In this paper, we propose a new method for smoke detection in both outdoor and indoor video sequences based on embedded system. The proposed method is composed from three main steps to determine the smoke in the field of view of the camera. The first step is to determine the moving area by using background subtraction algorithm. The second step is to find color of every pixel in the moving area by using pixel extraction algorithm. The final step is to find the shape of the moving area by using dispersion and growth rate parameters. Dispersion is based on ratio of perimeter and area of the moving area. Growth rate is calculated from increasing the number of pixel of the moving area. A new contribution of the proposed approach is that all algorithms are executed on embedded system. For embedded system, we chose BeagleBone Black embedded board because of its cost and efficient. Furthermore, a firefighter robot based on this board is built to demonstrate the efficacy of the proposed method.
CITATION STYLE
Nguyen, T. P. T., & Nguyen, H. (2016). Image processing for smoke detection based on embedded system. In Lecture Notes in Electrical Engineering (Vol. 371, pp. 509–517). Springer Verlag. https://doi.org/10.1007/978-3-319-27247-4_43
Mendeley helps you to discover research relevant for your work.