In this paper, a DSP-Based of an oversampling adaptive noise canceller for background noise reduction using the Recursive Least Squares (RLS) algorithm on a Digital Signal Processor (DSP) is presented and its performance discussed. The implementation described seeks to improve the signal to background noise ratio for effective telephone communication in adverse non-stationary acoustic environments. Real-time experiments oversampling at 96 kHz were carried out on a DSP board (Texas Instruments TMS320C6713 DSK). Primary input signal to noise ratios from 0 dB to -10 dB were proposed for the cancelling performance tests. Results were analyzed in time and frequency domain. Also, a practical method based on the normalized performance function to objectively assess the adaptive noise canceller performance is presented. Mean Opinion Score (MOS) listening test along three dimensions following the ITU-T P.835 procedures were applied to subjectively assess the adaptive noise canceller output quality.
In this paper, we propose a portable device named SOMN_IA, to detect drowsiness and distraction in drivers. The SOMN_IA can be installed inside of any type of vehicle, and it operates in real time, alerting the dangerous state caused by drowsiness and/or distraction in the driver. The SOMN_IA contains three types of alarm: light alarm, sound alarm, and the transmission of information about the driver’s dangerous state to a third party if the driver does not correct his/her dangerous state. The SOMN_IA contains a face detector and a classifier based on the convolutional neural networks (CNN), and it aids in the management of consecutive information, including isolated error correction mechanisms. All of the algorithmic parts of the SOMN_IA are analyzed and adjusted to operate in real-time in a portable device with limited computational power and memory space. The SOMN_IA requires only a buck-type converter to connect to the car battery. The SONM_IA discriminates correctly between real drowsiness and normal blinking, as well as between real dangerous distraction and a driver’s normal attention to his/her right and left. Although the real performance of the SOMN_IA is superior to the CNN classification accuracy thanks to isolated error correction, we compare the CNN classification accuracy with the previous systems.
Este artículo propone un sistema biométrico usando imágenes estéreo que permite incrementar la seguridad de los sistemas de reconocimiento de rostros convencionales, al poder discriminar entre imágenes de rostro reales en 3D y falsificadas en 2D, empleando la información proporcionada por las imágenes estéreo. Una vez que el sistema determina que la imagen de entrada es un rostro real en 3D, cada imagen estéreo es caracterizada e independientemente procesada usando un método de extracción de características (EC) convencional. Seguidamente se emplea un método de fusión (MF) para combinar la información obtenida de ambas imágenes. Con el fin de determinar la combinación EC-MF más adecuada, se analizaron tres métodos de extracción de características y tres métodos de fusión. Los resultados experimentales obtenidos muestran que realizando la fusión de los datos extraídos mediante la transformación ondoleta discreta, antes de pasar a la etapa de clasificación, se obtienen los mejores resultados.