This paper deals with the problem of source separation in the case when the observations result from a multiple-input multiple-output convolutive mixing system. In a blind framework, higher order contrast functions have been proved to be efficient for extracting sources. Inspired by a semiblind approach, we propose new contrast functions for blind signal separation that make use of reference signals. The main advantage of this approach consists in the quadratic form of these criteria: the extraction of one source hence reduces to a simple optimization task for which fast and efficient algorithms are available. The separation of the other sources from the mixture is then carried out by an iterative deflation method. Furthermore, these contrasts are shown to be valid for both independent identically distributed (i.i.d.) and non-i.i.d. source signals. The performance offered by these criteria is investigated through simulations: they appear as very appealing tools compared with some classical contrast functions

Smoke detection plays an important role in forest safety warning systems and fire prevention. Complicated changes in the shape, texture, and color of smoke remain a substantial challenge to identify smoke in a given image. In this paper, a new algorithm using the deep belief network (DBN) is designed for smoke detection. Unlike popular deep convolutional networks (e.g., Alex-Net, VGG-Net, Res-Net, Dense-Net, and the denoising convolution neural network (DNCNN), specifically devoted to detecting smoke), our proposed end-to-end network is mainly based on DBN. Indeed, most traditional smoke detection algorithms follow the pattern recognition process which consists basically feature extraction and classification. After extracting the candidate regions, the main idea is to perform both smoke recognition and smoke-no-smoke region classification using static and dynamic smoke characteristics. However, manual smoke detection cannot meet the requirements of a high smoke detection rate and has a long processing time. The convolutional neural network (CNN)-based smoke detection methods are significantly slower due to the maxpooling operation. In addition, the training phase can take a lot of time if the computer is not equipped with a powerful graphics processing unit (GPU). Thus, the contribution of this work is the development of a preprocessing step including a new combination of features—smoke color, smoke motion, and energy—to extract the regions of interest which are inserted within a simple architecture with the deep belief network (DBN). Our proposed method is able to classify and localize reliably the smoke regions providing an interesting computation time and improved performance metrics. First, the Gaussian mixture model (GMM) is employed to capture the frames containing a large amount of motion. After applying RGB rules to smoke pixels and analyzing the energy attitude of smoke regions, extracted features are then used to feed a DBN for classification. Experimental results conducted on the publicly available smoke detection database confirm that the DBN has reached a high detection rate that exceeded an average of 96% when tested on different videos containing smoke-like objects, which make smoke recognition more challenging. The proposed methodology provided high detection ratios and low false alarms, and guaranteed robustness verified by evaluations of accuracy, F1-score, and recall for noisy and non-noisy images with and without noise.

The paper deals with the problem of blind source extraction from a multiple-input/multiple-output (MIMO) convolutive mixture. We define a new criterion for source extraction which uses higher-order contrast functions based on so called reference signals. It generalizes existing reference-based contrasts. In order to optimize the new criterion, we propose a general algebraic algorithm based on best rank-1 tensor approximation. Computer simulations illustrate the good behavior and the interest of our algorithm in comparison with other approaches.