| 1. |
- Granlund, Gösta
(författare)
-
The Complexity of Vision
- 1999
-
Ingår i: Signal Processing. - 0165-1684 .- 1872-7557. ; 74:1, s. 101-126
-
Tidskriftsartikel (refereegranskat)abstract
- There is no indication that it will ever be possible to find some simple trick that miraculously solves most problems in vision. It turns out that the processing system must be able to implement a model structure, the complexity of which is directly related to the structural complexity of the problem under consideration in the external world. It has become increasingly apparent that Vision cannot be treated in isolation from the response generation, because a very high degree of integration is required between different levels of percepts and corresponding response primitives. The response to be produced at a given instance is as much dependent upon the state of the system, as the percepts impinging upon the system. In addition, it has become apparent that many classical aspects of perception, such as geometry, probably do not belong to the percept domain of a Vision system, but to the response domain. This article will focus on what are considered crucial problems in Vision for robotics for the future, rather than on the classical solutions today. It will discuss hierarchical architectures for combination of percept and response primitives. It will discuss the concept of combined percept-response invariances as important structural elements for Vision. It will be maintained that learning is essential to obtain the necessary flexibility and adaptivity. In consequence, it will be argued that invariances for the purpose of Vision are not abstractly geometrical, but derived from the percept-response interaction with the environment. The issue of information representation becomes extremely important in distributed structures of the types foreseen, where uncertainty of information has to be stated for update of models and associated data. The question of object representation is central to the paper. Equivalence is established between the representations of response, geometry and time. Finally an integrated percept-response structure is proposed for flexible response control.
|
|
| 2. |
- Händel, Peter, 1962-, et al.
(författare)
-
Asymptotic noise gain of polynomial predictors
- 1997
-
Ingår i: Signal Processing. - 0165-1684 .- 1872-7557. ; 62:2, s. 247-250
-
Tidskriftsartikel (refereegranskat)abstract
- Finite impulse response filters for the prediction of polynomial signals are considered. An expression for the asymptotic noise gain (as the filter length increases without bound) is derived. It is shown that the asymptotic noise gain only depends on the polynomial order - in particular, it is independent of the prediction horizon. It is also shown that the noise gain forms a non-increasing sequence for increasing filter lengths. Numerical results that lend support to the theoretical findings are included.
|
|
| 3. |
- Händel, Peter, 1962-, et al.
(författare)
-
Performance analysis of a correlation based single tone frequency estimator
- 1995
-
Ingår i: Signal Processing. - 0165-1684 .- 1872-7557. ; 44:2, s. 223-231
-
Tidskriftsartikel (refereegranskat)abstract
- This paper analyzes the frequency error variance of a low complexity single tone frequency estimator based on sample correlations of the input data. In the high SNR scenario it is analytically shown that the accuracy of a properly tuned algorithm is nearly optimal, i.e. nearly attains the Cramer-Rao lower bound. For low SNR the statistical efficiency of the algorithm is degraded, but it is analytically proven that for a large number of samples the error variance attains the lower bound for this class of estimators.
|
|
| 4. |
- Jansson, Magnus, et al.
(författare)
-
A Linear Regression Approach to State-Space Subspace System Identification
- 1996
-
Ingår i: Signal Processing. - : Elsevier. - 0165-1684 .- 1872-7557. ; 52:2, s. 103-129
-
Tidskriftsartikel (refereegranskat)abstract
- Recently, state-space subspace system identification (4SID) has been suggested as an alternative to the more traditional prediction error system identification. The aim of this paper is to analyze the connections between these two different approaches to system identification. The conclusion is that 4SID can be viewed as a linear regression multistep-ahead prediction error method with certain rank constraints. This allows us to describe 4SID methods within the standard framework of system identification and linear regression estimation. For example, this observation is used to compare different cost-functions which occur rather implicitly in the ordinary framework of 4SID. From the cost-functions, estimates of the extended observability matrix are derived and related to previous work. Based on the estimates of the observability matrix, the asymptotic properties of two pole estimators, namely the shift invariance method and a weighted subspace fitting method, are analyzed. Expressions for the asymptotic variances of the pole estimation error are given. From these expressions, difficulties in choosing user-specified parameters are pointed out. Furthermore, it is found that a row-weighting in the subspace estimation step does not affect the pole estimation error asymptotically.
|
|
| 5. |
- Jansson, Magnus, et al.
(författare)
-
Forward-Only and Forward-Backward Sample Covariances – A Comparative Study
- 1999
-
Ingår i: Signal Processing. - 0165-1684. ; 77:3, s. 235-245
-
Tidskriftsartikel (refereegranskat)abstract
- In some applications the covariance matrix of the observations enjoys a particular symmetry: it is not only symmetric with respect to its main diagonal but also with respect to the anti-diagonal. The standard forward-only sample covariance estimate does not impose this extra symmetry. In such cases one often uses the so-called forward-backward sample covariance estimate. In this paper, a direct comparative study of the relative accuracy of the two sample covariance estimates is performed. An explicit expression for the difference between the estimation error covariance matrices of the two sample covariance estimates is given. This expression shows quantitatively the gain of using the forward-backward estimate compared to the forward-only estimate. The presented results are also useful in the analysis of estimators based on either of the two sample covariances. As an example, spatial power estimation by means of the Capon method is considered. Using a second-order approximation, it is shown that Capon based on the forward-only sample covariance (F-Capon) underestimates the power spectrum, and also that the bias for Capon based on the forward-backward sample covariance is half that of F-Capon.
|
|
| 6. |
- Kristensson, Martin, et al.
(författare)
-
Modified IQML and Weighted Subspace Fitting without Eigendecomposition
- 1999
-
Ingår i: Signal Processing. - : Elsevier North-Holland, Inc. Amsterdam, The Netherlands. - 0165-1684. ; 79:1, s. 29-44
-
Tidskriftsartikel (refereegranskat)abstract
- This paper deals with direction estimation of signals impinging on a uniform linear sensor array. A well-known algorithm for this problem is IQML. However, estimates computed with IQML are in general biased, especially in noisy scenarios. We propose a modification of IQML (MIQML) that gives consistent estimates at approximately the same computational cost. In addition, an algorithm (WSF-E) with an estimation error covariance which is asymptotically identical to the asymptotic Cramér–Rao lower bound is presented. The WSF-E algorithm resembles weighted subspace fitting (WSF) or MODE, but achieves optimal performance without having to compute an eigendecomposition of the sample covariance matrix.
|
|
| 7. |
- Ljung, Lennart, 1946-, et al.
(författare)
-
Subspace Identification from Closed Loop Data
- 1996
-
Ingår i: Signal Processing. - : Elsevier BV. - 0165-1684 .- 1872-7557. ; 52:2, s. 209-215
-
Tidskriftsartikel (refereegranskat)abstract
- The so-called subspace methods for direct identification of linear models in state space form have drawn considerable interest recently. They have been found to work well in many cases but have one drawback — they do not yield consistent estimates for data collected under output feedback. The present paper points to the reasons for this. We stress how the basic idea is to focus on the estimation of the state-variable candidates — the k-step ahead output predictors. By recomputing these from a ‘non-parametric’ (or, rather, high order ARX) one-step ahead predictor model, closed loop data can be handled.
|
|
| 8. |
- Stoica, Petre, et al.
(författare)
-
The evil of superefficiency
- 1996
-
Ingår i: Signal Processing. - 0165-1684 .- 1872-7557. ; 55:1, s. 133-136
-
Tidskriftsartikel (refereegranskat)abstract
- We discuss the intriguing notion of statistical superefficiency in a straightforward manner with a minimum of formality. We point out that for any given parameter estimator there exist other estimators which have a strictly lower asymptotic variance and hence are statistically more efficient than the former. In particular, if the former estimator was statistically efficient (in the sense that its asymptotic variance was equal to the Cramer-Rao bound) then the latter estimators could be called ''superefficient''. Among others, the phenomenon of superefficiency implies that asymptotically there exists no uniformly minimum-variance parameter estimator.
|
|
| 9. |
- Tichavsky, P., et al.
(författare)
-
Recursive estimation of frequencies and frequency rates of multiple cisoids in noise
- 1997
-
Ingår i: Signal Processing. - 0165-1684 .- 1872-7557. ; 58:2, s. 117-129
-
Tidskriftsartikel (refereegranskat)abstract
- A recursive algorithm for simultaneous estimation and tracking of instantaneous frequencies and instantaneous frequency rates-of-change for signals that consist of multiple narrow-band components in noise is proposed and studied. The algorithm recursively separates the signal to individual components and uses estimated phase differences for updating the instantaneous frequency and frequency rate of each component. The main advantages of the proposed algorithm over frequencies-only tracking algorithms known in literature include the zero asymptotic bias (zero tracking delay) in estimating of the instantaneous frequencies of linear FM (chirp) signals and more accurate tracking of frequencies that cross each other. Performance of the algorithm is studied by means of a linear filter approximation technique and derived results are compared with the appropriate (posterior) Cramer-Rao bound. Superior performance of the algorithm is illustrated by computer simulations.
|
|
| 10. |
- Trump, Tõnu, et al.
(författare)
-
Estimation of Nominal Direction of Arrival and Angular Spread Using an Array of Sensors
- 1996
-
Ingår i: Signal Processing. - : Elsevier BV. - 0165-1684 .- 1872-7557. ; 50:1-2, s. 57-69
-
Tidskriftsartikel (refereegranskat)abstract
- The problem of estimating the nominal direction of arrival and angular spread of a source surrounded by a large number of local scatterers using an array of sensors is addressed. This type of propagation occurs frequently in, for example, mobile communications. The maximum likelihood estimator is considered and two computationally less complex estimators are also proposed. They are based on least-squares fits of the sample covariance to the theoretical covariance matrix derived from the measurement model. The performance of the least-squares-based algorithm is analyzed and based on this, an optimally weighted least-squares criterion is proposed. The weighted least-squares algorithm is shown to be asymptotically efficient. Results of numerical experiments are presented to indicate small sample behavior of the estimators. The nominal direction-of-arrival (DOA) estimates are compared with those provided by a standard subspace algorithm. Finally, the methods are applied to experimental array data to determine spread angles for non line of sight scenarios.
|
|
