中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共6条，第1-6条

帮助

条数/页：排序方式：
	An FPGA-Based Ultra-High-Speed Object Detection Algorithm with Multi-Frame Information Fusion 期刊论文 OAI收割 SENSORS, 2019, 卷号: 19, 期号: 17, 页码: 16 作者: Long, Xianlei; Hu, Shenhua; Hu, Yiming; Gu, Qingyi; Ishii, Idaku \| 收藏 \| 浏览/下载：82/0 \| 提交时间：2019/12/16 ultra-high-speed vision object detection field-programmable gate array histogram of oriented gradient multi-frame information fusion model
	基于概率图模型的视频目标跟踪与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: 中国科学院大学, 2015 作者: 刘玉强收藏 \| 浏览/下载：97/0 \| 提交时间：2015/09/02 智能交通系统概率图模型目标跟踪车型识别条件随机场动态贝叶斯网络 Intelligent transportation system Probabilistic graphical model Object tracking Vehicle recognition Conditional random field Dynamic Bayesian network
	A cluster-based method for marine sensitive object extraction and representation 期刊论文 OAI收割 JOURNAL OF OCEAN UNIVERSITY OF CHINA, 2015, 卷号: 14, 期号: 4, 页码: 2027-2047 作者: Xue Cunjin; Dong Qing; Qin Lijuan 收藏 \| 浏览/下载：16/0 \| 提交时间：2016/04/20 marine sensitive object kernel-based expansion Field-object model remote sensing images global change
	Buffer and vibration optimization of missile data recorder structure (EI CONFERENCE) 会议论文 OAI收割 2011 International Conference on Mechatronics and Materials Processing, ICMMP 2011, November 18, 2011 - November 20, 2011, Guangzhou, China 作者: Zhang J.; Zhang J.; Zhang J. 收藏 \| 浏览/下载：37/0 \| 提交时间：2013/03/25 On the analysis of the original data recorder the stress wave theory is the elastic theory can explain the filter buffer question from the micro-small space made several key problems clear when buffer and damping from this designed a composite structure for vibration reduction distinguished between a cushion theory and application field of stress wave theory which made the dynamic stress of protected component down about one order of magnitude. Optimization with Isight and Ls-dyna the traditional rigid spring-buffer model whose object is to reduce the impact of acceleration that can not accurately describe the elastic force of the part of the actual situation the protected component's dynamic stress down about 69.3% and the data recorder's quality 300g lower finally passed the Marshall Hammer test successfully. 2011 Trans Tech Publications.
	Patches-based Markov random field model for multiple object tracking under occlusion 期刊论文 OAI收割 SIGNAL PROCESSING, 2010, 卷号: 90, 期号: 5, 页码: 1518-1529 作者: Wu, Mingjun; Peng, Xianrong; Zhang, Qiheng; Zhao, Rujin 收藏 \| 浏览/下载：35/0 \| 提交时间：2015/09/21 Multiple object tracking Appearance model Markov random field Occlusion
	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：34/0 \| 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.