机构

• 自动化研究所 [3]
• 长春光学精密机械与物... [2]
• 计算技术研究所 [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

• 2023 [2]
• 2021 [1]
• 2019 [2]
• 2007 [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 SOTVerse: A User-Defined Task Space of Single Object Tracking 期刊论文  OAI收割 International Journal of Computer Vision, 2023, 页码: 1-59 作者:  Shiyu, Hu;  Xin, Zhao;  Kaiqi Huang   |  收藏  |  浏览/下载：17/0  |  提交时间：2024/01/22 Single object tracking  Experimental environment  Evaluation system  Performance analysis   Global Instance Tracking: Locating Target More Like Humans 期刊论文  OAI收割 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 卷号: 45, 期号: 1, 页码: 576-592 作者:  Hu, Shiyu;  Zhao, Xin;  Huang, Lianghua;  Huang, Kaiqi   |  收藏  |  浏览/下载：20/0  |  提交时间：2023/02/22 Global instance tracking  single object tracking  benchmark dataset  performance evaluation  human tracking ability   SiamCPN: Visual tracking with the Siamese center-prediction network 期刊论文  OAI收割 COMPUTATIONAL VISUAL MEDIA, 2021, 卷号: 7, 期号: 2, 页码: 253-265 作者:  Chen, Dong;  Tang, Fan;  Dong, Weiming;  Yao, Hanxing;  Xu, Changsheng   |  收藏  |  浏览/下载：40/0  |  提交时间：2021/06/15 Siamese network  single object tracking  anchor-free  center point detection   The Unmanned Aerial Vehicle Benchmark: Object Detection, Tracking and Baseline 期刊论文  OAI收割 INTERNATIONAL JOURNAL OF COMPUTER VISION, 2019, 页码: 19 作者:  Yu, Hongyang;  Li, Guorong;  Zhang, Weigang;  Huang, Qingming;  Du, Dawei   |  收藏  |  浏览/下载：41/0  |  提交时间：2020/12/10 UAV  Object detection  Single object tracking  Multiple object tracking   Enhanced Multiple-Object Tracking Using Delay Processing and Binary-Channel Verification 期刊论文  OAI收割 Applied Sciences-Basel, 2019, 卷号: 9, 期号: 22, 页码: 19 作者:  M.Y.Li;  X.He;  Z.H.Wei;  J.Wang;  Z.Y.Mu   |  收藏  |  浏览/下载：35/0  |  提交时间：2020/08/24 multiple object tracking,identity consistency,single object tracking,association,Chemistry,Engineering,Materials Science,Physics   Integrated intensity, orientation code and spatial information for robust tracking (EI CONFERENCE) 会议论文  OAI收割 2007 2nd IEEE Conference on Industrial Electronics and Applications, ICIEA 2007, May 23, 2007 - May 25, 2007, Harbin, China 作者:  Wang Y.;  Wang Y.;  Wang Y.;  Wang Y.;  Wang Y. 收藏  |  浏览/下载：26/0  |  提交时间：2013/03/25 real-time tracking is an important topic in computer vision. Conventional single cue algorithms typically fail outside limited tracking conditions. Integration of multimodal visual cues with complementary failure modes allows tracking to continue despite losing individual cues. In this paper  we combine intensity  orientation codes and special information to form a new intensity-orientation codes-special (IOS) feature to represent the target. The intensity feature is not affected by the shape variance of object and has good stability. Orientation codes matching is robust for searching object in cluttered environments even in the cases of illumination fluctuations resulting from shadowing or highlighting  etc The spatial locations of the pixels are used which allow us to take into account the spatial information which is lost in traditional histogram. Histograms of intensity  orientation codes and spatial information are employed for represent the target Mean shift algorithm is a nonparametric density estimation method. The fast and optimal mode matching can be achieved by this method. In order to reduce the compute time  we use the mean shift procedure to reach the target localization. Experiment results show that the new method can successfully cope with clutter  partial occlusions  illumination change  and target variations such as scale and rotation. The computational complexity is very low. If the size of the target is 3628 pixels  it only needs 12ms to complete the method. 2007 IEEE.