QQ客服 官方微博 反馈留言

浏览/检索结果: 共6条，第1-6条 帮助 限定条件 专题：沈阳自动化研究所    第一署名单位    第一作者单位    通讯作者单位     已选(0)清除 条数/页：5101520253035404550556065707580859095100   排序方式：请选择作者升序作者降序题名升序题名降序发表日期升序发表日期降序提交时间升序提交时间降序 An improved SSD for small target detection 会议论文 Zhuhai, China, January 8-10, 2021 作者:  Li X(李翔);  Luo HB(罗海波) 收藏  |  浏览/下载：24/0  |  提交时间：2021/06/27 Convolution neural network  Small targets  SSD  Target detection   Adaptive Greedy Dictionary Selection for Web Media Summarization 期刊论文 IEEE Transactions on Image Processing, 2017, 卷号: 26, 期号: 1, 页码: 185-195 作者:  Cong Y(丛杨);  Liu J(刘霁);  Sun G(孙干);  You, Quanzeng;  Li, Yuncheng 收藏  |  浏览/下载：35/0  |  提交时间：2016/12/29 Sparse representation  norm  dictionary learning  dictionary selection  forward-backward  greedy method   基于非负矩阵分解的图像聚类和标注方法研究 学位论文 博士: 中国科学院沈阳自动化研究所, 2016 作者:  李冰锋 收藏  |  浏览/下载：167/0  |  提交时间：2016/12/15 非负矩阵分解  几何结构保持  图正则化  多视图学习  图像标注   Incremental echo state network for a water-jet propulsion USV: Theoretical and experimental research 会议论文 2016 American Control Conference, ACC 2016, Boston, MA, United states, July 6－8, 2016 作者:  Li DC(李德才);  He YQ(何玉庆) 收藏  |  浏览/下载：21/0  |  提交时间：2016/11/14 A shape context based Hausdorff similarity measure in image matching 会议论文 5th International Symposium on Photoelectronic Detection and Imaging (ISPDI) - Infrared Imaging and Applications, Beijing, June 25-27, 2013 作者:  Ma TL(马天磊);  Liu YP(刘云鹏);  Shi ZL(史泽林);  Yin J(尹健) 收藏  |  浏览/下载：24/0  |  提交时间：2013/12/26 The traditional Hausdorff measure, which uses Euclidean distance metric (L2 norm) to define the distance between coordinates of any two points, has poor performance in the presence of the rotation and scale change although it is robust to the noise and occlusion. To address the problem, we define a novel similarity function including two parts in this paper. The first part is Hausdorff distance between shapes which is calculated by exploiting shape context that is rotation and scale invariant as the distance metric. The second part is the cost of matching between centroids. Unlike the traditional method, we use the centroid as reference point to obtain its shape context that embodies global information of the shape. Experiment results demonstrate that the function value between shapes is rotation and scale invariant and the matching accuracy of our algorithm is higher than that of previously proposed algorithm on the MEPG-7 database.   A robust template tracking algorithm with weighted active drift correction 期刊论文 PATTERN RECOGNITION LETTERS, 2011, 卷号: 32, 期号: 9, 页码: 1317-1327 作者:  Fan BJ(范保杰);  Du YK(杜英魁);  Zhu LL(朱琳琳);  Sun J(孙静);  Tang YD(唐延东) 收藏  |  浏览/下载：12/0  |  提交时间：2012/05/29 Template tracking  Inverse compositional algorithm  Active drift correction  Template update