.png){kind=icon}
返回
A visualized fire detection method based on convolutional neural network beyond anchor
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-022-03243-7.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Convolutional neural networks (CNNs) have achieved the most advanced performance in visual object detection and semantic segmentation tasks, so that the application of CNNs in fire detection will greatly improve the accuracy of detection. However, the existing fire detection methods are difficult to achieve real-time detection due to the complicated model, slow detection rate, low detection accuracy, and the huge amount of calculation, also, high memory usage limits the implementation of some methods on the device. Therefore, a fast and efficient fire detection model, whose design is derived from the lightweight network MobileNetV3 and the anchor free structure, is proposed in this paper. The proposed method has achieved an accuracy of 90.2% on a self-built dataset, while the model size is only 21.4M, and the running speed can reach 29.5f/s. At the same time, comparative experiments were conducted on two public fire datasets, and according to the results, the proposed method showed better performance and faster speed, confirming that the proposed method can satisfy real-time fire detection and is achievable for application on embeddable equipment.
Keyword:
Fire detection
Object detection
Anchor free
Lightweight network
CNNs
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
Convolutional Neural Networks Based Fire Detection in Surveillance Videos基于卷积神经网络的监控视频火灾检测.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Early fire detection algorithm based on irregular patterns of flames and hierarchical Bayesian NetworksFIRE SAFETY JOURNAL
FIRE SAFETY JOURNALIF3.3
PREAI
分享收藏Early fire detection using convolutional neural networks during surveillance for effective disaster management在监视过程中使用卷积神经网络进行早期火灾检测，以进行有效的灾难管理NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Thermal comfort, perceived air quality, and cognitive performance when personally controlled air movement is used by tropically acclimatized persons当热带适应的人使用个人控制的空气运动时，热舒适性，感知的空气质量和认知表现Indoor AirOAAI
Indoor AirIF0
OAAI分享收藏Fast fire flame detection in surveillance video using logistic regression and temporal smoothingFIRE SAFETY JOURNAL
FIRE SAFETY JOURNALIF3.3
PREAI
分享收藏Results of a prospective phase 2 study combining imatinib mesylate and cytarabine for the treatment of Philadelphia-positive patients with chronic myelogenous leukemia in chronic phaseBloodOAAI
BloodIF0
OAAI分享收藏
查看更多内容