Key Points' location in infrared images of the human body based on Mscf-ResNet
The human body generates infrared radiation through the thermal movement of molecules. Based on this phenomenon, infrared images of the human body are often used for monitoring and tracking. Among them, key point location on infrared images of the human body is an important technology in medical inf...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Published: |
MDPI AG
2021
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/93974/ |
| _version_ | 1848861887545999360 |
|---|---|
| author | Ge, Shengguo Mohd Rum, Siti Nurulain |
| author_facet | Ge, Shengguo Mohd Rum, Siti Nurulain |
| author_sort | Ge, Shengguo |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | The human body generates infrared radiation through the thermal movement of molecules. Based on this phenomenon, infrared images of the human body are often used for monitoring and tracking. Among them, key point location on infrared images of the human body is an important technology in medical infrared image processing. However, the fuzzy edges, poor detail resolution, and uneven brightness distribution of the infrared image of the human body cause great difficulties in positioning. Therefore, how to improve the positioning accuracy of key points in human infrared images has become the main research direction. In this study, a multi-scale convolution fusion deep residual network (Mscf-ResNet) model is proposed for human body infrared image positioning. This model is based on the traditional ResNet, changing the single-scale convolution to multi-scale and fusing the information of different receptive fields, so that the extracted features are more abundant and the degradation problem, caused by the excessively deep network, is avoided. The experiments show that our proposed method has higher key point positioning accuracy than other methods. At the same time, because the network structure of this paper is too deep, there are too many parameters and a large volume of calculations. Therefore, a more lightweight network model is the direction of future research. |
| first_indexed | 2025-11-15T13:08:16Z |
| format | Article |
| id | upm-93974 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-15T13:08:16Z |
| publishDate | 2021 |
| publisher | MDPI AG |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-939742023-05-17T08:40:38Z http://psasir.upm.edu.my/id/eprint/93974/ Key Points' location in infrared images of the human body based on Mscf-ResNet Ge, Shengguo Mohd Rum, Siti Nurulain The human body generates infrared radiation through the thermal movement of molecules. Based on this phenomenon, infrared images of the human body are often used for monitoring and tracking. Among them, key point location on infrared images of the human body is an important technology in medical infrared image processing. However, the fuzzy edges, poor detail resolution, and uneven brightness distribution of the infrared image of the human body cause great difficulties in positioning. Therefore, how to improve the positioning accuracy of key points in human infrared images has become the main research direction. In this study, a multi-scale convolution fusion deep residual network (Mscf-ResNet) model is proposed for human body infrared image positioning. This model is based on the traditional ResNet, changing the single-scale convolution to multi-scale and fusing the information of different receptive fields, so that the extracted features are more abundant and the degradation problem, caused by the excessively deep network, is avoided. The experiments show that our proposed method has higher key point positioning accuracy than other methods. At the same time, because the network structure of this paper is too deep, there are too many parameters and a large volume of calculations. Therefore, a more lightweight network model is the direction of future research. MDPI AG 2021-12-27 Article PeerReviewed Ge, Shengguo and Mohd Rum, Siti Nurulain (2021) Key Points' location in infrared images of the human body based on Mscf-ResNet. Future Internet, 14 (1). pp. 1-14. ISSN 1999-5903 https://www.mdpi.com/1999-5903/14/1/15 10.3390/fi14010015 |
| spellingShingle | Ge, Shengguo Mohd Rum, Siti Nurulain Key Points' location in infrared images of the human body based on Mscf-ResNet |
| title | Key Points' location in infrared images of the human body based on Mscf-ResNet |
| title_full | Key Points' location in infrared images of the human body based on Mscf-ResNet |
| title_fullStr | Key Points' location in infrared images of the human body based on Mscf-ResNet |
| title_full_unstemmed | Key Points' location in infrared images of the human body based on Mscf-ResNet |
| title_short | Key Points' location in infrared images of the human body based on Mscf-ResNet |
| title_sort | key points' location in infrared images of the human body based on mscf-resnet |
| url | http://psasir.upm.edu.my/id/eprint/93974/ http://psasir.upm.edu.my/id/eprint/93974/ http://psasir.upm.edu.my/id/eprint/93974/ |