图 书 馆
视频中的无监督目标发现与分割Unsupervised Object Discovery and Segmentation in Videos |
|
| 课程网址: | http://videolectures.net/bmvc2013_schulter_object_discovery/ |
| 主讲教师: | Samuel Schulter |
| 开课单位: | 格拉茨理工大学 |
| 开课时间: | 2014-04-03 |
| 课程语种: | 英语 |
| 中文简介: |  无监督对象发现是在没有任何人为监督的情况下，在一组未排序的图像上查找重复对象的任务，随着视觉数据量的成倍增长，这一点变得越来越重要。现有方法通常基于静态图像，并依赖于不同的先验知识来产生准确的结果。相比之下，我们提出了一种基于视频的新颖方法，该方法还允许利用运动信息，这是前景对象的强大且有效的物理指示符，因此极大地简化了任务。特别是，我们展示了如何将运动信息与外观提示并行集成到常见的条件随机场公式中，以自动从视频中发现对象类别。在实验中，我们证明了我们的系统可以成功地提取，分组和分割大多数前景对象，并且还能够发现给定视频中的静止对象。此外，我们证明了无监督学习的外观模型也可以为静止图像上的物体检测提供合理的结果。 |
| 课程简介: | Unsupervised object discovery is the task of finding recurring objects over an unsorted set of images without any human supervision, which becomes more and more important as the amount of visual data grows exponentially. Existing approaches typically build on still images and rely on different prior knowledge to yield accurate results. In contrast, we propose a novel video-based approach, allowing also for exploiting motion information, which is a strong and physically valid indicator for foreground objects, thus, tremendously easing the task. In particular, we show how to integrate motion information in parallel with appearance cues into a common conditional random field formulation to automatically discover object categories from videos. In the experiments, we show that our system can successfully extract, group, and segment most foreground objects and is also able to discover stationary objects in the given videos. Furthermore, we demonstrate that the unsupervised learned appearance models also yield reasonable results for object detection on still images. |
| 关 键 词: | 静态图像; 图像分割; 无监督学习 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2021-01-06：zyk |
| 最后编审: | 2021-06-27：zyk |
| 阅读次数: | 76 |