RI: Small: Hierarchical Probabilistic Layers for Visual Recognition of Complex Objects

对于与现实世界交互和/或分析网络上可用的视觉信息的系统来说，学习视觉表示仍然是一个挑战。基于梯度直方图的简单视觉特征已经取得了重大进展：这些模型在具有高度纹理和接近平面的图案或部件的对象上工作得非常好。然而，这些系统在面对现实世界中某些类型的物体时，特别是具有复杂光度模型的物体，就会受到影响，因为这些物体没有区分局部平面的不透明纹理斑块。该项目开发了用于视觉识别的分层视觉模型，可以对这类现象进行建模。研究小组将这些方法建立在概率基础上，主要利用稀疏贝叶斯方法将观察到的图像特征分解成一组与加性图像形成过程相对应的组件层。考虑到模型的局部描述子和局部特征检测器变体，研究小组提出了透明物体情况下兴趣点检测的新概念：潜在因子尺度空间中的极值检测。该模型有可能在透明的情况下找到不变的局部检测，并且可以在一系列视觉应用中发挥作用，而不仅仅是纯粹的识别，稀疏的局部特征检测器已经证明了其价值（例如，配准，拼接，SLAM）。机器人视觉系统可以使用这种表示来增强对日常物体的识别，支持家庭和工业应用。这些表示也有助于智能媒体处理和索引。

Learning visual representations remains a challenge for systems which interact with the real world and/or analyze visual information available on the web. Significant progress has been made with simple visual features based on gradient histograms: these models work extremely well on objects that have highly textured and nearly planar patterns or parts. However, these systems suffer when faced with certain classes of real world objects that do not have discriminative locally-planar opaque texture patches, especially objects with complex photometric models. This project develops layered visual models for visual recognition, which can model these classes of phenomena. The research team grounds the methods in a probabilistic foundation, primarily exploiting a sparse Bayesian approach to factoring observed image features into a set of component layers corresponding to an additive image formation process. Considering both local descriptor and local feature detector variants of the model, the research team offers a new concept for interest point detection in the case of transparent objects: extrema detection in a latent-factor scale space. This model has the potential to find invariant local detections despite transparency, and could be useful in a range of vision applications beyond pure recognition for which sparse local feature detectors have proven valuable (e.g., registration, mosaicing, SLAM). Robotic vision systems can use this representation for enhanced recognition of everyday objects, supporting domestic and industrial applications. These representations also facilitate intelligent media processing and indexing.