SGER: Recognizing Objects by Simultaneously Combining Appearance and Geometry

标题：SGER：通过同时结合外观和几何来识别对象PI：Daniel Huttenlocher计算机视觉中对象识别的40年历史一直由自下而上的方法主导，即首先在图像中检测局部特征，然后将这些特征与对象的几何模型进行匹配。建议的项目研究的方法是将目标识别问题表述为单一的全局优化，而不是特征检测和匹配的连续阶段。该方法结合了关于局部图像块外观的自下而上信息和关于这些块之间几何关系的自上而下信息。主要的重点是识别对象的通用类，如自行车、人、摩托车或汽车。每个对象类被建模为以可变形配置排列的部件的集合，其中某些部件对通过弹簧连接。识别是从能量最小化的角度来描述的，其中在图像中每个可能的位置放置每个面片的成本，以及以拉伸连接它们的弹簧的方式放置面片对的成本。这样的能量最小化公式在1970年的S中被命名为图片结构，但由于其计算复杂性而被放弃。最近的算法进步使进一步研究这种方法成为可能。在检测和定位目标方面的初步结果令人振奋，但也表明，要形成一种可行的替代基于特征的目标识别的方法，还有很多工作要做。该项目研究了一些关键的初始问题，以确定能量最小化的目标识别方法是否可以替代当前基于特征的方法，包括如何在最少的监督下学习这样的模型，以及如何将对象比例和方向等全局几何信息融入到模型中。该方法计算成本图，确定图像中每个可能位置的每个部分的匹配程度。然后在能量最小化过程中将这些成本图组合在一起。相比之下，传统的特征检测方法找到图像中可能存在每个特征或部件的少量位置。虽然要素位置的稀疏性似乎比处理整个成本地图需要更少的计算，但实际上处理虚假和遗漏要素检测的必要性使得这种基于要素的方法计算非常密集。项目URL 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/