中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共7条，第1-7条

帮助

条数/页：排序方式：
	OS-DS tracker: Orientation-variant Siamese 3D tracking with Detection based Sampling 期刊论文 OAI收割 PATTERN RECOGNITION LETTERS, 2023, 卷号: 174, 页码: 7 作者: Zhang, Qiuyu; Wang, Lipeng; Li, Wanyi; Meng, Hao; Zhang, Wen \| 收藏 \| 浏览/下载：18/0 \| 提交时间：2023/11/16 LIDAR point clouds Object tracking Gaussian sampling Candidate regions Auto-encoder
	Multilevel Building Detection Framework in Remote Sensing Images Based on Convolutional Neural Networks 期刊论文 OAI收割 IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2018, 卷号: 11, 期号: 10, 页码: 3688, 3700 作者: Peethambaran, Jiju; Sun, Lan; Chen, Chuqun; Ke, Yinghai; Chen, Dong \| 收藏 \| 浏览/下载：55/0 \| 提交时间：2019/08/27 Building detection convolutional neural networks (CNNs) candidate building regions multilevel framework remote sensing images
	Fast infrared sea ship target detection based on improved BING algorithm 会议论文 OAI收割 LIDAR IMAGING DETECTION AND TARGET RECOGNITION 2017, Changchun, China, July 23-25, 2017 作者: Liu YP(刘云鹏); Shi ZL(史泽林); Li LX(李乐星) \| 收藏 \| 浏览/下载：16/0 \| 提交时间：2017/12/21 Infrared image Sea ship BING algorithm Candidate regions
	Effective Candidate Component Extraction for Text Localization in Born-Digital Images by Combining Text Contours and Stroke Interior Regions 会议论文 OAI收割希腊, 2016-4 作者: Chen, Kai; Yin, Fei; Liu, Chenglin \| 收藏 \| 浏览/下载：11/0 \| 提交时间：2016/07/14 Candidate Component Extraction Text Contours Stroke Interior Regions Text Localization.
	Automatic bridge extraction for optical images (EI CONFERENCE) 会议论文 OAI收割 6th International Conference on Image and Graphics, ICIG 2011, August 12, 2011 - August 15, 2011, Hefei, Anhui, China Gu D.-Y.; Zhu C.-F.; Shen H.; Hu J.-Z.; Chang H.-X. 收藏 \| 浏览/下载：25/0 \| 提交时间：2013/03/25 This paper describes a novel hierarchy algorithm for extracting bridges over water in optical images. To reduce the omission of bridges by searching the edge we extract the river regions which the bridges are included in. Firstly we segment the optical image to get the coarse water bodies using iterative threshold eliminate the noise regions and add the missing regions based on k-means clustering with texture information and spatial coherence. Then the blanks are connected based on shape features and candidate bridge regions are segmented from river regions. Finally the bridges are verified by geometric information and the ubiety between bridges and river. The results show that this approach is efficient and effective for extracting bridges in satellite image from Google Earth and in aerial optical images acquired by unmanned aerial vehicle. 2011 IEEE.
	Fast covariance matching based on Genetic Algorithm (EI CONFERENCE) 会议论文 OAI收割 2010 6th International Conference on Wireless Communications, Networking and Mobile Computing, WiCOM 2010, September 23, 2010 - September 25, 2010, Chengdu, China 作者: Zhang X.; Zhang L.; Zhang L.; Zhang X.; Zhang X. 收藏 \| 浏览/下载：13/0 \| 提交时间：2013/03/25 This paper proposes an effective framework to boost the efficiency of covariance matching. In this framework covariance matrices are used to match object in complex environment by fusing multiple features. Then Genetic Algorithm (GA) is employed to improve the processing speed of covariance matching. To take advantage of the property of GA for the optimization in large search spaces to covariance matching a fitness function is designed using the distances between the covariance matrices of model and candidate regions. Experimental results show that the proposed approach can improve the processing speed of covariance matching observably. The computing speed of the proposed method is at least 7 times than that of exhaustive searching. 2010 IEEE.
	Affine object recognition and affine parameters estimation based on covariant matrix (EI CONFERENCE) 会议论文 OAI收割 2008 International Symposium on Information Science and Engineering, ISISE 2008, December 20, 2008 - December 22, 2008, Shanghai, China 作者: Wang Y.; Wang Y.; Wang Y.; Wang Y.; Wang Y. 收藏 \| 浏览/下载：121/0 \| 提交时间：2013/03/25 A new method of affine object recognition and affine parameters estimation is presented. For a real-time image and a group of templates in addition firstly on the basis of correct recognition we segment the object regions in them and compute their covariant matrices. Secondly it can estimate affine parameters exactly normalize the ellipse regions defined by covariant matrices to circle regions to get rotational invariants and the estimated error is within 3%. 2008 IEEE. and compute the similarity function value between rotational invariants of real-time image and every template respectively. Then compare the values with threshold set in advance if more than one value is larger than threshold take the corresponding templates as candidates and compute affine matrix between real-time image and every candidate. Finally transform the realtime image with every affine matrix and match the result with corresponding candidate by classical matching methods. Experimental results show that the presented method is robust to illumination with low computational complexity and it can realize recognition of different affine objects