Visual Feature Learning on Video Object and Human Action Detection: A Systematic Review
Video object and human action detection are applied in many fields, such as video surveillance, face recognition, etc. Video object detection includes object classification and object location within the frame. Human action recognition is the detection of human actions. Usually, video detection is m...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Micromachines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-666X/13/1/72 |
| _version_ | 1797491930283638784 |
|---|---|
| author | Dengshan Li Rujing Wang Peng Chen Chengjun Xie Qiong Zhou Xiufang Jia |
| author_facet | Dengshan Li Rujing Wang Peng Chen Chengjun Xie Qiong Zhou Xiufang Jia |
| author_sort | Dengshan Li |
| collection | DOAJ |
| description | Video object and human action detection are applied in many fields, such as video surveillance, face recognition, etc. Video object detection includes object classification and object location within the frame. Human action recognition is the detection of human actions. Usually, video detection is more challenging than image detection, since video frames are often more blurry than images. Moreover, video detection often has other difficulties, such as video defocus, motion blur, part occlusion, etc. Nowadays, the video detection technology is able to implement real-time detection, or high-accurate detection of blurry video frames. In this paper, various video object and human action detection approaches are reviewed and discussed, many of them have performed state-of-the-art results. We mainly review and discuss the classic video detection methods with supervised learning. In addition, the frequently-used video object detection and human action recognition datasets are reviewed. Finally, a summarization of the video detection is represented, e.g., the video object and human action detection methods could be classified into frame-by-frame (frame-based) detection, extracting-key-frame detection and using-temporal-information detection; the methods of utilizing temporal information of adjacent video frames are mainly the optical flow method, Long Short-Term Memory and convolution among adjacent frames. |
| first_indexed | 2024-03-10T00:55:18Z |
| format | Article |
| id | doaj.art-f1d234b82c8f4067a350d1dd42d4e6b1 |
| institution | Directory Open Access Journal |
| issn | 2072-666X |
| language | English |
| last_indexed | 2024-03-10T00:55:18Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Micromachines |
| spelling | doaj.art-f1d234b82c8f4067a350d1dd42d4e6b12023-11-23T14:44:27ZengMDPI AGMicromachines2072-666X2021-12-011317210.3390/mi13010072Visual Feature Learning on Video Object and Human Action Detection: A Systematic ReviewDengshan Li0Rujing Wang1Peng Chen2Chengjun Xie3Qiong Zhou4Xiufang Jia5Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaInstitute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaSchool of Computer Science and Technology, Anhui University, Hefei 230601, ChinaInstitute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaInstitute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaInstitute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaVideo object and human action detection are applied in many fields, such as video surveillance, face recognition, etc. Video object detection includes object classification and object location within the frame. Human action recognition is the detection of human actions. Usually, video detection is more challenging than image detection, since video frames are often more blurry than images. Moreover, video detection often has other difficulties, such as video defocus, motion blur, part occlusion, etc. Nowadays, the video detection technology is able to implement real-time detection, or high-accurate detection of blurry video frames. In this paper, various video object and human action detection approaches are reviewed and discussed, many of them have performed state-of-the-art results. We mainly review and discuss the classic video detection methods with supervised learning. In addition, the frequently-used video object detection and human action recognition datasets are reviewed. Finally, a summarization of the video detection is represented, e.g., the video object and human action detection methods could be classified into frame-by-frame (frame-based) detection, extracting-key-frame detection and using-temporal-information detection; the methods of utilizing temporal information of adjacent video frames are mainly the optical flow method, Long Short-Term Memory and convolution among adjacent frames.https://www.mdpi.com/2072-666X/13/1/72video object detectionhuman action recognitiondeep learningtemporal informationoptical flowLSTM |
| spellingShingle | Dengshan Li Rujing Wang Peng Chen Chengjun Xie Qiong Zhou Xiufang Jia Visual Feature Learning on Video Object and Human Action Detection: A Systematic Review Micromachines video object detection human action recognition deep learning temporal information optical flow LSTM |
| title | Visual Feature Learning on Video Object and Human Action Detection: A Systematic Review |
| title_full | Visual Feature Learning on Video Object and Human Action Detection: A Systematic Review |
| title_fullStr | Visual Feature Learning on Video Object and Human Action Detection: A Systematic Review |
| title_full_unstemmed | Visual Feature Learning on Video Object and Human Action Detection: A Systematic Review |
| title_short | Visual Feature Learning on Video Object and Human Action Detection: A Systematic Review |
| title_sort | visual feature learning on video object and human action detection a systematic review |
| topic | video object detection human action recognition deep learning temporal information optical flow LSTM |
| url | https://www.mdpi.com/2072-666X/13/1/72 |
| work_keys_str_mv | AT dengshanli visualfeaturelearningonvideoobjectandhumanactiondetectionasystematicreview AT rujingwang visualfeaturelearningonvideoobjectandhumanactiondetectionasystematicreview AT pengchen visualfeaturelearningonvideoobjectandhumanactiondetectionasystematicreview AT chengjunxie visualfeaturelearningonvideoobjectandhumanactiondetectionasystematicreview AT qiongzhou visualfeaturelearningonvideoobjectandhumanactiondetectionasystematicreview AT xiufangjia visualfeaturelearningonvideoobjectandhumanactiondetectionasystematicreview |