SGER: Recognizing Objects by Simultaneously Combining Appearance and Geometry

职务名称：SGER：PI：丹尼尔Huttenlocher计算机视觉中物体识别的40年历史一直由自下而上的方法主导，其中首先在图像中检测局部特征，然后将这些特征与物体的几何模型相匹配。 拟议的项目研究的方法，制定的对象识别问题作为一个单一的整体优化，而不是连续阶段的特征检测和匹配。 该方法结合了自下而上的局部图像补丁的外观信息与自上而下的这些补丁之间的几何关系的信息。 主要的重点是识别对象的通用类别，如自行车，人，摩托车或汽车。 每个对象类被建模为一个集合的部分安排在一个可变形的配置，其中某些对部分连接的弹簧。 识别是根据能量最小化来制定的，其中存在将每个补丁放置在图像中的每个可能位置处的成本，以及以拉伸连接它们的弹簧的方式放置补丁对的成本。 最近的算法进步使得进一步研究这种方法成为可能。 检测和定位物体的初步结果是有希望的，但也表明还有多少工作要做，这种方法形成一个可行的替代基于特征的物体识别。 拟议的项目调查了一些关键的初始问题，以确定物体识别的能量最小化方法是否可以作为当前基于特征的方法的可行替代方案，包括如何在最少的监督下学习这些模型，以及如何将全局几何信息（如对象比例和方向）合并到模型中。所提出的方法计算成本图，以确定每个部分在图像中的每个可能位置。 这些成本图然后在能量最小化过程中组合在一起。 相比之下，传统的特征检测方法找到少量的位置，其中每个特征或部分可能存在于图像中。 虽然特征位置的稀疏性可能看起来比使用整个成本图需要更少的计算，但处理虚假和遗漏特征检测的必要性实际上使得这种基于特征的方法在计算上非常密集。http://www.cs.cornell.edu/~dph/simulrec/

Title: SGER: Recognizing Objects by Simultaneously Combining Appearance and GeometryPI: Daniel HuttenlocherThe 40 year history of object recognition in computer vision has been dominated by bottom-up approaches where local features are first detected in an image and then those features are matched to geometric models of objects. The proposed project investigates methods that formulate the object recognition problem as a single overall optimization rather than as successive stages of feature detection and matching. The approach combines bottom-up information about the appearance of local image patches with top-down information about geometric relations between those patches. The main focus is on recognizing generic classes of objects such as bicycles, people, motorbikes, or cars. Each object class is modeled as a collection of parts arranged in a deformable configuration, where certain pairs of parts are connected by springs. Recognition is formulated in terms of energy minimization, where there is a cost for placing each patch at each possible location in the image, and a cost for placing pairs of patches in a manner that stretches the springs connecting them.Such an energy minimization formulation was proposed in the 1970's under the name Pictorial Structures, but was abandoned due to its computational complexity. Recent algorithmic advances have made it possible to further investigate this kind of approach. Initial results on detecting and localizing objects have been promising, but also demonstrate how much remains to be done for this approach to form a viable alternative to feature-based object recognition. The proposed project investigates some of the key initial questions in determining whether the energy minimization approach to object recognition could be a viable alternative to current feature-based approaches, including how to learn such models with minimal supervision, and how to incorporate global geometric information such as object scale and orientation into the models.The proposed approach computes cost maps that determine how well each part matches at each possible location in the image. These cost maps are then combined together in the energy minimization process. In contrast, traditional feature detection approaches find a small number of locations where each feature or part might be present in the image. While the sparse nature of feature locations may seem to require less computation than working with entire cost maps, the necessity of handling spurious and missed feature detections in fact makes such feature-based methods quite computationally intensive.Project URL http://www.cs.cornell.edu/~dph/simulrec/