READING NOTE: Learning to Segment Moving Objects in Videos

最新推荐文章于 2022-12-27 16:50:10 发布

Joshua_Li_

最新推荐文章于 2022-12-27 16:50:10 发布

阅读量1.1k

点赞数

CC 4.0 BY-SA版权

分类专栏：计算机视觉

本文链接：https://blog.youkuaiyun.com/joshua_1988/article/details/49644725

计算机视觉专栏收录该内容

72 篇文章

订阅专栏

本文探讨了通过光流提取运动边界，生成基于光流边界的移动对象提案（MOPs），并使用基于CNN的回归器对每帧段进行排名。提出的方法包括将每帧的MOPs扩展为时空管，并利用轨迹跟踪处理暂时静止的对象。优点在于减少内纹理对象噪声、检测刚体对象以及有效处理频繁遮挡/去遮挡情况。然而，该方法速度较慢，且使用多个独立方法检测对象，导致计算效率降低。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

READING NOTE: Learning to Segment Moving Objects in Videos

TITLE: Learning to Segment Moving Objects in Videos

AUTHOR: Fragkiadaki, Katerina and Arbelaez, Pablo and Felsen, Panna and Malik, Jitendra

FROM: CVPR2015

METHOD

Extract motion boundaries by optical flow
Generate segment proposals according to motion boundaries, called MOPs (Moving Object Proposal)
Rank the MOPs using a CNN based regressor
Combine per frame MOPs to space-time tubes based on pixelwise trajectories

CONTRIBUTIONS

Moving object proposals from multiple segmentations on optical flow boundaries
A moving objectness detector for ranking per frame segments and tube proposals
A method of extending per frame segments into spatial-temporal tubes

ADVANTAGES

Using optical flow could reduce the noises caused by inner texture of one object. Optical flow is more suitable for detecting rigid objects.
Using trajectory tracking could deal with objects that are temporary static.
Segments are effective to tackle frequent occlusions/dis-occlustions

DISADVANTAGES

Too slow. Every stage would take seconds to process, which is not suitable for practical applications.
Use several independent method to detect objects. Less computations are shared.
The power of CNN has not been fully applied.

OTHER

RCNN has excellent performance on object detection in static images
For slide window methods, too many patches need to be evaluated.
MRF methods neglect nearby pixels’ relation and could not separate adjacent instances.
Methods of object detection in video could be categorized into two types i) top-down tracking and ii) bottom-up segmentation.