RI: Small: Structured Sparse Conditional Random Fields Models for Joint Categorization and Segmentation of Objects.

对象分类和分割是计算机视觉中最重要和最具挑战性的问题之一。虽然这两个问题明显相关，但大多数现有文献将这两个任务分开处理。本项目通过开发同时使用类别级信息（自上而下）和像素级信息（自下而上）的对象联合分类和分割算法来弥补这一差距。该项目开发了一种新的图论范式，结合了条件随机场和稀疏表示理论的原理。在这个框架中，每个语义区域都用一个由对象、对象部分、子部分和超像素组成的过完备字典来表示。为了同时估计每个区域的分割和稀疏表示，研究小组为随机场定义了一个能量函数，其中包括作为应用于分割区域的稀疏表示的分类器的输出而获得的新的高阶势。研究小组还探索了基于结构化稀疏字典学习和潜在支持向量机的字典和分类器参数学习方法。此外，研究小组研究了有效的离散优化技术，以最大限度地减少结构稀疏模型与不同分类器相结合所产生的新能量。本研究的应用包括图像搜索、自主导航（道路、街道标志、行人和车辆的定位和识别）、医疗诊断工具（医学图像中病变和肿瘤的检测、定位和分类）、监控（可疑人员、武器和车辆的定位）和机器人（识别要与之交互的物体的边界和范围）。这个项目涉及不同层次的学生。

Object categorization and segmentation are arguably among the most important and challenging problems in computer vision. While these two problems are clearly related, most of the existing literature treats these tasks separately. This project bridges this gap by developing algorithms for joint categorization and segmentation of objects, which simultaneously use category-level information (top-down) and pixel-level information (bottom-up). This project develops a novel graph-theoretic paradigm that combines principles from conditional random fields and sparse representation theory. In this framework, each semantic region is represented in terms of an over-complete dictionary of objects, object parts, subparts and superpixels. To simultaneously estimate both the segmentation and a sparse representation for each region, the research team defines an energy function for the random field, which includes new higher order potentials obtained as the output of a classifier applied to the sparse representation of a segmented region. The research team also explores methods based on structured-sparse dictionary learning and latent support vector machines for learning the dictionaries and the classifier parameters. Furthermore, the research team investigates efficient discrete optimization techniques for minimizing the new energies resulting from the combination of structured-sparse models with different classifiers.Applications of this research include image search, autonomous navigation (localization and identification of the road, street signs, pedestrians and vehicles), medical diagnostic tools (detection, localization and classification of lesions and tumors in medical images), surveillance (localization of suspicious people, weapons and vehicles) and robotics (identifying the boundaries and extent of objects to be interacted with). The project involves students of different levels.