Skip to content
2000
Volume 18, Issue 7
  • ISSN: 2352-0965
  • E-ISSN: 2352-0973

Abstract

Background

Fire incidents occur in complex scenarios, where the dynamic positions and varying scales of flames and smoke pose challenges for fire detection. To improve the stability, localization accuracy, and detection precision of small targets in fire detection, a fused PBCA method for fire and smoke object detection has been proposed in this paper, called FS-YOLOv8.

Objective

The objective of this approach was to improve the detection accuracy of flames and smoke, enhance the robustness of the system, and strengthen the feature representation capability. It aimed to optimize the contribution of feature maps at different scales, allowing the network to capture inter-channel correlations while preserving precise localization information of the targets. Furthermore, it aimed to enhance the learning ability of small-scale flame and smoke objects.

Methods

Firstly, DCN (Deformable Convolutional Network) was integrated into the CSPDarknet backbone network to extract features from flame and smoke images. Subsequently, a module called PBCA was designed by combining BiFPN (Bidirectional Feature Pyramid Network) and coordinate attention. Finally, a small object detection layer, YOLO HEAD-4, was constructed.

Results

The experimental results of our proposed FS-YOLOv8 method on a self-made dataset demonstrated improved detection accuracy compared to other conventional methods. Therefore, the FS-YOLOv8 method effectively enhanced the performance of object detection in fire and smoke scenarios.

Conclusion

The FS-YOLOv8 method has been found to effectively improve the performance of object detection in fire and smoke scenarios, enhance the robustness of the system, strengthen the feature representation capability, and amplify the learning ability of small-scale flame and smoke objects.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/raeeng/10.2174/0123520965293234240416102241
2024-05-06
2025-09-26

  • From This Site

    /content/journals/raeeng/10.2174/0123520965293234240416102241
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. TuranM. AlmaliogluY. AraujoH. KonukogluE. SittiM. Deep EndoVO: A recurrent convolutional neural network (RCNN) based visual odometry approach for endoscopic capsule robots.Neurocomputing20182751861187010.1016/j.neucom.2017.10.014
     [Google Scholar]
  2. HuangH.N. ZhangT. YangC.T. SheenY.J. ChenH.M. ChenC.J. TsengM.W. Image segmentation using transfer learning and Fast R-CNN for diabetic foot wound treatments.Front. Public Health20221096984610.3389/fpubh.2022.969846 36203688
     [Google Scholar]
  3. WuS. WangY. YangH. WangP. Improved faster R-CNN for the detection method of industrial control logic graph recognition.Front. Bioeng. Biotechnol.1010.3389/fbioe.2022.944944 35992353
     [Google Scholar]
  4. ShunlingR. DanyangL. QinghuaG. An intelligent detection method for open-pit slope fracture based on the improved mask R-CNN.J. Min. Sci.202258350351810.1134/S1062739122030176
     [Google Scholar]
  5. XiangyuD. ShanshanL. An improved SSD object detection algorithm based on attention mechanism and feature fusion.J. Phys. Conf. Ser.20232450101208810.1088/1742‑6596/2450/1/012088
     [Google Scholar]
  6. RedmonJ. DivvalaS. GirshickR. You only look once: unified, real-time object detectionProceedings of the IEEE Conference on Computer Vision and Pattern Recognition2016779788.10.1109/CVPR.2016.91
     [Google Scholar]
  7. RedmonJ. FarhadiA. YOLO9000: better, faster, strongerProceedings of the IEEE Conference on Computer Vision and Pattern Recognition201765176525.
     [Google Scholar]
  8. RedmonJ. FarhadiA. YOLOv3: an incremental improvementTech Repor.Available from: https://arxiv.org/abs/1804.02767 2021
     [Google Scholar]
  9. Bochko vskiyA. WangC. Y. LiaoH. Y. M. YOLOv4: optimal speed and accuracy of object detection Tech Repor.2021
     [Google Scholar]
  10. DUANK. BAIS. XIE. Centernet: Keypoint triplets for object detectionProceedings of the IEEE/CVF international conference on computer vision, 2019, pp. 6569-6578 Seoul, Korea (South).10.1109/ICCV.2019.00667
     [Google Scholar]
  11. MadkarS. SakhareD.Y. Video-Based Forest Fire and Smoke Detection Using YoLo and CNN3rd International Conference on Power, Energy, Control and Transmission Systems, ICPECTS 2022 - Proceedings, 2022 Chennai, India
     [Google Scholar]
  12. ChenC. YuJ. LinY. LaiF. ZhengG. LinY. Fire detection based on improved PP-YOLO.Signal Image Video Process.20231741061106710.1007/s11760‑022‑02312‑1
     [Google Scholar]
  13. PandaS. PadhiA. RathB.S. Faster & smoother detection of forest fire using YOLO v3Proceedings - 2022 International Conference on Machine Learning, Computer Systems and Security MLCSS, 2022pp. 100-104.10.1109/MLCSS57186.2022.00026
     [Google Scholar]
  14. ZhaoX. XiangM. HeJ. HuangC. Fire detection method in infrared image based on improved YOLO networkProceeding - 2021 China Automation Congress, CAC, 2021, pp. 5565-5570.10.1109/CAC53003.2021.9728278
     [Google Scholar]
  15. HowardA SandlerM ChuG Searching for MobileNetV3.Comput. Vis. Patt. Recog.201910.48550/arXiv.1905.02244
     [Google Scholar]
  16. DaiJ.F. QiH.Z. XIONGY W Deformable convolutional networks2017 IEEE International Conference on Computer Vision (ICCV)., vol. 7, 2017, pp. 764-773 Venice, Italy.
     [Google Scholar]
  17. WangC.Y. LiaoH.Y.M. WuY.H. CSPNet: a new backbone that can enhance the learning capability of CNNProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020pp. 390-391.10.1109/CVPRW50498.2020.00203
     [Google Scholar]
  18. TanM.X. PangR.M. LeQ.V. fficientDet: scalable and efficient object detectionProceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10778-10787.
     [Google Scholar]
  19. HOUQ ZHOUD FENGJ Coordinate attention for efficient mobile network designProceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021pp. 13713-13722
     [Google Scholar]
  20. SimonyanK ZissermanA Very deep convolutional networks for large-scale image recognition.Comput. Vis. Patt. Recog.2021110.48550/arXiv.1409.1556
     [Google Scholar]
  21. LinT.Y. DollArP. GirshickR. Feature pyramid networks for object detectionProceedings of the E Conference on Computer Vision and Pattern Recognition, pp. 2117-2125.10.1109/CVPR.2017.106
     [Google Scholar]
  22. HeK. ZhangX. RenS. SunJ. Spatial pyramid pooling in deep convolutional networks for visual recognition.IEEE Trans. Pattern Anal. Mach. Intell.20153791904191610.1109/TPAMI.2015.2389824 26353135
     [Google Scholar]
  23. LiuS. QiL. QinH.F. Path aggregation network for instance segmentationProceedings of the IEEE conference on Computer Vision and Pattern Recognition20189876810.1109/CVPR.2018.00913
     [Google Scholar]
  24. TanM.X. PangR.M. LeQ.V. EfficientDet: scalable and efficient object detectionProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition20201077810787.10.1109/CVPR42600.2020.01079
     [Google Scholar]
  25. TanM. LeQ. EfficientNet: rethinking model scaling for convolutional neural networksProceedings of International Conference on Machine Learning.201961056114
     [Google Scholar]
  26. HuJ. ShenL. SunG. Squeeze-and-excitation networksProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition201871327141.
     [Google Scholar]
  27. WooS. ParkJ. LeeJ.Y. CBAM: convolutional block attention moduleProceedings of the European Conference on Computer Vision2018319.
     [Google Scholar]
/content/journals/raeeng/10.2174/0123520965293234240416102241
Loading
Fire Smoke Target Detection Incorporating PBCA
Recent Advances in Electrical & Electronic Engineering 18, 999 (2025); https://doi.org/10.2174/0123520965293234240416102241
/content/journals/raeeng/10.2174/0123520965293234240416102241
/content/journals/raeeng/10.2174/0123520965293234240416102241
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): DCN; fire; FS-YOLOv8; Object detection; PBCA; smoke

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test