Fully Automatic Approach for Smoke Tracking Based on Deep Image Quality Enhancement and Adaptive Level Set Model

Abstract

In recent decades, the need for advanced systems with good precision, low cost, and high-time response for wildfires and smoke detection and monitoring has become an absolute necessity. In this paper, we propose a novel, fast, and autonomous approach for denoising and tracking smoke in video sequences captured from a camera in motion. The proposed method is based mainly on two stages: the first one is a reconstruction and denoising path with a novel lightweight convolutional autoencoder architecture. The second stage is a specific scheme designated for smoke tracking, and it consists of the following: first, the foreground frames are extracted with the HSV color model and textural features of smoke; second, possible false detections of smoke regions are eliminated with image processing technique and last smoke contours detection is performed with an adaptive nonlinear level set. The obtained experimental results exposed in this paper show the potential of the proposed approach and prove its efficiency in smoke video denoising and tracking with a minimized number of false negative regions and good detection rates.

Technique based on the grayscale value for evaluating the shielding performance of infrared smokescreen

“…Ghali and Akhloufi 27 introduced a novel deep learning method, namely, BoucaNet, for recognizing smoke on satellite images, which achieved high performance. Daoudi et al 28 proposed an autonomous approach based on a novel lightweight convolutional autoencoder architecture for denoising and tracking smoke in video sequences captured from a camera in motion. Leonardo et al 29 proposed an approach based on using an instance segmentation algorithm to obtain the shape, color, and spectral features of the smoke, and an ensemble of machine learning algorithms was then used to further identify smoke.…”