机构

• 自动化研究所 [4]
• 计算技术研究所 [1]
• 沈阳自动化研究所 [1]

采集方式

• OAI收割 [6]

内容类型

• 期刊论文 [5]
• 会议论文 [1]

发表日期

• 2022 [1]
• 2021 [1]
• 2016 [2]
• 2015 [1]
• 2013 [1]

学科主题

筛选

浏览/检索结果: 共6条，第1-6条 帮助 条数/页： 5101520253035404550556065707580859095100 排序方式： 请选择题名升序题名降序提交时间升序提交时间降序作者升序作者降序发表日期升序发表日期降序 Large-Scale Semantic Scene Understanding with Cross-Correction Representation 期刊论文  OAI收割 REMOTE SENSING, 2022, 卷号: 14, 期号: 23, 页码: 15 作者:  Zhao, Yuehua;  Zhang, Jiguang;  Ma, Jie;  Xu, Shibiao   |  收藏  |  浏览/下载：21/0  |  提交时间：2023/03/20 point cloud  large-scale semantic segmentation  spatial geometric  semantic context  cross-correction   Context-Aware Dynamic Feature Extraction for 3D Object Detection in Point Clouds 期刊论文  OAI收割 IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2021, 页码: 13 作者:  Tian, Yonglin;  Huang, Lichao;  Yu, Hui;  Wu, Xiangbin;  Li, Xuesong   |  收藏  |  浏览/下载：24/0  |  提交时间：2022/01/27 Three-dimensional displays  Feature extraction  Convolution  Proposals  Kernel  Laser radar  Semantics  Point clouds  3D detection  dynamic network  context features   Background of shape contexts for point matching 期刊论文  OAI收割 PATTERN RECOGNITION LETTERS, 2016, 卷号: 84, 期号: 无, 页码: 114-119 作者:  Qian, Deheng;  Chen, Tianshi;  Qiao, Hong 收藏  |  浏览/下载：29/0  |  提交时间：2016/12/07 Point matching  Shape context  Local feature   Background of shape contexts for point matching 期刊论文  OAI收割 PATTERN RECOGNITION LETTERS, 2016, 卷号: 84, 页码: 114-119 作者:  Qian, Deheng;  Chen, Tianshi;  Qiao, Hong   |  收藏  |  浏览/下载：19/0  |  提交时间：2019/12/12 Point matching  Shape context  Local feature   Finding logos in real-world images with point-context representation-based region search 期刊论文  OAI收割 MULTIMEDIA SYSTEMS, 2015, 卷号: 21, 期号: 3, 页码: 301-311 作者:  Wang, Jinqiao;  Fu, Jianlong;  Lu, Hanqing 收藏  |  浏览/下载：26/0  |  提交时间：2015/09/17 Logo recognition  Point-context  Region search   A shape context based Hausdorff similarity measure in image matching 会议论文  OAI收割 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：36/0  |  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.