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.
For hyperspectral data classification, feature reduction techniques have become an apparent need to extract information from original data. In this paper, we introduce Locality Sensitive Discriminant Analysis (LSDA) to perform feature reduction for classification of hyperspectral imagery. By preserving both the discriminant and local geometrical structure in the data, the proposed method can obtain...
Channel interference factor for the identification result is prevalent among the existing speaker recognition algorithms. In order to improve the accuracy of the algorithm, the paper utilizes the technique of latent factor analysis(LFA) to deal with the channel factors in the speaker's Gaussian Mixture Model(GMM). In the endpoint detection phase of speaker recognition, the algorithm introduces the...
A sensitivity analysis is developed for a direction of arrival (DOA) based source localization method in an Underwater Wireless Sensor Array Networks (UWSAN). It is assumed that each sensor array in a UWSAN will yield an estimate of directions of arrival of underwater acoustic sources (DOAs). By collecting all DOAs in a fusion center, a least square estimate of the location of each target may be obtained...
The paper discusses a kernel RX algorithm for hyperspectral target detection. Because it is difficult to estimate the covariance matrix accurately for background areas, directly using the RX Algorithm for hyperspectral target detection is not a good choice in many cases. Therefore, we apply a kernel RX algorithm to our application. The kernel RX algorithm has good nonlinear anomaly detection ability...
When there are serious occlusion and illumination change, Probabilistic Occupancy Map (POM) algorithm can track six more people simultaneously with multiple video streams. The output result of foreground detection will be the available input data in POM algorithm, so the performance of a foreground detection algorithm is very important for the entire POM algorithm. Presently, Gaussian mixture model...
We focus on the problem of compressive sampling of Linear Frequency Modulation(LFM) signal via Matching Pursuit. We designed an adaptive matching pursuit algorithm through dynamic dictionary optimization. Results from the sparse property of LFM under Chirplet Basis, we use Chirplet atom to generate dictionary. Then by feeding the information of signal back into dictionary generating process, the grid...
In order to simplify the dense data of point cloud efficiently, this paper proposes an algorithm which is quick and easy to simplify the point cloud based on the standard deviation of the normal vector. First of all, the normal distribution have to be calculated after getting the dense point cloud data which has been down sampled. Second of all, calculate the separation threshold value between the...
Hyperspectral image classification is an important part of the hyperspectral remote sensing information processing. The Iterative Selforganizing Data Analysis Techniques Algorithm (ISODATA) clustering algorithm which is an unsupervised classification algorithm is considered as an effective measure in the area of processing hyperspectral images. In this paper, an improved ISODATA algorithm is proposed...
Image encryption is a hotspot of multimedia security. Many researchers adopted chaotic systems as pseudo-random number generators in image encryptions considering the properties of high sensitivity, large periodicity, low computation cost. Unpredictable, and etc. However, there is no deterministic approach to prove whether the way of using chaotic systems in an image encryption algorithm is secure...
Techniques used in text steganography are more difficult to develop, since there is less redundancy in text than other media, such as image, video and audio. A text hiding method using multiple-base encoding is proposed. The occurrence number of each word is counted and sorted in descending order, which is set as a base in the multiple-base notation system. Those unrepeated words are treated as a...
Nowadays, image enhancement, image restoration and dehazing had made a great progress. This paper addresses the problem of dehazing which is a serious question in computer vision and consumer photography applications. Due to the weakness of the existing methods to compute an accurate transmission map, we use the binocular vision method to compute the depth map. We have used in this paper, the discrepancy...
Compressed sensing is a topic that has recently gained much attention in high-speed underwater acoustic (UWA) communications. Combined the MIMO communication system with OFDM technology, they can realize high-speed data communication over UWA channels and overcome the fading problem efficiently. In this paper performance analysis of compressed sensing (CS) channel estimation algorithms for underwater...
For the modulation identification problem of CDMA2000 1x EV-DO Rev.A reverse data channel in low SNR, this paper proposes a joint identification algorithm based on singular value decomposition and cluster analysis. The algorithm identifies a part of the modulation types by the relation between the spread spectrum period and modulation types. Firstly, the algorithm estimates the spread spectrum period...
Generating region outlines from grayscale images using contour generation algorithms is one of the basic methods for image segmentation. The results can be used in 3D reconstruction from contours. The algorithm proposed in this paper which uses templates can effectively deal with the cases when contours pass through grid points and reach image boundaries.
Stable local feature detection and representation are the fundamental components of target recognition and image retrieval. The traditional SIFT algorithm's descriptor of the feature points is a 128-element vector, and a lot of redundant information is presence. So the brief and effective expression of the image feature information is the key to improve the performance of the algorithm. This paper...
This paper presents an image mosaic technique using ORB (oriented FAST and rotated BRIEF) descriptor and an improved blending algorithm. Features of images with overlapping regions are first described by ORB descriptors. This binary descriptor outperforms SIFT and SURF in regard of processing speed. RANSAC algorithm is then applied to reject mismatches. Once the best projective deformation matrix...
In the context of stereo matching remaining a classical problem in computer vision, this paper presents a novel stereo matching algorithm based on ground control points using graph cut (GC). The proposed algorithm incorporates local and global stereo methods, initializes the disparity map with a local stereo approach in the first place on purpose of selecting GCPs (Ground Control Points), and applies...
This paper introduces the fundamental knowledge of compressed sensing theory, and analyzes the important reconstruction algorithms such as orthogonal matching pursuit, subspace pursuit, but we should know the sparse degree. The sparsity adaptive matching pursuit algorithm can be terminated by setting the conditions to make adaptive sparse degree. This paper puts forward a modified sparsity adaptive...
Least Square (LS) estimation is a simple but not good enough for localization method which is widely used for target position estimation. The time difference of arrival (TDOA) location based on LS method needs to select a reference sensor to obtain a series of equations. Thus, the measured error of the selected first sensor will certainly influence the location accuracy. In our article, an algorithm...
A new soft-value bit-flipping low-density parity-check (LDPC) decoding is proposed based on a simplified reliability ratio based on weighted bit-flipping (RRWBF) algorithm. Moreover, we design a soft-output demapping and soft-decision decoding for the LDPC code in China Mobile Multimedia Broadcasting (CMMB). In addition, the complexity of decoding and the consumption of hardware is reduced effectively...
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.