0


对象识别和分割协会

Object Recognition and Segmentation by Association
课程网址: http://videolectures.net/cmulls08_malisiewicz_orsa/  
主讲教师: Tomasz Malisiewicz
开课单位: 卡内基梅隆大学
开课时间: 信息不详。欢迎您在右侧留言补充。
课程语种: 英语
中文简介:
许多对象识别系统为每个对象类别训练不同的分类器,并使用滑动窗口方法对图像区域进行分类。在本文中,我们将对象识别问题描述为数据关联,其中一个新的对象仅用一小组示例对象来解释,与之在视觉上相似。我们为每个示例学习不同的距离函数,这样可以解释返回的距离以检测对象的存在。我们的示例以图像区域表示,所学的距离捕获了该区域的形状、颜色、纹理和位置特征的相对重要性。我们使用距离函数来检测和分割新图像中的对象,通过将从多个图像分割获得的自下而上的片段与示例区域相关联。我们从Labelme数据集评估了算法在真实室外场景中的检测和分割性能,并给出了一些定性的图像解析结果。
课程简介: Many object recognition systems train a different classifier for each object category and use the sliding window approach to classify image regions. In this talk, we pose the object recognition problem as data association where a novel object is explained solely in terms of a small set of exemplar objects to which it is visually similar. We learn a different distance function for each exemplar such that the returned distances can be interpreted to detect the presence of an object. Our exemplars are represented as image regions and the learned distances capture the relative importance of shape, color, texture, and position features for that region. We use the distance functions to detect and segment objects in novel images by associating the bottom-up segments obtained from multiple image segmentations with the exemplar regions. We evaluate the detection and segmentation performance of our algorithm on real-world outdoor scenes from the LabelMe dataset and also show some qualitative image parsing results.
关 键 词: 对象识别; 图像; 计算机视觉
课程来源: 视频讲座网
最后编审: 2020-06-22:chenxin
阅读次数: 29