This paper presents a novel approach for automatic ECG delineation with focus on QT interval estimation, using an unsupervised learning algorithm. A three-dimensional feature space is created which uses the characteristics of ECG waveform at its inflection points. To this end, three features are introduced, including the Truncated Energy, which makes our method robust to baseline wandering and noise. Using the fact that the logarithm of features exhibits a mixture of four Gaussian distributions, each for one of the P wave, QRS complex, T wave and baseline, an unsupervised clustering algorithm based on Expectation Maximization is applied. The experimental results reveal that the proposed algorithm extracts the ECG waves accurately, even if they have a very low energy and amplitude. No pre-processing and windowing approach is required in the proposed method resulting in a significantly higher resolution and lower computational complexity in estimating the onset and offset of ECG waves. Furthermore, the proposed algorithm is robust to noise and baseline wandering, thanks to the Laplacian of Gaussian filter employed for inflection point detection.

In this paper, we introduce an algorithm for estimating and tracking the pitch period of audio signals using Bayesian filters. For this purpose, we propose a general Bayesian model, which is robust to the nonstationary variations of the amplitude and frequency of the input signal. We also employ a state-space model, which uses the delayed versions of the input signal to model the periodicity of nonstationary audio signals. This simple model allows a significant reduction of the required number of particles for the estimation of the pitch period compared to the state-of-the-art particle filtering methods. Moreover, we propose to estimate the logarithm of the period instead of the period itself. We show that the resulting algorithm does not require prior knowledge about the initial state and is robust to the octave error phenomenon, which is a common problem in pitch period estimation methods. Most of the existing methods require that the processing window be longer than the largest existing period of the input signal. In contrast, the proposed method does not impose such a limit. Our method often results in a higher time-domain resolution with no perceptible compromise on the frequency-domain resolution, especially for high-pitched audio signals such as music. Simulation results reveal that the proposed algorithm outperforms the state-of-the-art pitch period detection algorithms at low signal to noise ratios assuming no prior knowledge about the initial conditions.

This paper presents an algorithm for estimating the instantaneous fundamental frequency of a noisy non‐stationary periodic signal whose components are harmonically related. To this end, the authors’ propose a harmonic state‐space model for the input signal and use it to derive an extended Kalman filter (EKF), an unscented Kalman filter (UKF) and a particle filter (PF). In this model, the input signal is characterised by a time‐varying fundamental frequency and amplitude which is a practical assumption for real‐world periodic signals. In contrast to most of existing methods such as short‐time Fourier transform, the proposed algorithm does not use any windowing technique. Therefore the trade‐off between time and frequency resolutions is less controversial and so can be used for real‐time frequency tracking. It also reveals some fine and continuous variations in signal pitch such as Vibrato and Glissando. Simulation results show that the proposed algorithm performs well even when most of the signal energy is contained in the higher‐order harmonics. The performance of the proposed algorithm using EKF, UKF and PF is also evaluated and the results are compared in diverse conditions.

In this study, the problem of vehicle detection, tracking and speed estimation in the nighttime traffic surveillance videos captured in highly reflective environments is considered. In this case, a robust algorithm is proposed which uses vehicle headlights as their prominent features. The proposed algorithm consists of three main stages. In the first stage, bright objects are segmented by thresholding the grey‐scale image. An effective algorithm is then applied to distinguish between vehicles lights and lights reflected on the road and on the vehicles bodies. In the second stage, the segmented bright objects are tracked using their spatial characteristics and their shapes and then, their speeds are estimated. To correct the camera perspective effect and reduce computational complexity, a projective transformation is used. In the third stage, the lights of each vehicle are grouped and paired using their positions and speeds. Motorbikes are also identified among the unpaired lights in this stage. Finally, the proposed real‐time system is implemented in C and applied to videos captured by traffic surveillance cameras in some highways in Iran. Experimental results reveal that accuracy of the algorithm proposed for vehicle detection is more than 98%.