Human Behavior Recognition Method Based on Edge Intelligence
The increasingly intelligent video surveillance system is the certain result of the gradual maturity of information technology. Human behavior recognition is one of the important tasks in the area of intelligent security monitoring. This paper proposes a human behavior recognition mechanism that use...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Discrete Dynamics in Nature and Society |
| Online Access: | http://dx.doi.org/10.1155/2022/3955218 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849685661216407552 |
|---|---|
| author | Yongxia Sun Weijin Jiang |
| author_facet | Yongxia Sun Weijin Jiang |
| author_sort | Yongxia Sun |
| collection | DOAJ |
| description | The increasingly intelligent video surveillance system is the certain result of the gradual maturity of information technology. Human behavior recognition is one of the important tasks in the area of intelligent security monitoring. This paper proposes a human behavior recognition mechanism that uses edge-cloud collaborative computing. Firstly, at the edge node N0, the video is preprocessed to remove similar frames and the extracted skeleton sequence is expressed in multiple levels. Then the cloud trains the spatial-temporal graph ConvNet model and deploys it to the edge nodes N1∼Nm. The edge uses the trained model to complete behavior recognition tasks and uploads the results to the cloud for fusion to obtain the final behavior category. The experimental results prove that the advantages of edge-cloud collaboration have made the model recognition accuracy rate steadily increase by more than 2.2%. |
| format | Article |
| id | doaj-art-beb4b5801cbc47d4afbb7ee30954b1f4 |
| institution | DOAJ |
| issn | 1607-887X |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Discrete Dynamics in Nature and Society |
| spelling | doaj-art-beb4b5801cbc47d4afbb7ee30954b1f42025-08-20T03:23:02ZengWileyDiscrete Dynamics in Nature and Society1607-887X2022-01-01202210.1155/2022/3955218Human Behavior Recognition Method Based on Edge IntelligenceYongxia Sun0Weijin Jiang1School of Computer ScienceSchool of Computer ScienceThe increasingly intelligent video surveillance system is the certain result of the gradual maturity of information technology. Human behavior recognition is one of the important tasks in the area of intelligent security monitoring. This paper proposes a human behavior recognition mechanism that uses edge-cloud collaborative computing. Firstly, at the edge node N0, the video is preprocessed to remove similar frames and the extracted skeleton sequence is expressed in multiple levels. Then the cloud trains the spatial-temporal graph ConvNet model and deploys it to the edge nodes N1∼Nm. The edge uses the trained model to complete behavior recognition tasks and uploads the results to the cloud for fusion to obtain the final behavior category. The experimental results prove that the advantages of edge-cloud collaboration have made the model recognition accuracy rate steadily increase by more than 2.2%.http://dx.doi.org/10.1155/2022/3955218 |
| spellingShingle | Yongxia Sun Weijin Jiang Human Behavior Recognition Method Based on Edge Intelligence Discrete Dynamics in Nature and Society |
| title | Human Behavior Recognition Method Based on Edge Intelligence |
| title_full | Human Behavior Recognition Method Based on Edge Intelligence |
| title_fullStr | Human Behavior Recognition Method Based on Edge Intelligence |
| title_full_unstemmed | Human Behavior Recognition Method Based on Edge Intelligence |
| title_short | Human Behavior Recognition Method Based on Edge Intelligence |
| title_sort | human behavior recognition method based on edge intelligence |
| url | http://dx.doi.org/10.1155/2022/3955218 |
| work_keys_str_mv | AT yongxiasun humanbehaviorrecognitionmethodbasedonedgeintelligence AT weijinjiang humanbehaviorrecognitionmethodbasedonedgeintelligence |