返回
Model-Agnostic Temporal Regularizer for Object Localization Using Motion Fields
DOI:10.1109/TIP.2022.3155947.png)
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
IF:
13.7
论文数:
1.1W
被引数:
10.8W
机构
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
Conductivity Enhancement in Thin Silicon-on-Insulator Layer Embedding Artificial Dislocation Network
The influence of various precursors on solar-light-driven g-C3N4 synthesis and its effect on photocatalytic tetracycline hydrochloride (TCH) degradation各种前体对太阳光驱动的g-C3N4合成及其对光催化盐酸四环素 (TCH) 降解的影响
No balance between glutamate+glutamine and GABA+ in visual or motor cortices of the human brain: A magnetic resonance spectroscopy study
NeuroImage
IF0

