机构

• 自动化研究所 [3]
• 长春光学精密机械与物... [1]

采集方式

• OAI收割 [4]

内容类型

• 期刊论文 [3]
• 会议论文 [1]

发表日期

• 2020 [1]
• 2018 [2]
• 2012 [1]

学科主题

筛选

浏览/检索结果: 共4条，第1-4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 A parallel vision approach to scene-specific pedestrian detection 期刊论文  OAI收割 NEUROCOMPUTING, 2020, 卷号: 394, 页码: 114-126 作者:  Zhang, Wenwen;  Wang, Kunfeng;  Liu, Yating;  Lu, Yue;  Wang, Fei-Yue   |  收藏  |  浏览/下载：27/0  |  提交时间：2020/06/22 Pedestrian detection  Specific scene  Synthetic data  Video surveillance  Parallel vision   CRF based text detection for natural scene images using convolutional neural network and context information 期刊论文  OAI收割 NEUROCOMPUTING, 2018, 卷号: 295, 页码: 46-58 作者:  Wang, Yanna;  Shi, Cunzhao;  Xiao, Baihua;  Wang, Chunheng;  Qi, Chengzuo   |  收藏  |  浏览/下载：47/0  |  提交时间：2018/10/10 Scene Text Detection  Mser  Cnn  Crf  Context Information  Shape-specific Classifiers   CRF based text detection for natural scene images using convolutional 期刊论文  OAI收割 Neurocomputing, 2018, 期号: 295, 页码: 46-58 作者:  Wang YN(王燕娜);  Shi,Cunzhao;  Baihua Xiao;  Chunheng Wang;  Chengzuo Qi   |  收藏  |  浏览/下载：65/0  |  提交时间：2018/06/01 Scene Text Detection  Mser  Cnn  Crf  Context Information  Shape-specific Classifiers   Characteristic point match algorithm based on the SURF in binocular stereo vision (EI CONFERENCE) 会议论文  OAI收割 5th International Conference on Intelligent Networks and Intelligent Systems, ICINIS 2012, November 1, 2012 - November 3, 2012, Tianjin, China 作者:  Wang L.;  Wang L.;  Wang L.;  Yang L.;  Yang L. 收藏  |  浏览/下载：25/0  |  提交时间：2013/03/25 One of the main components of the computer vision is 3D reconstruction. Extracts and the match based on two-dimensional picture characteristic point is the 3D reconstruction technology core. Taking binocular stereoscopic vision theory as a foundation  through extracts the characteristics of SURF based on the multi-scale analysis  this feature has specific scale reproducibility  put the epipolar constraints and disparity constraints as conditions judgement to specific screening  it is greatly reduced the search range. The experiment use the matching method for three different actual scenes  the results shows that the method can enhance the image matching speed and precision  and can get more precise dense parallax  used for reconstruction complete scene. 2012 IEEE.