Image Based Forest Fire Detection Using Dynamic Characteristics with Artificial Neural Networks

Zhang, Dengyi; Han, Shizhong; Zhao, Jianhui; Zhong, Zhang; Qu, Chengzhang; Ke, Youwang; Chen, Xiang

doi:10.1109/jcai.2009.79

Cited by 49 publications

(28 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model estimated movement directions of objects in real-time for analysis of smoke. Zhang et al [9] proposed a real-time forest fire detection algorithm using artificial neural networks based on dynamic characteristics of fire regions segmented from video images. Yu et al [10]presented a method by using color and motion features for video smoke detection.…”

Section: Related Workmentioning

confidence: 99%

Dual-Encoded Features from Both Spatial and Curvelet Domains for Image Smoke Recognition

2019

KSII TIIS

View full text Add to dashboard Cite

Visual smoke recognition is a challenging task due to large variations in shape, texture and color of smoke. To improve performance, we propose a novel smoke recognition method by combining dual-encoded features that are extracted from both spatial and Curvelet domains. A Curvelet transform is used to filter an image to generate fifty sub-images of Curvelet coefficients. Then we extract Local Binary Pattern (LBP) maps from these coefficient maps and aggregate histograms of these LBP maps to produce a histogram map. Afterwards, we encode the histogram map again to generate Dual-encoded Local Binary Patterns (Dual-LBP). Histograms of Dual-LBPs from Curvelet domain and Completed Local Binary Patterns (CLBP) from spatial domain are concatenated to form the feature for smoke recognition. Finally, we adopt Gaussian Kernel Optimization (GKO) algorithm to search the optimal kernel parameters of Support Vector Machine (SVM) for further improvement of classification accuracy. Experimental results demonstrate that our method can extract effective and reasonable features of smoke images, and achieve good classification accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Dual-Encoded Features from Both Spatial and Curvelet Domains for Image Smoke Recognition

2019

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…related threshold is applied to discriminate fire objects candidates. Shape complexity [13]: In many cases, flame objects correspond to complex shape. This feature can be evaluated by the coefficient C=L 2 /S, where L corresponds to the shape perimeter and S to the shape surface.…”

Section: Flame Detection Using Features Fusion Based On a Fuzzy Classmentioning

confidence: 99%

Flame Detection for Video-Based Early Fire Warning for the Protection of Cultural Heritage

Dimitropoulos

Günay

Kose

et al. 2012

Progress in Cultural Heritage Preservation

View full text Add to dashboard Cite

Abstract. Cultural heritage and archaeological sites are exposed to the risk of fire and early warning is the only way to avoid losses and damages. The use of terrestrial systems, typically based on video cameras, is currently the most promising solution for advanced automatic wildfire surveillance and monitoring. Video cameras are sensitive in visible spectra and can be used either for flame or smoke detection. This paper presents and compares three video-based flame detection techniques, which were developed within the FIRESENSE EU research project.

show abstract

“…Zhang et al [9] have proposed an algorithm using artificial neural network for forest fire detection based on dynamic characteristics of fire regions segmented from video images. Zhang et al [7] in their approach have first used wavelet to test whether a pixel from the image belongs to fire region and then used Fast Fourier Transform to describe the contour of fire area.…”

Section: Related Workmentioning

confidence: 99%

A smart forest-fire early detection sensory system: Another approach of utilizing wireless sensor and neural networks

2010

View full text Add to dashboard Cite

In this paper, we analyze the potential of combining wireless sensor networks with artificial neural networks (ANNs) to build a "smart forest-fire early detection sensory system" (SFFEDSS). We outline our new SFFEDS system in which temperature, light and smoke data from low-cost sensor nodes spread out on the forest bed is aggregated into information. This information is spatially and temporally labeled into knowledge which will be encoded as input to ANN models that convert it into intelligence. At the top tier of our system, the trained neural models make intelligent decisions and report fire in its early stages based on gathered field knowledge. In our experimentation, we extended the sensing capability of the MicaZ sensor motes by attaching external smoke detectors of our own design. The results are very promising as the SFFEDSS unit is able to not only detect fire but also accurately report the direction of fire progress which is deduced from the wind direction. *

show abstract

Image Based Forest Fire Detection Using Dynamic Characteristics with Artificial Neural Networks

Cited by 49 publications

References 7 publications

Dual-Encoded Features from Both Spatial and Curvelet Domains for Image Smoke Recognition

Dual-Encoded Features from Both Spatial and Curvelet Domains for Image Smoke Recognition

Flame Detection for Video-Based Early Fire Warning for the Protection of Cultural Heritage

A smart forest-fire early detection sensory system: Another approach of utilizing wireless sensor and neural networks

Contact Info

Product

Resources

About