Learning Rich Statistical Models of the Visual World for Robust Perception

学习丰富的视觉世界统计模型以实现稳健的感知

• 批准号: 0535075
• 负责人: Michael Black
• 金额: --
• 依托单位: Brown University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2005
• 资助国家: 美国
• 起止时间: 2005-08-01 至 2008-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0535075&HistoricalAwards=false
• 关键词: Learning; Rich; Statistical; Models; Visual

Robust intelligence rests on the ability to reason about missing, incomplete, ambiguous and corrupted data. This is particularly true in visual perception, where an intelligent system is faced with reasoning about the complexity of a changing three-dimensional world given only two-dimensional images. Bayesian inference has become popular for dealing with such problems because it provides a sound way of combining ambiguous sensor measurements with prior knowledge about the world. Priors represent the collected experience of a perceptual system and by integrating heterogeneous sources of information in a statistically sound way enable such a system to respond robustly to novel situations.Markov random fields (MRFs) provide a powerful and popular formalism for representing visual priors. However, they have typically modeled only local, pairwise pixel interactions, which limit their modeling capabilities. This project aims at increasing the power and applicability of these models using larger pixel neighborhoods (cliques). The proposed Fields-of-Experts (FoE) model generalizes many previous MRF models, and all its parameters can be learned from real-world training data. Preliminary experiments have shown that, for example, image reconstruction applications benefit from such richer visual priors, but many other application domains have remained unexplored. The development of these statistical modeling tools will also have an impact on other domains outside of machine vision where the need for modeling complex, high-dimensional data arises. Finally, the dissemination of the collected experimental data, learned models, and software promises to stimulate research and make possible quantitative comparisons towards better statistical models of the visual world.

强大的智能依赖于对缺失、不完整、模糊和损坏的数据进行推理的能力。 这在视觉感知中尤其如此，智能系统面临的是对只给出二维图像的变化的三维世界的复杂性的推理。 贝叶斯推理已经成为流行的处理这样的问题，因为它提供了一个健全的方式相结合的模糊传感器测量与先验知识的世界。 先验信息代表了感知系统的经验，通过统计上合理的方式整合不同的信息源，使这样的系统能够对新的情况做出鲁棒的响应。马尔可夫随机场（MRF）提供了一个强大的和流行的形式主义表示视觉先验信息。 然而，他们通常只对局部的、成对的像素交互进行建模，这限制了他们的建模能力。 该项目旨在使用更大的像素邻域（团）来提高这些模型的能力和适用性。 提出的专家领域（FoE）模型概括了许多以前的MRF模型，其所有参数都可以从真实世界的训练数据中学习。 初步的实验已经表明，例如，图像重建应用程序受益于这种更丰富的视觉先验，但许多其他应用领域仍然没有探索。 这些统计建模工具的开发也将对机器视觉以外的其他领域产生影响，这些领域需要对复杂的高维数据进行建模。 最后，收集的实验数据，学习模型和软件的传播有望刺激研究，使更好的统计模型的视觉世界的定量比较。