arrow
返回

Model-Agnostic Temporal Regularizer for Object Localization Using Motion Fields

delete2022-01-01
delete1
PRE
AI
C
Carlos Santiago *
D
Daniela O. Medley
J
Jorge S. Marques
J
Jacinto C. Nascimento
DOI:10.1109/TIP.2022.3155947delete
delete原文链接
delete分享
delete收藏
摘要

摘要

En 中文
Video analysis often requires locating and tracking target objects. In some applications, the localization system has access to the full video, which allows fine-grain motion information to be estimated. This paper proposes capturing this information through motion fields and using it to improve the localization results. The learned motion fields act as a model-agnostic temporal regularizer that can be used with any localization system based on keypoints. Unlike optical flow-based strategies, our motion fields are estimated from the model domain, based on the trajectories described by the object keypoints. Therefore, they are not affected by poor imaging conditions. The benefits of the proposed strategy are shown on three applications: 1) segmentation of cardiac magnetic resonance; 2) facial model alignment; and 3) vehicle tracking. In each case, combining popular localization methods with the proposed regularizer leads to improvement in overall accuracies and reduces gross errors.
Keyword:
Location awareness
Tracking
Trajectory
Predictive models
Computational modeling
Estimation
Motion segmentation
Object localization
motion fields
temporal regularization

期刊

IEEE Transactions on Image Processing 封面图
IEEE Transactions on Image Processing
IF:
13.7
论文数:
1.1W
被引数:
10.8W

机构

U
universidade de coimbra
学者数:
300
论文数: 107
被引数: 8.6K
引用论文

引用论文

Judgment Capacity, Fear of Falling, and the Risk of Falls in Community-Dwelling Older Adults: The Progetto Veneto Anziani Longitudinal Study社区居住的老年人的判断能力,对跌倒的恐惧和跌倒的风险: Progetto Veneto Anziani纵向研究
err2020-06-01
err0
errOAAI
errCaterina Trevisan; Bruno M. Zanforlini; Stefania Maggi; Marianna Noale; Federica Limongi; Marina De Rui; Maria Chiara Corti; Egle Perissinotto; Anna-Karin Welmer; Enzo Manzato; Giuseppe Sergi
err分享
err收藏
A 12.5Gb/s SerDes in 65nm CMOS Using a Baud-Rate ADC with Digital Receiver Equalization and Clock Recovery
err2007-02-01
err0
PREAI
errMike Harwood; Nirmal Warke; Richard Simpson; Tom Leslie; Ajith Amerasekera; Sean Batty; Derek Colman; Eugenia Carr; Venu Gopinathan; Steve Hubbins; Peter Hunt; Andy Joy; Pulkit Khandelwal; Bob Killips; Thomas Krause; Shaun Lytollis; Andy Pickering; Mark Saxton; David Sebastio; Graeme Swanson; Andre Szczepanek; Terry Ward; Jeff Williams; Richard Williams; Tom Willwerth
err分享
err收藏
Conductivity Enhancement in Thin Silicon-on-Insulator Layer Embedding Artificial Dislocation Network
err2011-02-01
err0
PREAI
errYasuhiko Ishikawa; Kazuaki Yamauchi; Chihiro Yamamoto; Michiharu Tabe
err分享
err收藏
Activity Recognition Using A Mixture of Vector Fields
err2013-05-01
err30
PREAI
errNascimento, Jacinto C.; Figueiredo, Mario A. T.; Marques, Jorge S.
err分享
err收藏
Automatic segmentation of echocardiographic sequences by active appearance motion models
err2002-11-01
err250
PREAI
errBosch, JG; Mitchell, SC; Lelieveldt, BPF; Nijland, F; Kamp, O; Sonka, M; Reiber, JHC
err分享
err收藏
err分享
err收藏
学者 查看更多内容