ABSTRACT
In the early stages of a fire outbreak, timely and accurate detection is crucial. However, existing target algorithms struggle to meet the real-time and accuracy requirements for fire detection. Addressing this issue, this paper proposes a new fire detection algorithm, DG-YOLO (Double channels and Group convolution), based on the YOLOv5s model. Firstly, the model introduces a novel dual-branch group convolution structure called DGBlock, which cascades large convolutional kernels to increase the network's receptive field. Moreover, it employs group convolution to reduce computational and parameter complexity, effectively enhancing the network's detection capabilities while lowering computational complexity. Secondly, the Effective Squeeze-and-Excitation (ESE) attention mechanism is utilized to boost the network's long-range modeling ability, guiding the network to focus more on relevant features. Experimental results demonstrate that using the DG-YOLO algorithm achieves a detection accuracy (mAP) of 41.9% on a custom fire dataset, an improvement of 2.8% over the original algorithm. To further validate the network's performance, this paper compares four mainstream algorithms on the COCO 2017 dataset, achieving an mAP of 38.6%, a 1.2% improvement over the original algorithm, effectively confirming the algorithm's efficacy.
- Elizalde D Q R, Garcia R J P, Mitra M M S, 2018. Wireless automated fire detection system on utility posts using ATmega328P. 2018 IEEE 10th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control. Environment and Management (HNICEM). IEEE, 1-5.Google ScholarCross Ref
- Kadri B, Bouyeddou B, Moussaoui D. 2018. Early fire detection system using wireless sensor network. 2018 International conference on applied smart systems (ICASS). IEEE, 1-4.Google ScholarCross Ref
- Hutauruk A R, Pardede J, Aritonang P, 2019. Implementation of Wireless Sensor Network as Fire Detector using Arduino Nano. 2019 International Conference of Computer Science and Information Technology (ICoSNIKOM). IEEE, 1-4.Google ScholarCross Ref
- Muhammad K, Ahmad J, Lv Z, 2018. Efficient deep CNN-based fire detection and localization in video surveillance applications[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 49(7): 1419- 1434.Google ScholarCross Ref
- Iandola F N, Han S, Moskewicz M W, 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size. arXiv preprint arXiv:1602.07360.Google Scholar
- Xue Z, Lin H, Wang F. 2022. A small target forest fire detection model based on YOLOv5 improvement. Forests, 13(8): 1332.Google ScholarCross Ref
- Ultralytics Homepage. 2023. https://github.com/ultralytics/yolov5. 2023/12/02.Google Scholar
- Xu R, Lin H, Lu K, 2021. A forest fire detection system based on ensemble learning. Forests, 12(2): 217.Google ScholarCross Ref
- Celik T, Demirel H. 2009. Fire detection in video sequences using a generic color model. Fire safety journal, 44(2): 147-158.Google Scholar
- Frizzi S, Kaabi R, Bouchouicha M, 2016. Convolutional neural network for video fire and smoke detection. IECON 2016-42nd Annual Conference of the IEEE Industrial Electronics Society. IEEE, 877-882.Google ScholarCross Ref
- Namozov A, Im Cho Y. 2018. An efficient deep learning algorithm for fire and smoke detection with limited data. Advances in Electrical and Computer Engineering,18(4): 121-128.Google ScholarCross Ref
- Lee Y, Shim J. 2019. False positive decremented research for fire and smoke detection in surveillance camera using spatial and temporal features based on deep learning. Electronics, 8(10): 1167.Google ScholarCross Ref
- Lee Y, Park J. Centermask: 2020. Real-time anchor-free instance segmentation. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 13906-13915.Google Scholar
- Bochkovskiy A, Wang C Y, Liao H Y M. Yolov4. 2020. Optimal speed and accuracy of object detection. arxiv preprint arxiv:2004.10934Google Scholar
- Wang C Y, Bochkovskiy A, Liao H Y M. 2023. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7464-7475.Google ScholarCross Ref
Recommendations
A fire monitoring and alarm system based on channel-wise pruned YOLOv3
AbstractFire detection and alarm system is fully concerned for safety. And convolutional neural network (CNN) has been introduced into fire/smoke detection based on video/image understanding. However, the samples of the existed public fire/smoke data sets ...
QuasiVSD: efficient dual-frame smoke detection
AbstractSmoke is a typical symptom of early fire, and the appearance of a large amount of abnormal smoke usually indicates an impending abnormal accident. A smart smoke detection method can substantially reduce damage caused by fires in cities, factories ...
Smoke detection in video using convolutional neural networks and efficient spatio-temporal features
AbstractFire detection in its early stages is of a great importance in different environmental related applications. Among the visual signs of fire, smoke appears earlier than the flames in many cases, and quickly reaches the environment. Thus,...
Highlights- A computer vision-based smoke detection method is presented.
- A fusion of deep, ...
Comments