「VIDEO」 关键帧提取资源汇总
诸多视频分析技术都是以关键帧提取作为基础,在此就做一个汇总;
相关资源:关键帧提取概述
key frame extraction
· bag of keyframes
· key frame detection
shot boundary detection
· key volume mining
· Key Segments
1 综述
-
A Formal Study of Shot Boundary Detection
2007 paper
$\bullet \bullet$ study
基于图; -
Analysis of Popular Video Shot Boundary Detection Techniques in Uncompressed Domain
2012 paper -
A REVIEW ON DIFFERENT METHODS OF VIDEO SHOT BOUNDARY DETECTION
2012-08-01 paper -
Analysis and Review of Formal Approaches to Automatic Video Shot Boundary Detection
2012 paper
$\bullet \bullet$ analysis -
A SURVEY REPORT ON VIDEO SHORT BOUNDARY DETECTION SCHEMES
2014-05 paper -
A Review on Different Keyframe Abstraction Techniques from the Video
2014-11 paper -
Video Shot Boundary Detection: A Comprehensive Review
2017 paper -
Methods and Challenges in Shot Boundary Detection: A Review
2018-03-23 paper
$\bullet \bullet$ challenge
2 理论
3 关键帧提取
3.1 传统方法
- RPCA-KFE: Key Frame Extraction for Consumer Video based Robust Principal Component Analysis
2014-05-07 paper
PCA;
3.2 DL
- Video Key Frame Extraction using Entropy value as Global and Local Feature
2016-05-28 Paper
自注意力机制助力视频字幕提取;摘要不是很好,核心不清晰;
-
Recognizing Dynamic Scenes with Deep Dual Descriptor based on Key Frames and Key Segments
2017-02-15 paper -
Superframes, A Temporal Video Segmentation
2018-04-18 paper
基于光流进行运动估计; - 基于深度学习的视频关键帧提取与视频检索
2019 梁建胜,温贺平 知网
$\bullet \bullet$ 检索与关键帧
实际上是很早的算法了;
4 镜头边界检测
4.1 传统方法
-
Comparison of automatic shot boundary detection algorithms
1998 paper
关注淡入淡出问题; -
Video shot boundary detection using motion activity descriptor
2010-04-26 paper -
A Novel Approach for Shot Boundary Detection in Videos
2012 paper -
Video Shot Boundary Detection using Visual Bag-of-Words
2013 paper -
Histogram Based Split and Merge Framework for Shot Boundary Detection
2013 paper
基于颜色直方图; -
Video Shot Boundary Detection Using Normalized Periodogram Distance Metric
2016 paper -
A Novel Method of Shot Boundary Detection using Center Symmetric Local Binary Pattern
2016 paper -
Shot boundary detection using convolutional neural networks
2016 paper
消除假的镜头边界; -
Video shot boundary detection and key-frame extraction using mathematical models
2017 paper
好长;
4.2 DL
-
Large-scale, Fast and Accurate Shot Boundary Detection through Convolutional Neural Networks
2017-05-09 paper | home | matlab-official
CNN 检测镜头;开放了一个大型数据集;速度快; -
Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks
2017-05-23 paper | keras
超快 -
Fast Video Shot Transition Localization with Deep Structured Models
2018-08-13 paper -
Two Stage Shot Boundary Detection via Feature Fusion and Spatial-Temporal Convolutional Neural Networks
2019-01-26 paper
先用分镜头(融合了 CNN 和 颜色特征),再合并过渡段; -
TransNet: A deep network for fast detection of common shot transitions
2019-06-08 paper | tensorflow
$\bullet \bullet$ TransNet
5 应用
5.1 手势识别
- Fast and Robust Dynamic Hand Gesture Recognition via Key Frames Extraction and Feature Fusion
2019-01-15 paper | matlab-official
$\bullet \bullet$ Hand Gesture Fusion
基于图像熵和视频聚类提取到视频中的关键帧,一次提高手势识别的准确度;
5.2 动作识别
- Deep Keyframe Detection in Human Action Videos
2018-04-26 paper
人体行为关键帧的特点:这些关键帧的类别区分度最强;
做法:- 生成关键帧的label
- 利用 Imagenet 预训练的 VGG-16 提取每一帧的特征
- 根据每个视频的类别,将同一类别的帧组成 Vc
- 对于每一类,利用 LDA 学习一个矩阵,最大化与其他类别的距离
每一帧的得分为: - 利用生成的 label,训练一个关键帧得分生成网络
收获: - 关键帧的分布与原序列的分布一致(多样性)
- 关键帧的信息冗余尽可能少(离散型)
- 关键帧的个数应该尽可能的少
- 关键帧能够很容易识别出该 id(判别性)
- A Key Volume Mining Deep Framework for Action Recognition
CVPR 2016 2016 paper
$\bullet \bullet$ key volume
motivation:视频中包含大量静止画面,如果把这些帧送入网络,会对网络的训练起到一个反向的作用;
做法:将多个帧输入到网络中,只优化对于在目标类中取得最大概率的帧的loss;
思考:用分类来提取关键帧,类别分数越高,越有可能成为关键帧;
问题:测试时输入的帧也有可能不含有动作信息,为什么还要将各个帧的得分平均?是不是也可以考虑像训练集那样只考虑关键帧的预测结果;
5.3 视频摘要
-
Video Summarization with LongShort-term Memory
ECCV 2016 2016-05-26 paper | blog | theano
用 LSTM 提取关键帧序列; -
Unsupervised Video Summarization with Adversarial LSTM Networks
CVPR 2017 2017 paper
$\bullet \bullet$ ALSTM
先验:关键帧的分布应该与原序列的分布一直(去除冗余信息);
正规化:关键帧的个数应该尽可能的少;关键帧的信息尽可能离散;
做法:- slstm:输出每一帧的得分,与原来帧加权后得到新的特征;
- elstm:对于lstm得到的特征编码,得到一个特征;
- dlstm:对elstm得到的特征解码,恢复出原来的特征;
- clstm:判断dlstm得到的特征是否还是原来的特征;
处理:根据每一帧的得分选出关键帧
- 将视频分成不重叠的几个clip;
- 每个clip的得分是这个clip中所有帧的得分的平均,对clip排序;
- 高得分的clip中的帧按照分数排序,选出最高的几帧;
5.4 REID
附录
A 参考资料
- Shot transition detection
- 视频镜头分割方法综述
里边有 C++ 代码; - 视频镜头分割
有 python 代码; - python数字图像处理(二)关键镜头检测
- https://www.cnblogs.com/lynsyklate/p/7840881.html
Comments