解开模式和姿势因素:可见红外人重新识别的记忆-注意力和正交分解
IEEE transactions on neural networks and learning systems
|April 15, 2024
概括
这项研究引入了一种新型模型,通过分离模式和姿势因素,在可见和近红外图像中改进人重新识别 (Re-ID). 该方法在具有挑战性的低光条件下提高了跨模式匹配的准确性.
科学领域:
- 计算机视觉 计算机视觉
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 可见近红外 (VIS-NIR) 人重新识别 (Re-ID) 对于低光监控至关重要.
- 不同质的图像呈现模式,并造成差异,妨碍准确的身份匹配.
- 现有的方法很难有效地解开这些因素,以实现强大的交叉模式Re-ID.
研究的目的:
- 为VIS-NIR人重新识别提出一个新的解模式和姿势因素 (DMPF) 模型.
- 有效地应对模式所带来的挑战,并提出跨模式匹配的变化.
- 在各种成像条件下增强人重新识别系统的准确性和稳定性.
主要方法:
- 开发了一个三流特征提取网络 (TFENet) 来提取VIS-NIR图像和行人骨特征.
- 引入了使用存储队列和注意层的最佳传输 (OT) 来减少模式差异的模式因素解 (MFD).
- 实现的姿势因子解 (PFD) 与子空间直角分解和姿势特征一致性 (PfC) 损失来学习与姿势无关的特征.
主要成果:
- 拟议的DMPF模型有效地将模式和姿势因素从异构的图像特征中解脱出来.
- 在两个VIS-NIR行人Re-ID数据集上的实验验证显示,匹配准确度显著提高.
- 功能记忆和行人骨架信息的融合对于解至关重要.
结论:
- 通过有效处理模式和姿势变化,DMPF模型为VIS-NIR人重新识别提供了一个强大的解决方案.
- 解开这些因素会导致更具歧视性的身份表征,并改善跨模式匹配性能.
- 这种方法对现实世界的应用程序有希望,这些应用程序需要在具有挑战性的视觉环境中可靠的人员跟踪.
相关概念视频
Deindividuation
26.4K
Deindividuation is a form of social influence on an individual’s behavior such that the individual engages in unusual or non-normal behavior while in a group setting. Why? Because in these group settings, the individual no longer sees themselves as an individual anymore, disinhibiting their behavior and personal restraint.
26.4K
Perceptual Constancy
387
Perceptual constancy is the ability to recognize that objects remain consistent and unchanged even when their appearance varies due to changes in sensory input. There are four main types of perceptual constancy: size constancy, shape constancy, color constancy, and brightness constancy.
Size constancy is the recognition that an object remains the same size, even when its image on the retina changes. For instance, a bus is perceived to be large enough to carry people, even if it looks tiny from...
Size constancy is the recognition that an object remains the same size, even when its image on the retina changes. For instance, a bus is perceived to be large enough to carry people, even if it looks tiny from...
387


