Articles
"Comprehensive Grassland Fire Detection Using YOLOv5m-D Integrating Static and Dynamic Feature Analysis"
Downloads
Keywords
Grassland fire detection
YOLOv5m-D
static and dynamic
features, deep learning
Article Usage Statistics
Live Metrics
Abstract Views
175
File Views
94
PDF
0
HTML
0
Other
94
Total
269
Article Usage Chart
Abstract
File Views
PDF
HTML
Other
Total
Abstract
Grassland fires pose significant ecological, economic, and social threats globally, necessitating rapid, accurate detection methods to mitigate their impact. This study proposes a comprehensive grassland fire detection framework leveraging the YOLOv5m-D deep learning architecture, enhanced by the integration of both static and dynamic environmental features. Static features include vegetation type, topography, and historical fire distribution, while dynamic features capture temporal changes such as smoke evolution, flame intensity, and meteorological variability. The proposed system demonstrates robust detection performance under varying environmental conditions, achieving high precision and recall metrics. Comparative analysis with conventional detection algorithms indicates that incorporating both static and dynamic data significantly enhances early warning capabilities. The framework's scalability and real-time applicability make it a promising tool for fire management agencies, with implications for risk mitigation, ecological preservation, and resource allocation.
Downloads
Download data is not yet available.
References
1. Cardíl, V. M. Tapia, S. Monedero, T. Quiñones, K. Little, C. R. Stoof, J. Ramirez, and S. de-Miguel, “Characterizing the rate of spread of large wildfires in emerging fire environments of northwestern Europe using visible infrared imaging radiometer suite active fire data,” Natural Hazards Earth Syst. Sci., vol. 23, no. 1, pp. 361–373, Feb. 2023, doi: 10.5194/nhess-23-361-2023.
2. L. de Assis Barros, B. A. F. D. Mendonça, C. Sothe, E. I. F. Filho, and C. Elkin, “Fire in the Atlantic rainforest: An analysis of 20 years of fire foci distribution and their social-ecological drivers,” Geocarto Int., vol. 37, no. 16, pp. 4737–4761, Aug. 2022, doi: 10.1080/10106049.2021.1899301.
3. Y. Cheng, K. Chen, H. Bai, C. Mou, Y. Zhang, K. Yang, Y. Gao, and Y. Liu, “An efficient fire detection algorithm based on multi-scale convolutional neural network,” Fire Mater., vol. 46, no. 7, pp. 981–992, Nov. 2022, doi: 10.1002/fam.3045.
4. J. Chen, “The Fengyun-3D (FY-3D) global active fire product: Principle, methodology and validation,” Earth Syst. Sci. Data, vol. 14, no. 8, pp. 3489–3508, Aug. 2022, doi: 10.5194/essd-14-3489-2022.
5. H. Herakovich, N. A. Barber, and H. P. Jones, “Assessing the impacts of prescribed fire and bison disturbance on birds using bioacoustic recorders,” Amer. Midland Naturalist, vol. 186, no. 2, pp. 245–262, Oct. 2021, doi: 10.1674/0003-0031-186.2.245.
6. Y. Hu and G. Rein, “Development of gas signatures of smouldering peat wildfire from emission factors,” Int. J. Wildland Fire, vol. 31, no. 11, pp. 1014–1032, Nov. 2022, doi: 10.1071/WF21093.
7. Y. Hu, J. Zhan, G. Zhou, A. Chen, W. Cai, K. Guo, Y. Hu, and L. Li, “Fast forest fire smoke detection using MVMNet,” Knowl.-Based Syst., vol. 241, Apr. 2022, Art. no. 108219, doi: 10.1016/j.knosys.2022.108219.
8. A. Juneja, S. Juneja, A. Soneja, and S. Jain, “Real time object detection using CNN based single shot detector model,” J. Inf. Technol. Manage., vol. 13, no. 1, pp. 62–80, 2021, doi: 10.22059/jitm.2021.80025.
9. E. A. Kadir, S. L. Rosa, A. Syukur, M. Othman, and H. Daud, “Forest fire spreading and carbon concentration identification in tropical region Indonesia,” Alexandria Eng. J., vol. 61, no. 2, pp. 1551–1561, Feb. 2022, doi: 10.1016/j.aej.2021.06.064.
10. J. Li, G. Zhou, A. Chen, C. Lu, and L. Li, “BCMNet: Cross-layer extraction structure and multiscale downsampling network with bidirectional transpose FPN for fast detection of wildfire smoke,” IEEE Syst. J., vol. 17, no. 1, pp. 1235–1246, Mar. 2023, doi: 10.1109/JSYST.2022.3193951.
11. J. Li, G. Zhou, A. Chen, Y. Wang, J. Jiang, Y. Hu, and C. Lu, “Adaptive linear feature-reuse network for rapid forest fire smoke detection model,” Ecolog. Informat., vol. 68, May 2022, Art. no. 101584, doi: 10.1016/j.ecoinf.2022.101584.
12. X. Li, M. Li, Y. Wu, D. Zhou, T. Liu, F. Hao, J. Yue, and Q. Ma, “Accurate screw detection method based on faster R-CNN and rotation edge similarity for automatic screw disassembly,” Int. J. Comput. Integr. Manuf., vol. 34, no. 11, pp. 1177–1195, Nov. 2021, doi: 10.1080/0951192X.2021.1963476.
13. S. Oslund, C. Washington, A. So, T. Chen, and H. Ji, “Multiview robust adversarial stickers for arbitrary objects in the physical world,” J. Comput. Cognit. Eng., vol. 1, no. 4, pp. 152–158, Sep. 2022, doi: 10.47852/bonviewJCCE2202322.
14. H. A. Moore, D. R. Michael, J. A. Dunlop, L. E. Valentine, M. A. Cowan, and D. G. Nimmo, “Habitat amount is less important than habitat configuration for a threatened marsupial predator in naturally fragmented landscapes,” Landscape Ecol., vol. 37, no. 4, pp. 935–949, Feb. 2022, doi: 10.1007/s10980-022-01411-1.
15. M. Humber, M. Zubkova, and L. Giglio, “A remote sensing-based approach to estimating the fire spread rate parameter for individual burn patch extraction,” Int. J. Remote Sens., vol. 43, no. 2, pp. 649–673, Jan. 2022, doi: 10.1080/01431161.2022.2027544.
16. E. Marshall, A. Dorph, B. Holyland, A. Filkov, and T. D. Penman, “Suppression resources and their influence on containment of forest fires in Victoria,” Int. J. Wildland Fire, vol. 31, no. 12, pp. 1144–1154, Oct. 2022, doi: 10.1071/WF22029.
17. E. C. Morris and J. Sanders, “Repeat burning affects species composition in degraded cumberland plain woodland,” Austral. J. Botany, vol. 69, no. 8, pp. 596–609, Oct. 2021, doi: 10.1071/BT20171.
18. H. Shi, M. Rigge, K. Postma, and B. Bunde, “Trends analysis of rangeland condition monitoring assessment and projection (RCMAP) fractional component time series (1985–2020),” GISci. Remote Sens., vol. 59, no. 1, pp. 1243–1265, Dec. 2022, doi: 10.1080/15481603.2022.2104786.
19. Z. Shuo, Z. Jingyu, Z. Zhengxiang, and Z. Jianjun, “Identifying the density of grassland fire points with kernel density estimation based on spatial distribution characteristics,” Open Geosci., vol. 13, no. 1, pp. 796–806, Jul. 2021, doi: 10.1515/geo-2020-0265.
20. L. Wei, W. Cui, Z. Hu, H. Sun, and S. Hou, “A single-shot multi-level feature reused neural network for object detection,” Vis. Comput., vol. 37, no. 1, pp. 133–142, Jan. 2021, doi: 10.1007/s00371-019-01787-3.
21. H. Zhang, L. Sun, C. Zheng, S. Ge, J. Chen, and J. Li, “A weighted contextual active fire detection algorithm based on Himawari-8 data,” Int. J. Remote Sens., vol. 44, no. 7, pp. 2400–2427, Apr. 2023, doi: 10.1080/01431161.2023.2198652.
22. L. Zhang, C. Lu, H. Xu, A. Chen, L. Li, and G. Zhou, “MMFNet: Forest fire smoke detection using multiscale convergence coordinated pyramid network with mixed attention and fast-robust NMS,” IEEE Internet Things J., vol. 10, no. 20, pp. 18168–18180, May 2023, doi: 10.1109/JIOT.2023.3277511.