-band bright points three dimensional space-time cube evolution
	Image registration based on Mexican-hat wavelets and pseudo-Zernike moments (EI CONFERENCE) 会议论文 OAI收割 2012 World Automation Congress, WAC 2012, June 24, 2012 - June 28, 2012, Puerto Vallarta, Mexico 作者: Liu Y.; Liu Y.; Liu Y. 收藏 \| 浏览/下载：49/0 \| 提交时间：2013/03/25 Image registration is a key technique in pattern recognition and image processing and it is widely used in many application areas such as computer vision remote sensing image fusion and object tracking. A method for image registration combining Mexican-hat wavelets and pseudo-Zernike moments is proposed. Firstly feature points are extracted using scale-interaction Mexican-hat wavelets in the reference image and sensed image respectively. Then pseudo-Zernike moments are used to match them and classical RANSAC used to eliminate the wrong matches. And then the well match points are used to estimate the best affine transform parameters by least squares minimization. At last the sensed image is transformed and resampled to accomplish the image registration. The experiments indicate that the proposed algorithm extracts feature points and matches them exactly and eliminates wrong matched points effectively and achieves nice registration results. 2012 TSI Press.
	A matching algorithm on statistical properties of Harris corner (EI CONFERENCE) 会议论文 OAI收割 2011 International Conference on Information and Automation, ICIA 2011, June 6, 2011 - June 8, 2011, Shenzhen, China 作者: He B. 收藏 \| 浏览/下载：39/0 \| 提交时间：2013/03/25 The fundamental goal of target recognition and video tracking is to match target template with source image. Most matching methods are based on image intensity or multi-feature points. And the latter method is more popular for its high accuracy and small calculation. Image Registration Based on Feature Points focus on effective feature extraction of image points and paradigm. Harris corner in the image rotation gray noise and viewpoint change conditions has an ideal match results is more recent application of one feature point. This paper extract the Harris corner deviation and covariance firstly experiments show that the two features exclusive then applied them to image registration for the first time. A set of actual images have shown this proposed method not only overcomes the complicated background gray uneven distribution problems but also pan and zoom the image has a good resistance. 2011 IEEE.
	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：122/0 \| 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).
	自然小场景增强现实关键技术研究学位论文 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, 2010 作者: 杨明浩收藏 \| 浏览/下载：76/0 \| 提交时间：2015/09/02 增强现实物体识别特征点匹配最小二乘法随机采样一致性视觉注意特征点跟踪 Augmented Reality object recongnition point matching least squares RANSAC visual attention points tracking
	Development of Laser Stripe Sensor for Automatic Seam Tracking in Robotic Tailored Blank Welding 会议论文 OAI收割 7th World Congress on Intelligent Control and Automation, Chongqing, China, June 25-27, 2008 作者: Zou YY(邹媛媛); Zhao MY(赵明扬); Zhang L(张雷); Jiang CY(姜春英) 收藏 \| 浏览/下载：34/0 \| 提交时间：2012/06/06 laser strip sensor seam tracking tailored blank welding error analysis feature points extracting
	Real time tracking by LOPF algorithm with mixture model (EI CONFERENCE) 会议论文 OAI收割 MIPPR 2007: Automatic Target Recognition and Image Analysis; and Multispectral Image Acquisition, November 15, 2007 - November 17, 2007, Wuhan, China Meng B.; Zhu M.; Han G.; Wu Z. 收藏 \| 浏览/下载：40/0 \| 提交时间：2013/03/25 A new particle filter-the Local Optimum Particle Filter (LOPF) algorithm is presented for tracking object accurately and steadily in visual sequences in real time which is a challenge task in computer vision field. In order to using the particles efficiently we first use Sobel algorithm to extract the profile of the object. Then we employ a new Local Optimum algorithm to auto-initialize some certain number of particles from these edge points as centre of the particles. The main advantage we do this in stead of selecting particles randomly in conventional particle filter is that we can pay more attentions on these more important optimum candidates and reduce the unnecessary calculation on those negligible ones in addition we can overcome the conventional degeneracy phenomenon in a way and decrease the computational costs. Otherwise the threshold is a key factor that affecting the results very much. So here we adapt an adaptive threshold choosing method to get the optimal Sobel result. The dissimilarities between the target model and the target candidates are expressed by a metric derived from the Bhattacharyya coefficient. Here we use both the counter cue to select the particles and the color cur to describe the targets as the mixture target model. The effectiveness of our scheme is demonstrated by real visual tracking experiments. Results from simulations and experiments with real video data show the improved performance of the proposed algorithm when compared with that of the standard particle filter. The superior performance is evident when the target encountering the occlusion in real video where the standard particle filter usually fails.
	A segment detection method based on improved Hough transform (EI CONFERENCE) 会议论文 OAI收割 ICO20: Optical Information Processing, August 21, 2005 - August 26, 2005, Changchun, China 作者: 收藏 \| 浏览/下载：40/0 \| 提交时间：2013/03/25 Hough transform is recognized as a powerful tool in shape analysis which gives good results even in the presence of noise and the disconnection of edge. However 3. applying the standard Hough transform equation to every point of the input image edge 4. according to the local threshold 6. merging the segments whose extreme points are near. Experiment results show the approach not only can recognize regular geometric object but also can extract the segment feature of real targets in complex environment. So the proposed method can be used in the target detection of complicated scenes traditional Hough transform can only detect the lines 2. quantizing the parameter space and extracting a group of maximums according to the global threshold eliminating spurious peaks which are caused by the spreading effects and will improve the precision of tracking. cannot give the endpoints and length of the line segments and it is vulnerable to the quantization errors. Based on the analysis of its limitations Hough transform has been improved in order to detect line segment feature of targets. The algorithm aims to avoid the loss of spatial information as well as to eliminate the spurious peaks and fix on the line segments endpoints accurately 5. fixing on the endpoints of the segments according to the dynamic clustering rule which can expediently be used for the description and classification of regular objects. The method consists of 6 steps: 1. setting up the image parameter and line-segment spaces