In this paper, we present an unsupervised change detection approach that combines pixel-based local Haar-like features, color information, vegetation index, and man-made structure features using fuzzy logic rules to p...
详细信息
In this paper, we present an unsupervised change detection approach that combines pixel-based local Haar-like features, color information, vegetation index, and man-made structure features using fuzzy logic rules to provide multi-level change detection results. An illumination invariant descriptor for each pixel is introduced to describe a Haar-like feature in a local area. Hue is used as a color feature in our change detection method. For the purpose of enhancing the change area with man-made structures, we de-weight the level of detected change areas where there are no man-made objects. The comparison of all features is done separately and the decision results are then combined under seven fuzzy logic rules to provide multi-level change detection results. The performance of the change detection is evaluated qualitatively by visual inspection and quantitatively using ground truth. The quantitative test results show that more than 90% of changes are correctly detected.
Operation of instantaneous power theory (PQ) is effective in symmetric systems and has proved to yield erroneous results with asymmetric sources. Synchronous detection algorithm (SDA) distributing averaged equal power...
详细信息
Operation of instantaneous power theory (PQ) is effective in symmetric systems and has proved to yield erroneous results with asymmetric sources. Synchronous detection algorithm (SDA) distributing averaged equal power among each phase has eliminated the drawbacks in the former. Further improvements with modified synchronous detection algorithm (MSDA) simulation were carried for distorted three phase voltage source brings further suppression in source current THDs has been presented in this paper.
With the current development of astronomical instruments able to detect the direct light of exoplanets, such as the very large telescope instrument SPHERE, statistical tools need to be developed in order to make preci...
详细信息
With the current development of astronomical instruments able to detect the direct light of exoplanets, such as the very large telescope instrument SPHERE, statistical tools need to be developed in order to make precise detection and estimation assessments. We propose a detection algorithm that delivers an estimation of the position and the intensity of the potentially detected exoplanet. Because of the numerical constraints on the signal processing task, the detector- estimator is based on a simplified Gaussian model where we use a field-rotation effect as the main discriminating criterium between the planet and the speckles. However, for a given threshold on the statistics test, the probability of false alarm (PFA) and the probability of detection (PD) need to be accurate. For that purpose we use a more realistic model and the saddlepoint approximation to compute the PFA and PD. The performance of the approximation is evaluated on a ID data model.
In this paper, a novel Bayesian peak detection algorithm is proposed for peptide peak detection in high resolution prOTOFtrade MALDI Mass Spectrometry(MS) data. A nonlinear parametric model is proposed for modeling th...
详细信息
In this paper, a novel Bayesian peak detection algorithm is proposed for peptide peak detection in high resolution prOTOFtrade MALDI Mass Spectrometry(MS) data. A nonlinear parametric model is proposed for modeling the peptide signals, chemical noise, and thermal noise. A metropolized Gibbs sampling algorithm is derived for Bayesian peak detection. The proposed algorithm is compared with a popular wavelet-based algorithm and the results show a significant improvement in performance on simulated data. The algorithm is finally tested on real MS MALDI data and the results agree with visual inspection very well.
Orthogonal frequency division multiplexing convolutional multi-code multiplexing (OFDM-CMM) has been proposed to achieve notable coding gain and diversity without loss of spectral efficiency. However, the complexity o...
详细信息
Orthogonal frequency division multiplexing convolutional multi-code multiplexing (OFDM-CMM) has been proposed to achieve notable coding gain and diversity without loss of spectral efficiency. However, the complexity of maximum likelihood sequence estimation (MLSE) grows exponentially in the number of parallel streams. This detection algorithm is prohibitive when the number of parallel streams is large. The interference cancellation based sequence detection (ICSD) is proposed in this paper to reduce the detection complexity without performance loss. The heart of this method is to combine the interference cancellation and the MLSE into one iteration. The complexity of ICSD grows linearly in the number of parallel streams. The simulation results have shown that the proposed method can efficiently approximate the optimum MAP performance at a moderate signal to noise ratio (SNR) in coded OFDM-CMM systems.
The Bayesian Aerosol Release Detector (BARD) is a system designed to detect and characterize disease outbreaks caused by aerosol releases of B. anthracis. The detection algorithm of BARD requires, among other things, ...
详细信息
The Bayesian Aerosol Release Detector (BARD) is a system designed to detect and characterize disease outbreaks caused by aerosol releases of B. anthracis. The detection algorithm of BARD requires, among other things, an accurate estimation of the number of spores that would be inhaled under a specific release scenario. This is a challenging problem, in part due to the lack of fine-grained data on the mobility patterns of the exposed population. Indeed, the only type of spatial information routinely contained in biosurveillance databases is the residential administrative unit-such as the home zip code-of each case. The current version of BARD detector deals with this challenge by making the simplifying assumption that exposure to anthrax would occur at onepsilas residential unit. This paper presents an experimental study to assess how BARDpsilas performance would be impacted by incorporation of a commuting model in outbreak simulation. Our results show that incorporation of commuting in simulation leads to statistically and practically significant changes in BARDpsilas detection and characterization performance.
Every year, many pedestrians are killed or seriously injured due to car accidents. A pedestrian recognition and warning system could save lives by warning the driver about a possible pedestrian hazard. Although signif...
详细信息
Every year, many pedestrians are killed or seriously injured due to car accidents. A pedestrian recognition and warning system could save lives by warning the driver about a possible pedestrian hazard. Although significant progress in research for such systems has been reported, these systems are yet to be implemented in vehicles. In this paper, we review some major pedestrian detection systems and identify the challenges that a real-time pedestrian recognition system has to overcome. We also discuss some positive experimental results using a modified pedestrian detection algorithm that is suitable for implementation on a Field Programmable Gate Array (FPGA) platform.
In this paper, we propose one grouped-iterative framework to generate a family of the MIMO detection algorithms. The presented framework not only includes the conventional iterative, grouped, and Chase detection algor...
详细信息
In this paper, we propose one grouped-iterative framework to generate a family of the MIMO detection algorithms. The presented framework not only includes the conventional iterative, grouped, and Chase detection algorithms, but also derives a new low-complexity MIMO detection algorithm. The proposed detection can adjust some parameters to achieve a range of trade-offs between performance and complexity. In (4,4) system with uncoded 16-QAM inputs, one instance of the proposed detection algorithm not only substantially reduces the multiplication complexity by 26.3% but also outperforms the BODF algorithm about 5 dB. Another instance of the proposed algorithm can save multiplication complexity by 34% at the penalty of 1 dB loss compared with the B-Chase detector.
The automatic lane marking detection, vehicle detection and incident detection systems are proposed in this paper. The block-based background extraction that combines statistical algorithm and the moving block informa...
详细信息
The automatic lane marking detection, vehicle detection and incident detection systems are proposed in this paper. The block-based background extraction that combines statistical algorithm and the moving block information is used to obtain the color background image more exactly. The lane detection algorithm is applied to obtain the lane information from the color background image without the limitation of the camera setting. The presented vehicle detection algorithm is a block-based approach which is widely used in highway systems, urban roadways or tunnels. Different applications adopt the different detection zones where the vehicles will be tracked and identified in. The presented incident detection algorithm focuses on the car stopped, vehicle lane changing, and congestion condition, and the experimental results in Hsueh-Shan tunnel are addressed, which also demonstrate the stability and the effectiveness of the proposed methods.
Chinese segmentation is an important issue inChinese text *** traditional segmentationmethods those depend on an existing dictionary sufferthe drawbacks when encounter unknown *** proposed a segmenting algorithm for C...
详细信息
Chinese segmentation is an important issue inChinese text *** traditional segmentationmethods those depend on an existing dictionary sufferthe drawbacks when encounter unknown *** proposed a segmenting algorithm for Chinesebased on extracting local context *** addedthe context information of the testing text into the localPPM statistical model so as to guide the detection ofnew *** algorithm focusing on the process ofonline segmentation and new word detection achievesa good effect in the close or opening test,andoutperforms some well-known Chinese segmentationsystem to a certain extent.
暂无评论