Research on Image Fire Detection Based on Support Vector Machine

Chen, Ke; Cheng, Yanying; Bai, Hui; Mou, Chunjie; Zhang, Yuchun

doi:10.1109/icfsfpe48751.2019.9055795

Cited by 19 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The last is to determine the classification to determine whether the image is as desired and looking at the resulting accuracy, the resulting accuracy will explain in the last section. [35]. • Taking Picture…”

Section: Methodsmentioning

confidence: 99%

Prototype Design Internet of Things Based Waste Management Using Image Processing

Widianto¹,

Wahyu²,

Gusna³

2021

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Waste is currently a serious problem often found in rural areas, rural areas, and even industrial areas. Waste is a side effect of activities carried out by humans to meet social or industrial needs. Increasing human productivity will also increase the amount of waste produced. To overcome this, a sorting management system is needed. Good waste is seen from the processing method to the recycling process. The waste management problem still relies on the old system transporting and disposing of waste to the final disposal site (TPA). The TPA itself sometimes piles up in one place so that the waste process becomes uneven and the sorting process is not good, causing type waste. This accumulates and mixes with other hazardous waste. In today's modern era, the management and sorting system is the same. Object detection and waste classification are carried out in the Sensor system to introduce the previously prepared model. The prototype article recognition model is prepared with waste images to produce a freeze forecast graph used for object discovery which is carried out via the camera associated with the Arduino Uno as the basic unit handling. Ultrasonic sensors are inserted into each garbage compartment to filter out the refill filling rate. The sorting system itself can use computer-based image processing methods. Image Processing is used to process data in real-time and fill the trash level. The sensor module that is implanted to detect waste management personnel, the results of this study prove that image management can accommodate waste particles and tested in the BlackBox method produces results following the required quantitative with the accuracy in both the camera, sensor, and image process used can detect an average of 70%.

show abstract

Section: Methodsmentioning

confidence: 99%

Prototype Design Internet of Things Based Waste Management Using Image Processing

Widianto¹,

Wahyu²,

Gusna³

2021

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

show abstract

“…Nahid et al [31] combined visual sensors with smoke sensors can provide more effective fire detection. Traditional machine learning methods heavily rely on handcrafted features and support vector machines(SVMs) for fire detection [32]. However, these methods are susceptible to false alarms caused by objects with similar colors to fire.With the development of computer vision, A deep classification network has been employed to classify the presence or absence of fire in images [33].…”

Section: A Fire Detectionmentioning

confidence: 99%

FCLGYOLO: Feature Constraint and Local Guided Global Feature for Fire Detection in Unmanned Aerial Vehicle Imagery

Ren,

Zhang,

Wang

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Recently, the use of Unmanned Aerial Vehicle (UAV) imagery for object detection in forest fire detection has gained significant attention and has shown remarkable performance. However, most existing object detection models have neglected the exploration of relationships between positive sample features, which is crucial for learning more representative and colorrobust features. Additionally, small objects in UAV images poses challenges in capturing sufficient object information and hinders accurate object detection. To address these issues, we propose FCLGYOLO that aims to constrain positive sample features and enrich the object information in the feature maps. Specifically, a Feature Invariance and Covariance Constraint (FICC) structure proposed to maintain feature invariance among positive samples and remove internal correlations. Furthermore, a Local Guided Global Module (LGGM) proposed to enrich object positioning and semantic information in the feature map, which leverages local features that focus on spatial information to facilitate the learning of global features that focus on frequency information. It is interesting to show that FCLGYOLO performs well even in the presence of heavy smoke or tree occlusions. Compared with multiple state-of-the-art object detection models on a forest fire dataset, experimental results demonstrate the superiority of FCLGYOLO. The code is available at: https://www.github.com/ zhangshao249/FCLGYOLO.

show abstract

“…It is difficult to exclude objects whose colors are highly similar to flames only by using the color model, so it is necessary to segment moving objects based on the dynamic features of flames in a video. In the process of fire recognition, the interframe difference method [20], optical flow method [21], or background subtraction method [22] are commonly used to segment moving targets. The interframe difference method has low computational complexity, but it depends too much on the moving speed of the target.…”

Section: Vibe Moving Target Segmentationmentioning

confidence: 99%

Random Forest Feature Selection and Back Propagation Neural Network to Detect Fire Using Video

et al. 2022

View full text Add to dashboard Cite

As the most common serious disaster, fire may cause a lot of damages. Early detection and treatment of fires are of great significance to ensure public safety and to reduce losses caused by fires. However, traditional fire detectors are facing some focus issues such as low sensitivity and limited detection scenes. To overcome these problems, a video fire detection hybrid method based on random forest (RF) feature selection and back propagation (BP) neural network is proposed. The improved flame color model in RGB and HSI space and the visual background extractor (ViBe) in moving target detection algorithm are used to segment the suspected flame regions. Then, multidimensional features of flames are extracted from the suspected regions, and these extracted features are combined and selected according to the RF feature importance analysis. Finally, a BP neural network model is constructed for multifeature fusion and fire recognition. The test results on several experimental video sets show that the proposed method can effectively avoid feature interference and has an excellent recognition effect on fires in a variety of scenarios. The proposed method is applicable for fire recognition applied in video surveillance and detection robots.

show abstract

Research on Image Fire Detection Based on Support Vector Machine

Cited by 19 publications

References 6 publications

Prototype Design Internet of Things Based Waste Management Using Image Processing

Prototype Design Internet of Things Based Waste Management Using Image Processing

FCLGYOLO: Feature Constraint and Local Guided Global Feature for Fire Detection in Unmanned Aerial Vehicle Imagery

Random Forest Feature Selection and Back Propagation Neural Network to Detect Fire Using Video

Contact Info

Product

Resources

About