0


用于高效物体检测的固定特征和折叠层次结构

Stationary Features and Folded Hierarchies for Efficient Object Detection
课程网址: http://videolectures.net/eml07_geman_sff/  
主讲教师: Donald Geman
开课单位: 约翰霍普金斯大学
开课时间: 2007-12-29
课程语种: 英语
中文简介:
用于从静止图像中的对象类别检测实例的大多数辨别技术包括使用专用二进制分类器在姿势空间的分区上循环。这种策略对于复杂的姿势是低效的,即,对于细粒度描述:i)对训练数据进行分段,这在处理高级变化时是不可避免的,严重降低了准确性; ii)由于访问大量姿势分区,高姿态分辨率下的计算成本过高。为了克服数据碎片,我将讨论一个以姿势索引,静止特征为中心的新颖框架,它允许对姿势特定分类器进行有效的一次性学习。这些特征为由图像和姿势组成的对分配响应,并且被设计成使得如果对象实际存在则响应的概率分布是恒定的。为了避免昂贵的场景处理,分类器基于姿势的嵌套分区以层次结构排列,这允许有效搜索。然后将层次“折叠”用于训练:每个级别的所有分类器都是从从所有数据中学习的一个基本预测器导出的。层次结构被“展开”用于测试:解析场景相当于仅在有足够证据表明较粗略的对象描述时才检查越来越精细的对象描述。我将通过在高度混乱的灰度场景中检测和定位猫来说明这些想法。这是与Francois Fleuret的联合工作。
课程简介: Most discriminative techniques for detecting instances from object categories in still images consist of looping over a partition of a pose space with dedicated binary classifiers. This strategy is inefficient for a complex pose, i.e., for fine-grained descriptions: i) fragmenting the training data, which is inevitable in dealing with high in-class variation, severely reduces accuracy; ii) the computational cost at high pose resolution is prohibitive due to visiting a massive pose partition. \\ To overcome data-fragmentation I will discuss a novel framework centered on pose-indexed, stationary features, which allows for efficient, one-shot learning of pose-specific classifiers. Such features assign a response to a pair consisting of an image and a pose, and are designed so that the probability distribution of the response is constant if an object is actually present. To avoid expensive scene processing, the classifiers are arranged in a hierarchy based on nested partitions of the pose, which allows for efficient search. The hierarchy is then "folded" for training: all the classifiers at each level are derived from one base predictor learned from all the data. The hierarchy is "unfolded" for testing: parsing a scene amounts to examining increasingly finer object descriptions only when there is sufficient evidence for coarser ones. I will illustrate these ideas by detecting and localizing cats in highly cluttered greyscale scenes. This is joint work with Francois Fleuret.
关 键 词: 静止图像; 辨别技术; 二进制分类器
课程来源: 视频讲座网
最后编审: 2019-04-10:lxf
阅读次数: 46