“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

System Identification I

Thank you for reading statistical signal processing detection estimation and time series analysis. Maybe you have knowledge that, people have look hundreds times for their chosen novels like this statistical signal processing detection estimation and time series analysis, but end up in harmful downloads. Rather than reading a good book with a cup of tea in the afternoon, instead they juggled with some malicious bugs inside their laptop.

Statistical Signal Processing Detection Estimation And Time Series Analysis

This paper is devoted to the maximum likelihood estimation of multiple sources in the presence of unknown noise. With the spatial noise covariance modeled as a function of certain unknown parameters, e.g., an autoregressive (AR) model, a direct and systematic way is developed to find the exact maximum likelihood (ML) estimates of all parameters associated with the direction finding problem, including the direction-of-arrival (DOA) angles /spl Theta/, the noise parameters /spl alpha/, the signal covariance /spl Phi//sub s/, and the noise power /spl sigma//sup 2/. We show that the estimates of the linear part of the parameter set /spl Phi//sub s/ and /spl sigma//sup 2/ can be separated from the nonlinear parts /spl Theta/ and /spl alpha/. Thus, the estimates of /spl Phi//sub s/ and /spl sigma//sup 2/ become explicit functions of /spl Theta/ and /spl alpha/. This results in a significant reduction in the dimensionality of the nonlinear optimization problem. Asymptotic analysis is performed on the estimates of /spl Theta/ and /spl alpha/, and compact formulas are obtained for the Cramer-Rao bounds (CRB's). Finally, a Newton-type algorithm is designed to solve the nonlinear optimization problem, and simulations show that the asymptotic CRB agrees well with the results from Monte Carlo trials, even for small numbers of snapshots. >

Maximum likehood DOA estimation and asymptotic Cramer-Rao bounds for additive unknown colored noise

We propose a new subspace-based localization of far-field (FF) and near-field (NF) narrowband signals (LOFNS) without eigendecomposition impinging on a symmetrical uniform linear array, where the oblique projection operator is utilized to isolate the NF signals from the FF ones, and the procedures of computationally burdensome eigendecomposition are not required in the estimation of the NF and FF location parameters and the computation of oblique projection operator. As a measure against the impact of finite array data, an alternating iterative scheme is presented to improve the estimation accuracy of the oblique projection operator and, hence, that of the NF location parameters, where the “saturation behavior” encountered in most of localization methods is overcome. Furthermore, the statistical analysis of the proposed LOFNS is studied, and the asymptotic mean-squared-error expressions of the estimation errors are derived for the FF and NF location parameters. Finally, the effectiveness and the theoretical analysis of the proposed LOFNS are substantiated through numerical examples, and the simulation results demonstrate that the LOFNS provides remarkable and satisfactory estimation performance for both the NF and FF signals compared with some existing localization methods even with eigendecomposition.

Subspace-Based Localization of Far-Field and Near-Field Signals Without Eigendecomposition

This paper investigates the localization of multiple near-field narrowband sources with a symmetric uniform linear array, and a new linear prediction approach based on the truncated singular value decomposition (LPATS) is proposed by taking an advantage of the anti-diagonal elements of the noiseless array covariance matrix. However, when the number of array snapshots is not sufficiently large enough, the “saturation behavior” is usually encountered in most of the existing localization methods for the near-field sources, where the estimation errors of the estimated directions-of-arrival (DOAs) and ranges cannot decrease with the signal-to-noise ratio. In this paper, an oblique projection based alternating iterative scheme is presented to improve the accuracy of the estimated location parameters. Furthermore, the statistical analysis of the proposed LPATS is studied, and the asymptotic mean-square-error expressions of the estimation errors are derived for the DOAs and ranges. The effectiveness and the theoretical analysis of the proposed LPATS are verified through numerical examples, and the simulation results show that the LPATS provides good estimation performance for both the DOAs and ranges compared to some existing methods.

Localization of Near-Field Sources Based on Linear Prediction and Oblique Projection Operator

Visual place recognition is a challenging task for applications such as autonomous driving navigation and mobile robot localization. Distracting elements presenting in complex scenes often lead to deviations in the perception of visual place. To address this problem, it is crucial to integrate information from only task-relevant regions into image representations. In this paper, we introduce a novel holistic place recognition model, TransVPR, based on vision Transformers. It benefits from the desirable property of the self-attention operation in Transformers which can naturally aggregate task-relevant features. Attentions from multiple levels of the Transformer, which focus on different regions of interest, are further combined to generate a global image representation. In addition, the output tokens from Transformer layers filtered by the fused attention mask are considered as key-patch descriptors, which are used to perform spatial matching to re-rank the candidates retrieved by the global image features. The whole model allows end-to-end training with a single objective and image-level supervision. TransVPR achieves state-of-the-art performance on several real-world benchmarks while maintaining low computational time and storage requirements.

TransVPR: Transformer-Based Place Recognition with Multi-Level Attention Aggregation

In this paper, we investigate the problems of estimating and tracking the location parameters [i.e., directions-of-arrival (DOAs) and ranges] of multiple near-field (NF) narrowband sources impinging on a symmetric uniform linear array, and a simple subspace-based algorithm for localization of NF sources (SALONS) is presented, where the computationally burdensome eigendecomposition and spectrum peak searching are avoided. In the SALONS, the DOAs and ranges are estimated separately with a one-dimensional subspace-based estimation technique, where the null spaces are obtained through the linear operation of the correlation matrices formed from the antidiagonal elements of the noiseless array covariance matrix, and the estimated DOAs and ranges are automatically paired without any additional procedure. Then the statistical analysis of the presented batch SALONS is studied, and the asymptotic mean-squared-error expressions of the estimated DOAs and ranges are derived. Furthermore, an online algorithm is developed for tracking the multiple moving NF sources with crossover points on their trajectories. The effectiveness and the theoretical analysis of the presented algorithms are verified through numerical examples, and the simulation results show that the proposed algorithms provide good estimation and tracking performance for DOAs and show satisfactory estimation and tracking performance for ranges.

Subspace-Based Algorithms for Localization and Tracking of Multiple Near-Field Sources

In this paper, we investigate the problem of estimating the directions-of-arrival (DOAs) and ranges of multiple narrowband near-field sources in unknown spatially nonuniform noise (spatially inhomogeneous temporary white noise) environment, which is usually encountered in many practical applications of sensor array processing. A new subspace-based localization of near-field sources (SLONS) is proposed by exploiting the advantages of a symmetric uniform linear sensor array and using Toeplitzation of the array correlations. Firstly three Toeplitz correlation matrices are constructed by using the anti-diagonal elements of the array covariance matrix, where the nonuniform variances of additive noises are reduced to a uniform one, and then the location parameters (i.e., the DOAs and ranges) of near-field sources can be estimated by using the MUSIC-like method, while a new pair-matching scheme is developed to associate the estimated DOAs and ranges. Additionally, an alternating iterative scheme is considered to improve the estimation accuracy of the location parameters by utilizing the oblique projection operator, where the “saturation behavior” caused by finite number of snapshots is overcome effectively. Furthermore, the closed-form stochastic Cramer-Rao lower bound (CRB) is also derived explicitly for the near-field sources in the additive unknown nonuniform noises. Finally, the effectiveness of the proposed method and the theoretical analysis are substantiated through numerical examples.

Weiliang Zuo

Papers

Subspace-Based Localization of Far-Field and Near-Field Signals Without Eigendecomposition

Localization of Near-Field Sources Based on Linear Prediction and Oblique Projection Operator

TransVPR: Transformer-Based Place Recognition with Multi-Level Attention Aggregation

Subspace-Based Algorithms for Localization and Tracking of Multiple Near-Field Sources

Subspace-Based Near-Field Source Localization in Unknown Spatially Nonuniform Noise Environment