基于深度学习的视频中人体动作识别进展综述
The Progress of Human Action Recognition in Videos Based on Deep Learning: A Review
查看参考文献68篇
|
文摘
|
视频中的人体动作识别是计算机视觉领域内一个充满挑战的课题.不论是在视频信息检索、日常生活安全、公共视频监控,还是人机交互、科学认知等领域都有广泛的应用.本文首先简单介绍了动作识别的研究背景、意义及其难点,接着从模型输入信号的类型和数量、是否结合了传统特征提取方法、模型预训练三个维度详细综述了基于深度学习的动作识别方法,及比较分析了它们在UCF101和HMDB51这两个数据集上的识别效果.最后分别从视频预处理、视频中人体运动信息表征、模型学习训练这三个角度对未来动作识别可能的发展方向进行了论述. |
|
其他语种文摘
|
Human action recognition in videos is a challenging topic in the field of computer vision. It is widely not only used in video information retrieval,daily life security,public video surveillance,but also human-computer interaction, scientific cognition and other fields. First, the research background, research significance and difficulties of action recognition are briefly introduced,and then the deep learning model based action recognition methods are comprehensively reviewed from three different aspects: the types and numbers of input signals, the combination with traditional feature extraction methods, and the pre-trained datasets. Furthermore, the performances of some typical methods on UCF101 and HMDB51 datasets are overviewed and analyzed. Last the possible future research directions are discussed from three perspectives: the video data preprocessing, the video human motion feature representation, and the model training. |
|
来源
|
电子学报
,2019,47(5):1162-1173 【核心库】
|
|
DOI
|
10.3969/j.issn.0372-2112.2019.05.025
|
|
关键词
|
动作识别
;
综述
;
卷积神经网络
;
深度学习
|
|
地址
|
1.
江西理工大学信息工程学院, 江西, 赣州, 341000
2.
浙江大学计算机科学技术学院, 浙江, 杭州, 310027
|
|
语种
|
中文 |
|
文献类型
|
综述型 |
|
ISSN
|
0372-2112 |
|
学科
|
自动化技术、计算机技术 |
|
基金
|
国家自然科学基金
;
江西省自然科学基金
;
江西省青年科学家培养对象计划资助
|
|
文献收藏号
|
CSCD:6668539
|
参考文献 共
68
共4页
|
|
1.
胡琼. 基于视觉的人体动作识别综述.
计算机学报,2013,36(12):2512-2524
|
CSCD被引
50
次
|
|
|
|
|
2.
Poppe R. A survey on vision-based human action recognition.
Image and Vision Computing,2010,28(6):976-990
|
CSCD被引
71
次
|
|
|
|
|
3.
Weinland D. A survey of vision-based methods for action representation, segmentation and recognition.
Computer Vision and Image Understanding,2011,115(2):224-241
|
CSCD被引
35
次
|
|
|
|
|
4.
杜友田. 基于视觉的人的运动识别综述.
电子学报,2007,35(1):84-90
|
CSCD被引
36
次
|
|
|
|
|
5.
Chaquet J M. A survey of video datasets for human action and activity recognition.
Computer Vision and Image Understanding,2013,117(6):633-659
|
CSCD被引
15
次
|
|
|
|
|
6.
Dawn D D. A comprehensive survey of human action recognition with spatio-temporal interest point ( STIP) detector.
Visual Computer,2016,32(3):289-306
|
CSCD被引
11
次
|
|
|
|
|
7.
朱红蕾. 人体行为识别数据集研究进展.
自动化学报,2018,44(6):978-1004
|
CSCD被引
15
次
|
|
|
|
|
8.
Zhu F. From handcrafted to learned representations for human action recognition.
Image and Vision Computing,2016,55(P2):42-52
|
CSCD被引
9
次
|
|
|
|
|
9.
Herath S. Going deeper into action recognition: a survey.
Image and Vision Computing,2017,60(4):4-21
|
CSCD被引
30
次
|
|
|
|
|
10.
Sargano A. A comprehensive review on handcrafted and learning-based action representation approaches for human activity recognition.
Applied Sciences,2017,7(1):110-147
|
CSCD被引
1
次
|
|
|
|
|
11.
Wu D. Recent advances in video-based human action recognition using deep learning: a review.
International Joint Conference on Neural Networks,2017:2865-2872
|
CSCD被引
1
次
|
|
|
|
|
12.
Yao G L. A review of convolutional-neural-network-based action recognition.
Pattern Recognition Letters,2019,118(2):14-22
|
CSCD被引
6
次
|
|
|
|
|
13.
Du T. Learning spatiotemporal features with 3D convolutional networks.
International Conference on Computer Vision,2015:4489-4497
|
CSCD被引
2
次
|
|
|
|
|
14.
Karpathy A. Largescale video classification with convolutional neural networks.
Computer Vision and Pattern Recognition,2014:1725-1732
|
CSCD被引
5
次
|
|
|
|
|
15.
Feichtenhofer C. Convolutional two-stream network fusion for video action recognition.
Computer Vision and Pattern Recognition,2016:1933-1941
|
CSCD被引
4
次
|
|
|
|
|
16.
Simonyan K. Two-stream convolutional networks for action recognition in videos.
Neural Information Processing Systems. NIPS Proceedings,2014:568-576
|
CSCD被引
1
次
|
|
|
|
|
17.
Wang H. Action recognition with improved trajectories.
International Conference on Computer Vision,2013:3551-3558
|
CSCD被引
4
次
|
|
|
|
|
18.
Wang L. Temporal segment networks: towards good practices for deep action recognition.
ACM Transactions on Information Systems,2016,22(1):20-36
|
CSCD被引
6
次
|
|
|
|
|
19.
Sun S. Optical flow guided feature: a fast and robust motion representation for video action recognition.
Computing Vision and pattern Recognition,2018:1390-1399
|
CSCD被引
1
次
|
|
|
|
|
20.
Zhang B. Real-time action recognition with enhanced motion vector CNNs.
Computer Vision and Pattern Recognition,2016:2718-2726
|
CSCD被引
1
次
|
|
|
|
|
了解气象卫星更多信息，请访问