Fire Video Recognition Based on Local and Global Adaptive Enhancement
Fires pose an enormous risk to human life and property. In the domain of fire warning, earlier approaches leveraging computer vision have achieved significant progress. However, these methods ignore the local and global motion characteristics of flames. To address this issue, a Local and Global Adap...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/18/1/8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589398262153216 |
|---|---|
| author | Jian Ding Yun Yi Tinghua Wang Tao Tian |
| author_facet | Jian Ding Yun Yi Tinghua Wang Tao Tian |
| author_sort | Jian Ding |
| collection | DOAJ |
| description | Fires pose an enormous risk to human life and property. In the domain of fire warning, earlier approaches leveraging computer vision have achieved significant progress. However, these methods ignore the local and global motion characteristics of flames. To address this issue, a Local and Global Adaptive Enhancement (LGAE) network is proposed, which mainly includes the backbone block, the Local Adaptive Motion Enhancement (LAME) block, and the Global Adaptive Motion Enhancement (GAME) block. Specifically, the LAME block is designed to capture information about local motion, and the GAME block is devised to enhance information about global motion. Through the utilization of these two blocks, the fire recognition ability of LGAE is improved. To facilitate the research and development in the domain of fire recognition, we constructed a Large-scale Fire Video Recognition (LFVR) dataset, which includes 11,560 video clips. Extensive experiments were carried out on the LFVR and FireNet datasets. The F1 scores of LGAE on LFVR and FireNet were 88.93% and 93.18%, respectively. The experimental outcomes indicate that LGAE performs better than other methods on both LFVR and FireNet. |
| format | Article |
| id | doaj-art-51a04b40a16740349151d5b1167c6295 |
| institution | Kabale University |
| issn | 1999-4893 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj-art-51a04b40a16740349151d5b1167c62952025-01-24T13:17:26ZengMDPI AGAlgorithms1999-48932025-01-01181810.3390/a18010008Fire Video Recognition Based on Local and Global Adaptive EnhancementJian Ding0Yun Yi1Tinghua Wang2Tao Tian3School of Mathematics and Computer Science, Gannan Normal University, Ganzhou 341000, ChinaSchool of Mathematics and Computer Science, Gannan Normal University, Ganzhou 341000, ChinaSchool of Mathematics and Computer Science, Gannan Normal University, Ganzhou 341000, ChinaSchool of Computer Science and Artificial Intelligence, Chaohu University, Hefei 238024, ChinaFires pose an enormous risk to human life and property. In the domain of fire warning, earlier approaches leveraging computer vision have achieved significant progress. However, these methods ignore the local and global motion characteristics of flames. To address this issue, a Local and Global Adaptive Enhancement (LGAE) network is proposed, which mainly includes the backbone block, the Local Adaptive Motion Enhancement (LAME) block, and the Global Adaptive Motion Enhancement (GAME) block. Specifically, the LAME block is designed to capture information about local motion, and the GAME block is devised to enhance information about global motion. Through the utilization of these two blocks, the fire recognition ability of LGAE is improved. To facilitate the research and development in the domain of fire recognition, we constructed a Large-scale Fire Video Recognition (LFVR) dataset, which includes 11,560 video clips. Extensive experiments were carried out on the LFVR and FireNet datasets. The F1 scores of LGAE on LFVR and FireNet were 88.93% and 93.18%, respectively. The experimental outcomes indicate that LGAE performs better than other methods on both LFVR and FireNet.https://www.mdpi.com/1999-4893/18/1/8fire warningfire video recognitiondatasettransformermotion enhancement |
| spellingShingle | Jian Ding Yun Yi Tinghua Wang Tao Tian Fire Video Recognition Based on Local and Global Adaptive Enhancement Algorithms fire warning fire video recognition dataset transformer motion enhancement |
| title | Fire Video Recognition Based on Local and Global Adaptive Enhancement |
| title_full | Fire Video Recognition Based on Local and Global Adaptive Enhancement |
| title_fullStr | Fire Video Recognition Based on Local and Global Adaptive Enhancement |
| title_full_unstemmed | Fire Video Recognition Based on Local and Global Adaptive Enhancement |
| title_short | Fire Video Recognition Based on Local and Global Adaptive Enhancement |
| title_sort | fire video recognition based on local and global adaptive enhancement |
| topic | fire warning fire video recognition dataset transformer motion enhancement |
| url | https://www.mdpi.com/1999-4893/18/1/8 |
| work_keys_str_mv | AT jianding firevideorecognitionbasedonlocalandglobaladaptiveenhancement AT yunyi firevideorecognitionbasedonlocalandglobaladaptiveenhancement AT tinghuawang firevideorecognitionbasedonlocalandglobaladaptiveenhancement AT taotian firevideorecognitionbasedonlocalandglobaladaptiveenhancement |