Khaled Chetehouna

On the Evaluation of Segmentation Methods for Wildland Fire

This paper focuses on the study of fire color spaces and the evaluation of image segmentation methods commonly available in the literature of wildland and urban fires. The evaluation method, based on the determination of a segmentation quality index, is applied on three series of fire images obtained at the usual scales of validation of forest fire models (laboratory scale, fire tunnel scale and field scale). Depending on the considered scale, different methods reveal themselves as being the most appropriate. In this study we present the advantages and drawbacks of different segmentation algorithms and color spaces used in fire detection and characterization.

Comparison of two methods for estimating fire positions and the rate of spread of linear flame fronts

The aim of this paper is to compare two continuous methods for the identification of fire front positions and the rate of spread of linear flame fronts. The first technique is based on the heat fluxes measured by a specific thermal sensor and the use of the inverse method. The second one uses an image processing technique applying the simple direct linear transformation (DLT) algorithm and the fire segmentation algorithm to obtain fire front positions. The fire segmentation method has been selected by benchmarking four recently published studies and involves a supervised evaluation criterion. The two continuous approaches give closely similar results and it is shown that these two techniques can be respectively validated by each other.

Measurement of radiative absorption coefficient for a vegetal medium

The radiative heat flux received by vegetation is a leading process of the propagation of forest fires. This flux is a function of the radiative absorption coefficient. We have measured this coefficient for Quercus coccifera. The variation of the values of the absorption coefficient as a function of the load (surface density of vegetation) has been studied. We have shown that the absorption coefficient is proportional to the load; the proportionality coefficient depends upon the nature of the vegetation.

Investigation of a novel image segmentation method dedicated to forest fire applications

To face fire it is crucial to understand its behaviour in order to maximize fighting means. To achieve this task, the development of a metrological tool is necessary for estimating both geometrical and physical parameters involved in forest fire modelling. A key parameter is to estimate fire positions accurately. In this paper an image processing tool especially dedicated to an accurate extraction of fire from an image is presented. In this work, the clustering on several colour spaces is investigated and it appears that the blue chrominance Cb from the YCbCr colour space is the most appropriate. As a consequence, a new segmentation algorithm dedicated to forest fire applications has been built using first an optimized k-means clustering in the Cb-channel and then some properties of fire pixels in the RGB colour space. Next, the performance of the proposed method is evaluated using three supervised evaluation criteria and then compared to other existing segmentation algorithms in the literature. Finally a conclusion is drawn, assessing the good behaviour of the developed algorithm.

Fire scene segmentations for forest fire characterization: A comparative study

Forest fires constitute one of the most damaging natural disaster for many countries around the world. Its mechanisms can be studied through forest fire metrology. Despite a large number of proposed algorithms for fire detection, only few works adress the segmentation problem in fire metrology. The main purpose of this paper is to introduce a SVM-based segmentation method for forest fire metrology. This method is confronted with state-of-the-art fire segmentation algorithms using supervised evaluation criteria and an ad hoc expertised picture database. The obtained results highlight the good performances of the proposed method compared to prior algorithms.