基于多尺度特征融合的轻量级火灾检测算法

doi:10.3778/j.issn.1002-8331.2404-0262

摘要/Abstract

摘要： 针对传统火灾检测算法存在的检测精度不足及速度瓶颈，特别是对于小规模初发火情与大规模迅速蔓延火灾的识别难题，研究提出一种基于多尺度特征融合的轻量级火灾检测算法，设计了EDBAN模块以替代YOLOv8中的C2f模块，提升模型的泛化能力和适应性，尤其是在处理多尺度火灾场景时的精准度。改进原有的BiFPN结构适配YOLOv8模型结构，并设计Weighted Blend模块对各层特征进行加权融合，增强特征的表征能力，降低漏检风险。进一步提出LOTT检测模块，以替代传统的YOLOv8检测，通过一系列组卷积和尺度调整操作，实现了在轻量化的同时保持了检测性能的准确性和稳定性。通过在场景丰富的火灾数据集上进行实验，结果表明，改进的YOLOv8算法在基准模型的基础上参数量减少了58.3%、计算量减少了 34.5%，同时 mAP 提升了2.6个百分点，基本满足火灾实时检测的需求。

关键词: YOLOv8, 轻量化, 火灾检测, 目标检测, 加权双向特征金字塔（BiFPN）

Abstract: Aiming at the lack of detection accuracy and speed bottleneck of traditional fire detection algorithms, especially for the recognition of small-scale incipient fires and large-scale rapidly spreading fires, this paper proposes a lightweight fire detection algorithm based on multi-scale feature fusion. Firstly, the EDBAN module is designed to replace the C2f module in YOLOv8, to improve the generalization ability and adaptability of the model, especially the accuracy when dealing with multi-scale fire scenarios. Secondly, the original BiFPN structure is improved to adapt to the YOLOv8 model structure, and the Weighted Blend module is designed to weight and fuse the features at each layer, which enhances the feature characterization ability and reduces the risk of missed detection. Finally, the LOTT detection module is further proposed to replace the traditional YOLOv8 detection, which achieves the accuracy and stability of the detection performance while maintaining the lightweight through a series of group convolution and scale adjustment operations. Through experiments on scene-rich fire datasets, the results show that the improved YOLOv8 algorithm reduces the parameter amount by 58.3% and the computation amount by 34.5% based on the baseline model, while the mAP improves by 2.6 percentage points, which basically meets the demand of real-time fire detection.

Key words: YOLOv8, lightweighting, fire detection, target detection, BiFPN

杨国为, 刘璇, 郜敏, 许迪. 基于多尺度特征融合的轻量级火灾检测算法[J]. 计算机工程与应用, 2024, 60(23): 229-237.

YANG Guowei, LIU Xuan, GAO Min, XU Di. Lightweight Fire Detection Algorithm Based on Multi-Scale Feature Fusion[J]. Computer Engineering and Applications, 2024, 60(23): 229-237.

参考文献

[1] ZHENG Q H, TIAN X Y, YU Z G, et al. MobileRaT: a lightweight radio transformer method for automatic modulation classification in drone communication systems[J]. Drones, 2023, 7(10): 596.
[2] ZHENG Q H, SAPONARA S, TIAN X Y, et al. A real-time constellation image classification method of wireless communication signals based on the lightweight network MobileViT[J]. Cognitive Neurodynamics, 2024, 18(2): 659-671.
[3] LIN G, ZHANG Y, XU G, et al. Smoke detection on video sequences using 3D convolutional neural networks[J]. Fire Technology, 2019, 55(5): 1827-1847.
[4] 李巨虎, 范睿先, 陈志泊. 基于颜色和纹理特征的森林火灾图像识别[J]. 华南理工大学学报 (自然科学版), 2020, 48(1): 70-83.
LI J H, FAN R X, CHEN Z B. Forest fire recognition based on color and texture features[J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(1): 70-83.
[5] TRAN D, BOURDEV L, FERGUS R, et al. Learning spatiotemporal features with 3D convolutional networks[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 4489-4497.
[6] 赵杰, 汪洪法, 吴凯. 基于特征增强及多层次融合的火灾火焰检测[J]. 中国安全生产科学技术, 2024, 20(1): 93-99.
ZHAO J, WANG H F, WU K. Fire flame detection based on feature enhancement and multi-level fusion[J]. China Safety Science and Technology, 2024, 20(1): 93-99.
[7] 李晓旭, 李泊宁, 张曦, 等. 基于CA-Res注意力机制的YOLOv5图像火灾检测算法[J]. 消防科学与技术, 2023, 42(8): 1113-1116.
LI X X, LI B N, ZHANG X, et al. Image fire detection algorithm based on YOLOv5 with CA-Res attention mechanism[J]. Fire Science and Technology, 2023, 42(8): 1113-1116.
[8] 皮骏, 刘宇恒, 李久昊. 基于YOLOv5s的轻量化森林火灾检测算法研究[J]. 图学学报, 2023, 44(1): 26-32.
PI J, LIU Y H, LI J H. Research on lightweight forest fire detection algorithm based on YOLOv5s[J]. Journal of Graphics, 2023, 44(1): 26-32.
[9] PARK M J, KO B C. Two-step real-time night-time fire detection in an urban environment using static ELASTIC-YOLOv3 and temporal fire-tube[J]. Sensors, 2020, 20(8): 2202.
[10] BOCHKOVSKIY A, WANG C Y, LIAO H Y. YOLOv4: optimal speed and accuracy of object detection[J]. arXiv:2004.10934, 2020.
[11] GE Z, LIU S T, WANG F, et al. YOLOX: exceeding YOLO series in 2021[J]. arXiv:2107.08430, 2021.
[12] LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2117-2125.
[13] WANG C Y, LIAO H, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020: 1571-1580.
[14] WANG C, LIAO H M, YEH A I. Designing network design strategies through gradient path analysis[J]. Journal of Information Science and Engineering, 2023, 39(4): 975-995.
[15] DING X, ZHANG X, HAN J, et al. Diverse branch block: building a convolution as an inception-like unit[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 10886-10895.
[16] TIAN Z, SHEN C, CHEN H, et al. FCOS: fully convolutional one-stage object detection[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2020: 9626-9635.
[17] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 7464-7475.
[18] FENG C, ZHONG Y, GAO Y, et al. TOOD: task-aligned one-stage object detection[C]//Proceedings of the 2021 IEEE International Conference on Computer Vision, 2021: 3490-3499.
[19] CHEN Q, WANG Y, YANG T, et al. You only look one-level feature[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021: 13039-13048.
[20] HASHEMZADEH M, ZADEMEHDI A. Fire detection for video surveillance applications using ICA K-medoids-based color model and efficient spatiotemporal visual features[J]. Expert Systems with Applications, 2019, 130: 60-78.
[21] HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 13713-13722.
[22] ZENG N, WU P, WANG Z, et al. A small-sized object detection oriented multi-scale feature fusion approach with application to defect detection[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-14.
[23] WANG Z, WU L, LI T, et al. A smoke detection model based on improved YOLOv5 [J]. Mathematics, 2022, 10(7): 1190.