READING NOTE: Learning to Segment Moving Objects in Videos
来源:互联网 发布:浙江大学宁波软件学院 编辑:程序博客网 时间:2024/05/16 11:13
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.
0 0
- READING NOTE: Learning to Segment Moving Objects in Videos
- 视频分割--Learning to Segment Instances in Videos with Spatial Propagation Network
- #Paper Reading# Learning to Segment Object Candidates
- READING NOTE: Two-Stream Convolutional Networks for Action Recognition in Videos
- READING NOTE: Learning to Detect Human-Object Interactions
- Learning to Count Objects in Images
- READING NOTE: FastMask: Segment Multi-scale Object Candidates in One Shot
- READING NOTE: Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neura
- In-depth introduction to machine learning in 15 hours of expert videos
- Learning to Segment[译]
- 物体计数--Learning To Count Objects in Images
- [CVPR2015]Learning to propose objects
- 视频中的运动特征--Learning Motion Patterns in Videos
- READING NOTE: Learning Deconvolution Network for Semantic Segmentation
- READING NOTE: What makes ImageNet good for transfer learning?
- Reading Note: DSOD: Learning Deeply Supervised Object Detectors from Scratch
- Reading Note
- Learning to Segment (Facebook AI Research)
- java中常用的字符串的截取方法
- Python 中 import 的机制与实现
- hdoj 1087Super Jumping! Jumping! Jumping!【dp】
- 在伪分布式环境下通过宿主机上的eclipse运行WordCount小程序出现的问题小结
- android 从Activity 获取 rootView 根节点
- READING NOTE: Learning to Segment Moving Objects in Videos
- iOS开发-常用第三方开源框架介绍(你了解的ios只是冰山一角)
- leetcode-Reverse Linked List
- 初学 Java Web 开发,请远离各种框架,从 Servlet 开发
- 字符串之数字子串求和
- 解析Android ListView工作原理及其缓存机制
- android 加密
- 字符串---求一个字符串中连续出现次数最多的子串
- Codevs_P1036 商务旅行(LCA)