Using PCAand one‐stage detectors for real‐time forest fire detection

Wu, Shixiao; Guo, Chengcheng; Yang, Jianfeng

doi:10.1049/joe.2019.1145

Cited by 13 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Redundant filters, which had low energy impulse response, were removed to ensure the model's efficiency on edge devices. Wu et al [24] applied principal component analysis (PCA) to process forest fire images, and then fed them into the training network. The combination of two models was proved to enhance location results.…”

Section: Introductionmentioning

confidence: 99%

A Forest Fire Detection System Based on Ensemble Learning

Lin

et al. 2021

Forests

369

125

View full text Add to dashboard Cite

Due to the various shapes, textures, and colors of fires, forest fire detection is a challenging task. The traditional image processing method relies heavily on manmade features, which is not universally applicable to all forest scenarios. In order to solve this problem, the deep learning technology is applied to learn and extract features of forest fires adaptively. However, the limited learning and perception ability of individual learners is not sufficient to make them perform well in complex tasks. Furthermore, learners tend to focus too much on local information, namely ground truth, but ignore global information, which may lead to false positives. In this paper, a novel ensemble learning method is proposed to detect forest fires in different scenarios. Firstly, two individual learners Yolov5 and EfficientDet are integrated to accomplish fire detection process. Secondly, another individual learner EfficientNet is responsible for learning global information to avoid false positives. Finally, detection results are made based on the decisions of three learners. Experiments on our dataset show that the proposed method improves detection performance by 2.5% to 10.9%, and decreases false positives by 51.3%, without any extra latency.

show abstract

Section: Introductionmentioning

confidence: 99%

A Forest Fire Detection System Based on Ensemble Learning

Lin

et al. 2021

Forests

369

125

View full text Add to dashboard Cite

show abstract

“…Additionally, lightweight forest fire detection models have been developed for deployment on hardware devices such as CCTV. These applications typically employ onestage detectors such as Yolov3, SSD [19,20], Yolov5, EfficientDet [21], Yolov5 [22][23][24], and Deformable DETR [25]. Similarly, object detectors have been employed for fire detection in urban indoor and outdoor environments, including chemical facility fire detection using Yolov2 [26], fire and smoke detection using Yolov3 and Yolov2 [27,28], and indoor fire and smoke detection using Faster R-CNN and Yolov5 [29][30][31].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Based Fire Risk Detection on Construction Sites

Ann,

Koo

2023

Sensors

View full text Add to dashboard Cite

The recent large-scale fire incidents on construction sites in South Korea have highlighted the need for computer vision technology to detect fire risks before an actual occurrence of fire. This study developed a proactive fire risk detection system by detecting the coexistence of an ignition source (sparks) and a combustible material (urethane foam or Styrofoam) using object detection on images from a surveillance camera. Statistical analysis was carried out on fire incidences on construction sites in South Korea to provide insight into the cause of the large-scale fire incidents. Labeling approaches were discussed to improve the performance of the object detectors for sparks and urethane foams. Detecting ignition sources and combustible materials at a distance was discussed in order to improve the performance for long-distance objects. Two candidate deep learning models, Yolov5 and EfficientDet, were compared in their performance. It was found that Yolov5 showed slightly higher mAP performances: Yolov5 models showed mAPs from 87% to 90% and EfficientDet models showed mAPs from 82% to 87%, depending on the complexity of the model. However, Yolov5 showed distinctive advantages over EfficientDet in terms of easiness and speed of learning.

show abstract

“…Wang et al [1] used neural networks for multi-sensor fire detection and applied wavelet filtering for feature extraction of the collected data to filter out noisy signals, avoiding the signal from being swamped by the noise associated with the maximum and minimum measurements through normalization, and performing data fusion on the feature part of the signal to identify fires. Tlig [2], Otabek [3], and Wu [4] studied multi-sensor data fusion systems for fire detection, and they all used principal component analysis (PCA) for feature extraction of the acquired data and conducted fire alarm studies based on the feature values of the acquired data. Derbel In summary, researchers at home and abroad have conducted research on multi-sensor fire alarms for fire scenarios such as ship fires and indoor fires, and relatively little research has been conducted on multi-sensor data fusion for transformer fire scenarios.…”

Section: Introductionmentioning

confidence: 99%

Pre-processing study of multi-sensor data

Li¹,

Wang²,

Yan³

2023

IJCIT

View full text Add to dashboard Cite

For multi-sensor data with multi-source heterogeneity, data pre-processing is required for data fusion. This paper proposes a data pre-processing method, firstly, the image data is binarized using the designed image binarization algorithm and flame area extraction algorithm, and the flame area information in the fire image is extracted into one-dimensional data, then the five one-dimensional data of ambient temperature, temperature-sensitive cable, CO2, CO and flame area are noise reduced using the designed wavelet noise reduction algorithm, and finally the final pre-processed data is calculated by the selected normalization formula. The results of the study show that the method can improve the effectiveness of multi-sensor data fusion.

show abstract

Using PCAand one‐stage detectors for real‐time forest fire detection

Cited by 13 publications

References 14 publications

A Forest Fire Detection System Based on Ensemble Learning

A Forest Fire Detection System Based on Ensemble Learning

Deep Learning Based Fire Risk Detection on Construction Sites

Pre-processing study of multi-sensor data

Contact Info

Product

Resources

About