图 书 馆
利用外观和立体声线索的多视图对象分割Multiple View Object Cosegmentation using Appearance and Stereo Cues |
|
| 课程网址: | http://videolectures.net/eccv2012_kowdle_stereo/ |
| 主讲教师: | Silvio Savarese; Adarsh Kowdle; Aude Oliva |
| 开课单位: | 康奈尔大学 |
| 开课时间: | 2012-11-12 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We present an automatic approach to segment an object in calibrated images acquired from multiple viewpoints. Our system starts with a new piecewise planar layer-based stereo algorithm that estimates a dense depth map that consists of a set of 3D planar surfaces. The algorithm is formulated using an energy minimization framework that combines stereo and appearance cues, where for each surface, an appearance model is learnt using an unsupervised approach. By treating the planar surfaces as structural elements of the scene and reasoning about their visibility in multiple views, we segment the object in each image independently. Finally, these segmentations are refined by probabilistically fusing information across multiple views. We demonstrate that our approach can segment challenging objects with complex shapes and topologies, which may have thin structures and non-Lambertian surfaces. It can also handle scenarios where the object and background color distributions overlap significantly. |
| 关 键 词: | 计算机视觉; 对象识别; 图像分割 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2021-02-03：nkq |
| 阅读次数: | 62 |