[1] Xu Zhao, Dai Tianqi,. Efficient fire-smoke detection and evacuation simulation from buildings based on YOLOX-Swin [J]. Journal of Southeast University (English Edition), 2023, 39 (4): 372-383. [doi:10.3969/j.issn.1003-7985.2023.04.006]
Copy
Efficient fire-smoke detection and evacuation simulation from buildings based on YOLOX-Swin(
)
基于YOLOX-Swin的高效建筑火灾烟雾检测和疏散模拟方法
)Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]
- Volumn:
- 39
- Issue:
- 2023 4
- Page:
- 372-383
- Research Field:
- Civil Engineering
- Publishing date:
- 2023-12-20
Info
- Title:
- Efficient fire-smoke detection and evacuation simulation from buildings based on YOLOX-Swin
- 基于YOLOX-Swin的高效建筑火灾烟雾检测和疏散模拟方法
- Author(s):
- Xu Zhao; Dai Tianqi
- School of Civil Engineering, Southeast University, Nanjing 211189, China
- PACS:
- TU998.1;TP391.9
- DOI:
- 10.3969/j.issn.1003-7985.2023.04.006
- Abstract:
- To achieve efficient emergency response and evacuation from building fires, the possibility of applying object detection technology to building fire emergency management is investigated. An application of object detection algorithms in the early warning stage of fire is proposed by combining a transformer, convolutional neural network, and lightweight attention mechanism module(namely convolutional block attention module)to extract the local and global features of flames and smoke, thereby improving the accuracy of the object detection algorithm and achieving fast localization of fire occurrence. An improved ant colony algorithm for path searching is proposed by improving the heuristic function and pheromone evaporation coefficient. A grid map model is developed in a case, and the effectiveness of the proposed method is verified through simulation and emulation by considering positioning information. The results show that compared with the YOLOX algorithm, the YOLOX-Swin model improves the average accuracy by 1.5%. The improved ant colony algorithm reduces the search range of the traditional ant colony algorithm, improves the convergence speed of the model, and avoids the problem of getting trapped in local optimum solutions. By integrating early warning of fire and personnel evacuation, a comprehensive building fire emergency management plan is developed.
- 为了实现高效的建筑火灾应急救援疏散, 分析了将目标检测技术应用于建筑火灾应急处置的可能性.将目标检测算法应用于火灾预警阶段, 将Transformer、卷积神经网络CNN和轻量级注意力机制模块CBAM相结合, 对火焰和烟雾局部和全局特征进行提取, 提高目标检测算法的精度并实现对火灾发生位置的快速定位.提出一种用于路径搜索的改进的蚁群算法, 对启发函数和信息素挥发系数进行改进.在案例中, 建立栅格图模型, 结合定位信息, 通过仿真模拟的方式验证方法的有效性.结果表明:相比与YOLOX算法, YOLOX-Swin模型平均精度提高1.5%;改进蚁群算法降低了传统蚁群算法的搜索范围, 提高模型的收敛速度, 有效避免了模型陷入局部最优解的困境.将火灾预警和火灾人员疏散相结合, 建立完整的建筑火灾应急处置方案.
References:
[1] Kodur V, Kumar P, Rafi M M. Fire hazard in buildings:Review, assessment and strategies for improving fire safety[J]. PSU Research Review, 2019, 4(1): 1-23. DOI:10.1108/PRR-12-2018-0033.
[2] Guanquan C, Jinhua S. Quantitative assessment of building fire risk to life safety[J].Risk Analysis, 2008, 28(3): 615-625. DOI: 10.1111/j.1539-6924.2008.01048.x.
[3] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Las Vegas, NV, USA, 2016: 770-778. DOI: 10.1109/CVPR.2016.90.
[4] Khan S, Muhammad K, Mumtaz S, et al. Energy-efficient deep CNN for smoke detection in foggy IoT environment[J]. IEEE Internet of Things Journal, 2019, 6(6): 9237-9245. DOI: 10.1109/JIOT.2019.2896120.
[5] Zhang Q, Lin G, Zhang Y, et al. Wild land forest fire smoke detection based on faster R-CNN using synthetic smoke images[J]. Procedia Engineering, 2018, 211: 441-446. DOI: 10.1016/j.proeng.2017.12.034.
[6] Ge Z, Liu S, Wang F, et al. YOLOX: Exceeding YOLO series in 2021[J].(2021-07-18)[2022-12-15].http://arXiv.org/pdf/2107.08430v2.pdf.
[7] Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16×16 words: Transformers for image recognition at scale[J].(2020-10-22)[2022-12-15].http://arXiv.org/pdf/2010.11929.pdf.
[8] Porwal A, Hewage K N. Building information modeling(BIM)partnering framework for public construction projects[J].Automation in Construction, 2013, 31: 204-214. DOI: 10.1016/j.autcon.2012.12.004.
[9] Sun L, Podila K, Chen Q, et al. Computational fluid dynamics modeling of fire and human evacuation for nuclear applications[J].Journal of Nuclear Engineering and Radiation Science, 2020, 6(1): 011112. DOI: 10.1115/1.4044531.
[10] Zhao G, Beji T, Merci B. Study of FDS simulations of buoyant fire-induced smoke movement in a high-rise building stairwell[J].Fire Safety Journal, 2017, 91: 276-283. DOI: 10.1016/j.firesaf.2017.04.005.
[11] Yang X, Yang X, Li Y, et al. Obstacle avoidance in the improved social force model based on ant colony optimization during pedestrian evacuation[J].Physica A: Statistical Mechanics and Its Applications, 2021, 583: 126256. DOI:10.1016/j.physa.2021.126256.
[12] Wang J. Bidirectional ACO intelligent fire evacuation route optimization[J].Journal of Ambient Intelligence and Smart Environments, 2022, 14(4):1-19. DOI: 10.3233/AIS-220620.
[13] Xia W, Cao K, Hu Q C. Ancient village fire escape path planning based on improved ant colony algorithm[C]// IOP Conference Series: Earth and Environmental Science. Chengdu, China, 2017, 69(1): 012074. DOI: 10.1088/1755-1315/69/1/012074.
[14] Liu Z, Lin Y, Cao Y, et al. Swin transformer: Hierarchical vision transformer using shifted windows[C]//IEEE/CVF International Conference on Computer Vision(ICCV). Montreal, Canada, 2021:10012-10022. DOI: 10.1109/ICCV48922.2021.00986.
[15] Luo M, Xu L, Yang Y, et al. Laboratory flame smoke detection based on an improved YOLOX algorithm[J]. Applied Sciences, 2022, 12(24): 12876. DOI: 10.3390/app122412876.
[16] Liu S, Qi L, Qin H, et al. Path aggregation network for instance segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Salt Lake City, UT, USA, 2018: 8759-8768. DOI: 10.1109/CVPR.2018.00913.
[17] Ali M R, Ma W X. New exact solutions of Bratu Gelfand model in two dimensions using Lie symmetry analysis[J].Chinese Journal of Physics, 2020, 65: 198-206. DOI: 10.1016/j.cjph.2020.01.008.
[18] Woo S, Park J, Lee J Y, et al. CBAM: Convolutional block attention module[C]// Proceedings of the European Conference on Computer Vision(ECCV). Munich, Germany, 2018: 3-19. DOI: 10.1007/978-3-030-01234-2_1.
[19] Lin T Y, Dollár P, Girshick R, et al. Feature pyramid networks for object detection[C]// IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu, HI, USA, 2017: 936-944. DOI: 10.1109/CVPR.2017.106.
[20] Karur K, Sharma N, Dharmatti C, et al. A survey of path planning algorithms for mobile robots[J].Vehicles, 2021, 3(3): 448-468. DOI: 10.3390/vehicles3030027.
[21] Wu X, Lei Y, Tong X, et al. A Non-rigid hierarchical discrete grid structure and its application to UAVs conflict detection and path planning[J]. IEEE Transactions on Aerospace and Electronic Systems, 2022, 58(6): 5393-5411. DOI: 10.1109/TAES.2022.3170323.
Memo
- Memo:
-
Biographies: Xu Zhao(1982—), male, Ph.D., associate professor, xuzhao@seu.edu.cn.
Foundation items: The National Natural Science Foundation(No. 72071043), the Natural Science Foundation of Jiangsu Province(BK20201280), Humanities and Social Science Fund of Ministry of Education(20YJAZH114).
Citation: Xu Zhao, Dai Tianqi.Efficient fire-smoke detection and evacuation simulation from buildings based on YOLOX-Swin[J].Journal of Southeast University(English Edition), 2023, 39(4):372-383.DOI:10.3969/j.issn.1003-7985.2023.04.006.