No abstract

Handcraft features are commonly used for signal classification, which is a time-consuming feature engineering. In order to develop a general and robust feature learning method for radio signals, a novel One-dimensional Deep Attention Convolution Network (ODACN) is proposed to automatically extract discriminative features and classify various kinds of signals. First, one-dimensional (1-D) sparse filters are designed to learn hierarchical features of raw signals. Second, an attention layer is constructed to weight and assemble feature maps, to derive more context-relevant representation. By using simple 1-D filtering, ODACN is characteristic of less parameters and lower computation complexity than traditional Convolutional Neural Networks (CNNs). Moreover, feature attention can mimic a succession of partial glimpses of humans and focus on context parts of signals, thus helps in recognizing signals even at low Signal-to-Noise Ratio (SNR). Some experiments are taken to classify 31 kinds of signals with different modulation and channel coding types, and the results show that ODACN can achieve accurate classification of very similar signals, without any prior knowledge and manual operation.

We present UWSPSM, an algorithm of uncertainty weighted stereopsis pose solution method based on the projection vector which to solve the problem of pose estimation for stereo vision measurement system based on feature points. Firstly, we use a covariance matrix to represent the direction uncertainty of feature points, and utilize projection matrix to integrate the direction uncertainty of feature points into stereo-vision pose estimation. Then, the optimal translation vector is solved based on the projection vector of feature points, as well the depth is updated by the projection vector of feature points. In the absolute azimuth solution stage, the singular value decomposition algorithm is used to calculate the relative attitude matrix, and the above two stages are iteratively performed until the result converges. Finally, the convergence of the proposed algorithm is proved, from the theoretical point of view, by the global convergence theorem. Expanded into stereo-vision, the fixed relationship constraint between cameras is introduced into the stereoscopic pose estimation, so that only one pose parameter of the two images captured is optimized in the iterative process, and the two cameras are better bound as a camera, it can improve accuracy and efficiency while enhancing measurement reliability. The experimental results show that the proposed pose estimation algorithm can converge quickly, has high-precision and good robustness, and can tolerate different degrees of error uncertainty. So, it has useful practical application prospects.

The images always are corrupted by noises, which filter and other methods, which based on the mean filter, work have a bad influence on the subsequently processing. There are best with the Gaussian noise. In all kinds of the methods, the various types of filters developed to reduce noises. But Wiener filter, the Gaussian filter and the wavelet soft unfortunately, there are no any kinds of filters, which are perfect threshing filter are more popular de-noising methods in for de-noise in any cases. We try our best to resolve this problem, removing Gaussian noise [4] and design a novel filter based on the grey relational analysisIn recent years, many new theories are applied successful (GRA). The flag matrix, which marks the type of every pixel, can .. v v l l be obtained by using GRA between the two sequences in four in the image processing, such as grey system theory, the rough operators. The noise pixel is removed by the mean of the 3 by 3 sets theory, the mathematical morphology and partial window, and non-noise pixel is kept its intensity value. We put an differential equation etc. The application of the new theories emphasis on removing the Gaussian noise, and compare the three gives an opportunity for find new method to remove noise. more popular filters with our new filter. We also study the effect The aim of our research is to find a new removing noise on removing the salt and pepper noise. The results show that the method based on grey system theory, which is more robust approach cannot only remove the Gaussian noise in infrared than the popular de-noising methods. In this paper, we present image or visible light image, but also the non-Gaussian noise, a . such as salt and pepper noise. In all cases, our new filter gives a noel methodat rmvthnis imAge which ba e improved results when compared to some more popular degrey relationA analysis (rA)eAcrdn the noising methods.application of the GRA in image processing [5][6][7], the noise pixels and non-noise pixels can be flagged respectively. Then

No abstract