图 书 馆
同一目标的无监督检测与分割Unsupervised Detection and Segmentation of Identical Objects |
|
| 课程网址: | http://videolectures.net/cvpr2010_cho_udas/ |
| 主讲教师: | Minsu Cho |
| 开课单位: | 首尔国立大学 |
| 开课时间: | 2010-07-19 |
| 课程语种: | 英语 |
| 中文简介: |  我们解决了无监督的对象检测和分割问题，该问题超出了图像之间一对一对象对应关系或模型测试设置的常规假设。我们的方法可以直接从单个图像或少量图像中检测和分割相同的对象，而无需任何监督。为了从给定的图像中检测和分割所有的对象级对应关系，提出了一种新颖的多层匹配增长方法，该方法从初始局部特征匹配开始，并通过层内扩展和层间合并来探索图像。它估算对象实体之间的几何关系，并建立连接匹配对象的“对象对应网络”。实验证明了我们的方法在具有挑战性的数据集上的强大性能。 |
| 课程简介: | We address an unsupervised object detection and segmentation problem that goes beyond the conventional assumptions of one-to-one object correspondences or modeltest settings between images. Our method can detect and segment identical objects directly from a single image or a handful of images without any supervision. To detect and segment all the object-level correspondences from the given images, a novel multi-layer match-growing method is proposed that starts from initial local feature matches and explores the images by intra-layer expansion and inter-layer merge. It estimates geometric relations between object entities and establishes ‘object correspondence networks’ that connect matching objects. Experiments demonstrate robust performance of our method on challenging datasets. |
| 关 键 词: | 对象检测; 多层匹配; 数据集 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2021-03-25：zyk |
| 最后编审: | 2021-03-25：zyk |
| 阅读次数: | 53 |