The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
To improve the accuracy of corner's detection in the traditional black and white chessboard, a new method based on multi-features is proposed. Three distinct local features of the corners have been analyzed, they are structural response, symmetric response and edge response. By selectively applying these features, initial selection and later screening of potential corners have been done. Non-maximum...
Traffic sign detection plays an important role in driving assistance systems and traffic safety. But the existing detection methods are usually limited to a predefined set of traffic signs. Therefore we propose a traffic sign detection algorithm based on deep Convolutional Neural Network (CNN) using Region Proposal Network(RPN) to detect all Chinese traffic sign. Firstly, a Chinese traffic sign dataset...
We present an efficient approach to lane and pedestrian detection by processing sequential images from a camera attached to a moving vehicle. The left and right lines of the current lane are detected by finding high intensity pixels along multiple horizontal scan lines and connecting the detected pixel points. Line positions are predicted by tracking in order to increase detection credibility while...
Falls have been a major health risk that diminishes the quality of life among the elderly. In this paper, we propose a new method using acceleration data and hidden Markov model (HMM) to detect fall events. A wearable device integrating a tri-axial accelerometer was used to collect acceleration data of human chest. Feature sequences (FSs) were extracted from the acceleration data and used as sequence...
A correctness analysis method of horizon detection result is present. Firstly, several small regions which take the points on the detected horizon as centers are selected equidistantly. Then gray variance, between-class variance and gradient information of each small region are calculated to judge whether it meets existence conditions of a horizon. Finally, the proportion of the number of the regions...
Error-Control Coding (ECC) now plays an important role in wireless transceivers because it helps to increase link reliability and lower required transmit power. One popular problem of ECC implementation is the trade-off between high coding-gain and decoder's complexity. In this paper, we propose a serial concatenated ECC solution which is a combination of truncated-iteration layered-decoding LDPC...
Compressed sensing, as a novel framework, needs a small amount of characteristic datas to reconstruct the original datas and breakthroughs the limitation of the Nyquist sampling law, which effectively relieves the pressure of dealing with a large amount of datas in the practical application. But the noise reduction performance in traditional compressed sensing is very poor, in order to improve the...
In this paper, we propose a new hierarchical modulation scheme for DVB-NGH to improve the performance of LP (Low-Parity) signals by applying a conventional constellation-rotation method to the LP signals with virtually no loss of performance in the HP (High-Parity) signals. The improvement of the LP signals is mainly due to the increased diversity gain caused by the constellation-rotation method which...
Speech recognition, as the man-machine interface, plays a very important role in the field of artificial intelligence. Traditional speech recognition methods are shallow learning structure, and have their limitations. This paper uses the Convolution Neural Networks (CNNs) to realize speech recognition. It is an alternative type of neural network that can reduce spectral variation and model spectral...
The display quality improvement of electrophoretic paper largely depends on the increase in the number of grayscale, but it will make drive mode design complicated. The inhibition of residual driving voltage also becomes more difficult. This paper presents a new 16 gray-scale driving schema based on the DC-balance principle, improve the display quality of electrophoretic display (EPD). The display...
Pattern matching algorithms are very important in both data mining and the intrusion detection system. Efficiency and accuracy BM algorithm for text matching is relatively high, but, when a large number of repeated and complex characters to match in the network, the efficiency will be lower. Aiming at BM algorithm's efficiency of matching is lower in the network environment, an improved algorithm...
Identification and mitigation of ground clutter are crucial problems in radar meteorology because the ground-clutters contaminate radar echoes and mask weather echoes. In this paper, two algorithms, Spectral Stationary Echo Filter (SSEF) and the clutter mitigation decision (CMD), are introduced to address the contamination of ground clutter on radar products, and performances of them are tested with...
In this paper, a new probability density distribution, “the square Cauchy mixture distribution” is proposed for recognition of sound. The proposed density is based on the Cauchy distribution and modified so that it has mean and variance. Since the proposed density can be calculated using only simple arithmetic operations, it can be calculated faster than the Gaussian mixture model (GMM). In addition...
Visual Tracking is often hindered by difficulties such as occlusion, abrupt motion and out of view problems. Motivated by the wide range of existing features, search mechanisms and target representations, a cooperation strategy between Bayesian tracking and matching by the Binary Robust Invariant Scalable Key-points (BRISK) is devised in this paper. The Bayesian tracker is considered as the main tracker,...
Spectrum sensing is one of the main parts in cognitive radio. The performance of the adopted spectrum sensing method is very important. When the primary user and the cognitive radio are in operation simultaneously, performance of spectrum sensing is damaged. We propose to apply the linear prediction for the blind source separation algorithm as an alternative for more conventional techniques. Simulation...
Multiplier is a fundamental component for digital signal processing (DSP) applications and takes up the most part of the resource utilization, namely power and area. Approximate circuitry architectures have been studied as innovative paradigm for reducing resource utilization for DSP systems. In this paper, the 4:2 compressor based approximate multiplier architecture which uses both truncation and...
A novel technique of segmenting people for counting using adaptive thresholding has been proposed in this paper. The technique uses adaptive thresholding to detect and extract objects of interest and is based on the idea of counting people through a slit window. The technique works well for highly occluded crowded scenes in Masjid-e-Haram during Hajj and Umrah congregation. It is a very diverse problem...
One of the most used techniques for estimating the a priori SNR in many speech enhancement systems is the decision-directed (DD) approach, which is famous for the good performance in reducing musical noise with low complexity calculation. However, the conventional DD approach with fixed smoothing factor suffers from the inherent tradeoff between speech distortion elimination and musical noise reduction...
Under the condition of low sample, how to improve the robustness of adaptive beamforming algorithm is a key problem in engineering application. This article first introduces the minimum variance distrtionless response. On the basis, the algorithm of diagonal loading has been researched and how to select the optimal loading value in the practical application has been emphatically analyzed. Finally,...
The use of the direct evaluation of the Gaussian Process, using the square exponential function kernel prediction at the given data points is often misleading towards evaluation of the fit, given by the coefficient of determination. The predicted value at the data points when using the Gaussian Process, is almost at all cases equal to the original value. As such, interpretation problems arise when...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.