改进YOLOv7的无明火森林烟雾检测算法

doi:10.3778/j.issn.1002-8331.2308-0349

摘要/Abstract

摘要： 快速准确判断森林火情对森林防火有着重要意义。然而，现有的森林烟雾检测模型提取的烟雾特征较为单一。因此，现有模型在图像中只有烟雾未见明火时的火情检测任务中表现并不理想。针对该问题，提出一种基于改进YOLOv7的无明火森林烟雾检测算法。该算法在主干网络中引入注意力机制CA和全卷积掩码自编码器框架FCMAE，使模型在提取语义特征的同时可以获取更为丰富的局部信息，解决了现有模型存在的特征崩溃问题。同时在预测网络中引入集中式特征金字塔CFP以加强特征的层内调节能力。另外，模型使用动态非单调调频的损失函数Wise-IoU以加强对低质量烟雾样本的检测能力。实验结果表明，相较于其他模型，该模型在检测无明火烟雾时表现上佳，精确率达到98.1%且mAP@50%达到99.1%。

关键词: 无明火森林烟雾检测, YOLOv7, 注意力机制, 特征金字塔

Abstract: Rapid and accurate judgment of forest fire is of great significance to forest fire prevention. However, the existing forest smoke detection model extracts a single smoke feature. Therefore, the existing models do not perform well in the fire detection task when there is only smoke in the image with no visible fire. To address this problem, an improved YOLOv7-based smoke detection algorithm for forests without open fires is proposed. The algorithm introduces the attention mechanism CA and the full convolutional mask self-encoder framework FCMAE in the backbone network, so that the model can obtain richer local information while extracting semantic features and solves the feature collapse problem existing in the existing model. Meanwhile, a centralized feature pyramid CFP is introduced into the prediction network to strengthen the intra-layer adjustment ability of features. In addition, the model uses the loss function Wise-IoU with dynamic non-monotonic FM to strengthen the detection ability of low-quality smoke samples. The experimental results show that compared to other models, this model performs better in detecting smoke without open flames, with an accuracy of 98.1%, mAP@50 % reaching 99.1%.

Key words: forest smoke detection without open flames, YOLOv7, attention mechanism, feature pyramid

王灏文, 朴燕, 王鈅, 姜品依. 改进YOLOv7的无明火森林烟雾检测算法[J]. 计算机工程与应用, 2024, 60(24): 340-350.

WANG Haowen, PIAO Yan, WANG Yue, JIANG Pinyi. Forest Smoke Detection Method Without Open Flames Based on Improved YOLOv7[J]. Computer Engineering and Applications, 2024, 60(24): 340-350.

参考文献

[1] 蒋春颖, 杨雪清, 张国丽, 等. 森林火灾风险评估技术体系探讨[J]. 林业资源管理, 2023(2): 17-26.
JIANG C Y, YANG X Q, ZHANG G L, et al. Discussion on the technical system of forest fire risk assessment[J]. Forest and Grassland Resources Research, 2023(2): 17-26.
[2] 徐建军. 计算机视觉技术在遥感卫星影像目标检测中的应用研究[J]. 信息记录材料, 2023, 24(5): 62-64.
XU J J. Computer vision technology in remote sensing satellite image target detection application research[J]. Information Recording Materials, 2023, 24(5): 62-64.
[3] YUAN F. Video-based smoke detection with histogram sequence of LBP and LBPV pyramids[J]. Fire Safety Journal, 2011, 46(3): 132-139.
[4] HO C C. Nighttime fire/smoke detection system based on a support vector machine[J]. Mathematical Problems in Engineering, 2013: 428545.
[5] GU K, XIA Z, QIAO J, et al. Deep dual-channel neural network for image-based smoke detection[J]. IEEE Transactions on Multimedia, 2019, 22(2): 311-323.
[6] LIU Y, QIN W, LIU K, et al. A dual convolution network using dark channel prior for image smoke classification[J]. IEEE Access, 2019, 7: 60697-60706.
[7] BA R, CHEN C, YUAN J, et al. SmokeNet: satellite smoke scene detection using convolutional neural network with spatial and channel-wise attention[J]. Remote Sensing, 2019, 11(14): 1702.
[8] TOAN N T, CONG P T, HUNG N Q V, et al. A deep learning approach for early wildfire detection from hyperspectral satellite images[C]//Proceedings of the 2019 7th International Conference on Robot Intelligence Technology and Applications (RiTA), 2019: 38-45.
[9] GOVIL K, WELCH M L, BALL J T, et al. Preliminary results from a wildfire detection system using deep learning on remote camera images[J]. Remote Sensing, 2020, 12(1): 166.
[10] XIA X, XU C, NAN B. Inception-v3 for flower classification[C]//Proceedings of the 2017 2nd International Conference on Image, Vision and Computing (ICIVC), 2017: 783-787.
[11] WOO S, DEBNATH S, HU R, et al. ConvNeXt V2: co-designing and scaling convnets with masked autoencoders[J]. arXiv:2301.00808, 2023.
[12] CHATURVEDI S, KHANNA P, OJHA A. A survey on vision-based outdoor smoke detection techniques for environmental safety[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 185: 158-187.
[13] 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.
[14] 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.
[15] TONG Z, CHEN Y, XU Z, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[J]. arXiv:2301.10051, 2023.
[16] QUAN Y, ZHANG D, ZHANG L, et al. Centralized feature pyramid for object detection[J]. arXiv:2210.02093, 2022.
[17] YUAN F, ZHANG L, XIA X, et al. Deep smoke segmentation[J]. Neurocomputing, 2019, 357: 248-260.
[18] 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.
[19] XIE Z, SONG W, BA R, et al. A spatiotemporal contextual model for forest fire detection using Himawari-8 satellite data[J]. Remote Sensing, 2018, 10(12): 1992.
[20] ZHANG Q L, YANG Y B. SA-Net: shuffle attention for deep convolutional neural networks[C]//Proceedings of the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021: 2235-2239.
[21] YANG L, ZHANG R Y, LI L, et al. SimAM: a simple, parameter-free attention module for convolutional neural networks[C]//Proceedings of the International Conference on Machine Learning, 2021: 11863-11874.
[22] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV), 2018: 3-19.
[23] LI X, WANG W, HU X, et al. Selective kernel networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 510-519.
[24] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 7132-7141.
[25] HUANG Z, WANG X, HUANG L, et al. CCNet: criss-cross attention for semantic segmentation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019: 603-612.
[26] ZHENG Z, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 12993-13000.
[27] GEVORGYAN Z. SIoU loss: more powerful learning for bounding box regression[J]. arXiv:2205.12740, 2022.
[28] LI X, WANG W, WU L, et al. Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection[C]//Advances in Neural Information Processing Systems, 2020: 21002-21012.
[29] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[30] AL-SMADI Y, ALAUTHMAN M, AL-QEREM A, et al. Early wildfire smoke detection using different YOLO models[J]. Machines, 2023, 11(2): 246.
[31] DIWAN T, ANIRUDH G, TEMBHURNE J V. Object detection using YOLO: challenges, architectural successors, datasets and applications[J]. Multimedia Tools and Applications, 2023, 82(6): 9243-9275.
[32] TAN M, PANG R, LE Q V. EfficientDet: scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 10781-10790.
[33] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
[34] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems, 2015.
[35] CHEN G, CHENG R, LIN X, et al. LMDFS: a lightweight model for detecting forest fire smoke in UAV images based on YOLOv7[J]. Remote Sensing, 2023, 15(15): 3790.
[36] PAN H, BADAWI D, CETIN A E. Fourier domain pruning of mobilenet-v2 with application to video based wildfire detection[C]//Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), 2021: 1015-1022.
[37] WU X, CAO Y, LU X, et al. Patchwise dictionary learning for video forest fire smoke detection in wavelet domain[J]. Neural Computing and Applications, 2021, 33: 7965-7977.
[38] LARSEN A, HANIGAN I, REICH B J, et al. A deep learning approach to identify smoke plumes in satellite imagery in near-real time for health risk communication[J]. Journal of Exposure Science & Environmental Epidemiology, 2021, 31(1): 170-176.