Multi‐step implicit Adams predictor‐corrector network for fire detection
Abstract Fire detection methods based on the Convolutional Neural Networks (CNN) have advantages of high accuracy, wide coverage and robustness, receiving significant attention from researchers. Among CNN‐based methods, ResNet has achieved better performance than other CNN frameworks in fire detecti...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-07-01
|
| Series: | IET Image Processing |
| Online Access: | https://doi.org/10.1049/ipr2.12491 |
| _version_ | 1798027613569024000 |
|---|---|
| author | Zhen Deng Shuhao Hu Shibai Yin Yibin Wang Anup Basu Irene Cheng |
| author_facet | Zhen Deng Shuhao Hu Shibai Yin Yibin Wang Anup Basu Irene Cheng |
| author_sort | Zhen Deng |
| collection | DOAJ |
| description | Abstract Fire detection methods based on the Convolutional Neural Networks (CNN) have advantages of high accuracy, wide coverage and robustness, receiving significant attention from researchers. Among CNN‐based methods, ResNet has achieved better performance than other CNN frameworks in fire detection system, since it uses stacked residual blocks to enlarge the receptive field to overcome the vanishing gradient problem with residual learning. The merits of ResNet can be attributed to the similarity between ResNet and the single‐step explicit solver for Ordinary Differential Equations (ODEs), for example, the Euler method. Motivated by the theory of numerical ODE that a multi‐step implicit solver has higher accuracy than a single‐step explicit solver, the Multi‐step Implicit Adams predictor‐corrector (MIAPC) network for fire detection is proposed. The MIAPC method is first mapped to a corresponding predictor‐corrector Adams block which achieves higher accuracy than a single‐step explicit solver. Then, Adaptive Feature Fusion (AFF) and the Spatial Attention Layer (SAL) are utilized to extract hierarchical features from stacked predictor‐corrector Adams blocks, forming the corresponding Adams module. Finally, the 4 Adams modules which are made of 4, 6, 8, 10 predictor‐corrector Adams blocks and followed by AFF and SAL form the crucial ODE‐based approximation part in the proposed network. By adding a simple feature extraction and detection in front of and after the ODE‐based approximation part, the MIAPC network is built. Experiments demonstrate that the method achieves 87% accuracy in the challenging test dataset, outperforming existing methods by at least 6%. Besides, the 5.3M model size with inference speed of 4.7 frames/second in CPU and 65.7 frames/second in GPU enables the proposed method to be used in practical applications. |
| first_indexed | 2024-04-11T18:55:22Z |
| format | Article |
| id | doaj.art-8751d3e083824abeb73bdb2528e93a1e |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-04-11T18:55:22Z |
| publishDate | 2022-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-8751d3e083824abeb73bdb2528e93a1e2022-12-22T04:08:13ZengWileyIET Image Processing1751-96591751-96672022-07-011692338235010.1049/ipr2.12491Multi‐step implicit Adams predictor‐corrector network for fire detectionZhen Deng0Shuhao Hu1Shibai Yin2Yibin Wang3Anup Basu4Irene Cheng5Department of Information Engineering Ningxia University Yinchuan Ningxia ChinaDepartment of Economic Information Engineering Southwestern University of Finance and Economics Chengdu Sichuan ChinaDepartment of Economic Information Engineering Southwestern University of Finance and Economics Chengdu Sichuan ChinaDepartment of Engineering Sichuan Normal University Chengdu Sichuan ChinaDepartment of Computing Science University of Alberta Edmonton AB CanadaDepartment of Computing Science University of Alberta Edmonton AB CanadaAbstract Fire detection methods based on the Convolutional Neural Networks (CNN) have advantages of high accuracy, wide coverage and robustness, receiving significant attention from researchers. Among CNN‐based methods, ResNet has achieved better performance than other CNN frameworks in fire detection system, since it uses stacked residual blocks to enlarge the receptive field to overcome the vanishing gradient problem with residual learning. The merits of ResNet can be attributed to the similarity between ResNet and the single‐step explicit solver for Ordinary Differential Equations (ODEs), for example, the Euler method. Motivated by the theory of numerical ODE that a multi‐step implicit solver has higher accuracy than a single‐step explicit solver, the Multi‐step Implicit Adams predictor‐corrector (MIAPC) network for fire detection is proposed. The MIAPC method is first mapped to a corresponding predictor‐corrector Adams block which achieves higher accuracy than a single‐step explicit solver. Then, Adaptive Feature Fusion (AFF) and the Spatial Attention Layer (SAL) are utilized to extract hierarchical features from stacked predictor‐corrector Adams blocks, forming the corresponding Adams module. Finally, the 4 Adams modules which are made of 4, 6, 8, 10 predictor‐corrector Adams blocks and followed by AFF and SAL form the crucial ODE‐based approximation part in the proposed network. By adding a simple feature extraction and detection in front of and after the ODE‐based approximation part, the MIAPC network is built. Experiments demonstrate that the method achieves 87% accuracy in the challenging test dataset, outperforming existing methods by at least 6%. Besides, the 5.3M model size with inference speed of 4.7 frames/second in CPU and 65.7 frames/second in GPU enables the proposed method to be used in practical applications.https://doi.org/10.1049/ipr2.12491 |
| spellingShingle | Zhen Deng Shuhao Hu Shibai Yin Yibin Wang Anup Basu Irene Cheng Multi‐step implicit Adams predictor‐corrector network for fire detection IET Image Processing |
| title | Multi‐step implicit Adams predictor‐corrector network for fire detection |
| title_full | Multi‐step implicit Adams predictor‐corrector network for fire detection |
| title_fullStr | Multi‐step implicit Adams predictor‐corrector network for fire detection |
| title_full_unstemmed | Multi‐step implicit Adams predictor‐corrector network for fire detection |
| title_short | Multi‐step implicit Adams predictor‐corrector network for fire detection |
| title_sort | multi step implicit adams predictor corrector network for fire detection |
| url | https://doi.org/10.1049/ipr2.12491 |
| work_keys_str_mv | AT zhendeng multistepimplicitadamspredictorcorrectornetworkforfiredetection AT shuhaohu multistepimplicitadamspredictorcorrectornetworkforfiredetection AT shibaiyin multistepimplicitadamspredictorcorrectornetworkforfiredetection AT yibinwang multistepimplicitadamspredictorcorrectornetworkforfiredetection AT anupbasu multistepimplicitadamspredictorcorrectornetworkforfiredetection AT irenecheng multistepimplicitadamspredictorcorrectornetworkforfiredetection |