期刊
COMPUTERS & GRAPHICS-UK
卷 104, 期 -, 页码 86-94出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.cag.2022.03.010
关键词
Crowd simulation; Saliency; Visual attention
资金
- NSERC Discovery, Canada [RGPIN-2021-03541]
- National Science Foundation, USA [IIS-1703883, IIS-1955404, IIS-1955365, RETTL-2119265, EAGER-2122119]
- U.S. Department of Homeland Security [22STESE00001 01 01]
- U.S. Department of Homeland Security
- NSERC Create DAV
- ORF/ISSUM
This study proposes a parametric model and method for generating real-time saliency maps from the perspective of virtual agents. The model aggregates saliency scores from user-defined parameters and outputs a 2D saliency map that can be modulated by an attention field to incorporate 3D information and a character's state of attentiveness.
Modelling visual attention is an important aspect of simulating realistic virtual humans. This work proposes a parametric model and method for generating real-time saliency maps from the perspective of virtual agents which approximate those of vision-based saliency approaches. The model aggregates a saliency score from user-defined parameters for objects and characters in an agent's view and uses that to output a 2D saliency map which can be modulated by an attention field to incorporate 3D information as well as a character's state of attentiveness. The aggregate and parameterized structure of the method allows the user to model a range of diverse agents. The user may also expand the model with additional layers and parameters. The proposed method can be combined with normative and pathological models of the human visual field and gaze controllers, such as the recently proposed model of egocentric distractions for casual pedestrians that we use in our results.& nbsp;This is an extended version of a short paper published in MIG 2021. The extension includes an optimization approach that fits the parameters of the proposed model to established saliency models such as SALICON using a much larger and more realistic urban test set. (C)& nbsp;2022 Published by Elsevier Ltd.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据