2016 IEEE International Conference on Recent Trends in Electronics, Information &Amp; Communication Technology (RTEICT) 2016
DOI: 10.1109/rteict.2016.7808136
|View full text |Cite
|
Sign up to set email alerts
|

Video based action detection and recognition human using optical flow and SVM classifier

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
9
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
7
2
1

Relationship

0
10

Authors

Journals

citations
Cited by 19 publications
(9 citation statements)
references
References 9 publications
0
9
0
Order By: Relevance
“…B Jagadeesh et al [12] (2016) described that human actions were detected and recognized based on video on the KTH dataset and on videos of real-time. Initially, the extraction of 100 frames was completed from every video sequence and the optical flow was evaluated among the frames.…”
Section: Dogo Rangsang Researchmentioning
confidence: 99%
“…B Jagadeesh et al [12] (2016) described that human actions were detected and recognized based on video on the KTH dataset and on videos of real-time. Initially, the extraction of 100 frames was completed from every video sequence and the optical flow was evaluated among the frames.…”
Section: Dogo Rangsang Researchmentioning
confidence: 99%
“…Many SVM-based action recognition algorithms have been developed, such as Liu and Zhi-Pan [20], who proposed an action recognition algorithm based on Kinect and SVM methods. Jagadeesh and Patil et al [21] proposed that video-based human action recognition is addressed and performed on a public baseline dataset to conduct verification. Karpathy and Toderici et al [22] combined local spatial-temporal feature information and proposed multiresolution action recognition methods and improved network speeding of the training.…”
Section: Related Workmentioning
confidence: 99%
“…The SVM is also known as a binary classifier, in which data is classified according to the hyperplane [27]. It supports classification and regression functions, and can handle several continuous and categorical variables [39]. The SVM demonstrated to be an extremely robust and effective categorization and regression algorithm [40].…”
Section: Scalp Problem Classificationmentioning
confidence: 99%