|
|
基于深度学习的火焰检测算法设计
|
Abstract:
为了更好地实现消防机器人对于火源的自主识别，结合YOLOv5s提出一种改进的火焰检测方法。在YOLOv5s的主干网络和检测头中添加CBAM注意力模块，能够自适应地对特征图进行调整，使得网络能够更好地关注重要的特征，从而降低火焰检测的小目标漏检率。使用C3-DBB模块替换卷积层，C3-DBB模块采用了密集的连接和多尺度的感受野，从而能够更好地捕捉目标的细节信息，减少信息损失。使用ConvNeXt V2模块替换主干网络模块，从而获得更大的感受野和更好的特征提取能力，提高目标检测的精度。实验结果表明，与YOLOv5s原始模型相比，改进后的模型平均精度提升5.8%，同时降低了模型大小。
In order to better realize the autonomous recognition of fire sources by firefighting robots, an improved flame detection method is proposed in combination with YOLOv5s. Adding the CBAM attention module to the backbone network and detection head of YOLOv5s can adaptively adjust the feature map, enabling the network to better focus on important features, thus reducing the small target miss detection rate of flame detection. Replacing the convolutional layer with the C3-DBB module, the C3-DBB module employs dense connectivity and a multi-scale receptive field, which enables better capture of detailed information about the target and reduces information loss. The ConvNeXt V2 module is used to replace the backbone network module, thus obtaining a larger receptive field and better feature extraction capability to improve the accuracy of target detection. The experimental results show that the improved model improves the average accuracy by 5.8% compared to the original YOLOv5s model, while reducing the model size.
| [1] | Ren, S., He, K., Girshick, R., et al. (2015) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Advances in Neural Information Processing Systems. https://doi.org/10.48550/arXiv.1506.01497 |
| [2] | Begum, S.R., Datta, S.Y. and Manoj, M.S.V. (2021) Mask R-CNN for Fire Detection. International Research Journal of Computer Science, 8, 145-151. https://doi.org/10.26562/irjcs.2021.v0807.003 |
| [3] | Cai, Z. and Vasconcelos, N. (2019) Cascade R-CNN: High Quality Object Detection and Instance Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43, 1483-1498. https://doi.org/10.1109/TPAMI.2019.2956516 |
| [4] | Lin, T.Y., Goyal, P., Girshick, R., et al. (2017) Focal Loss for Dense Object Detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, 22-29 October 2017, 2980-2988. https://doi.org/10.1109/ICCV.2017.324 |
| [5] | Duan, K., Bai, S., Xie, L., et al. (2019) CenterNet: Keypoint Triplets for Object Detection. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, 27 October-2 November 2019, 6569-6578. https://doi.org/10.1109/ICCV.2019.00667 |
| [6] | Redmon, J., Divvala, S., Girshick, R., et al. (2016) You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, 27-30 June 2016, 779-788. https://doi.org/10.1109/CVPR.2016.91 |
| [7] | Woo, S., Debnath, S., Hu, R., et al. (2023) Convnext v2: Co-Designing and Scaling Convnets with Masked Autoencoders. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, 17-24 June 2023, 16133-16142. https://doi.org/10.1109/CVPR52729.2023.01548 |
| [8] | Woo, S., Park, J., Lee, J.Y., et al. (2018) CBAM: Convolutional Block Attention Module. Proceedings of the European Conference on Computer Vision (ECCV), 3-19. https://doi.org/10.1007/978-3-030-01234-2_1 |
| [9] | Ding, X., Zhang, X., Han, J., et al. (2021) Diverse Branch Block: Building a Convolution as an Inception-Like Unit. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, 20-25 June 2021, 10886-10895. https://doi.org/10.1109/CVPR46437.2021.01074 |
