| 1. |
- Gustavsson, Jan-Olof, et al.
(författare)
-
A simultaneous maximum likelihood estimator based on a generalized matched filter
- 1994
-
Ingår i: ICASSP-94. - Piscataway, NJ : IEEE Communications Society. - 0780317750 ; , s. 481-484
-
Konferensbidrag (refereegranskat)abstract
- The paper discusses parameter estimation and detection in Laplace distributed noise. The received signal is modeled as r(·)=As(·,&thetas;)+n(·), where A is an unknown amplitude, &thetas; is the parameter vector to be estimated and n(·) is independent Laplace distributed noise. The simultaneous maximum likelihood estimator of (A,&thetas;) is derived. The derived estimator is based on a combination of a weighted median filter [Astola and Nuevo, 1992] and a generalized form of the ordinary matched filter [Gustavsson and Borjesson, 1992]. Examples of performance for four different detectors are given for a case of binary detection, when the amplitude A or the signal shape s(·,&thetas;) are varied. Simulations indicate that the performance of detectors based on the generalized matched filter is not particularly dependent on either the estimate of the amplitude A or the signal shape
|
|
| 2. |
- Westin, Carl-Fredrik, et al.
(författare)
-
On the Equivalence of Normalized Convolution and Normalized Differential Convolution, Vol. 5
- 1994
-
Ingår i: IEEE International Conference on Acoustics, Speech, and Signal Processing, 1994. - 0780317750 ; , s. 457-460
-
Konferensbidrag (refereegranskat)abstract
- This paper establishes an algebraic relation between two methods recently reported; normalized convolution and normalized differential convolution. These are general methods for filtering incomplete or uncertain data and are based on the separation of both data and operator into a signal part and a certainty part. General filtering can be performed without preprocessing input data with an interpolation step. The methods allow both data and operators to be scalars, vectors or tensors of higher order. Normalized differential convolution has been used in a wide range of applications. Examples are estimation of gradient estimation in irregularly sampled data, estimation of differential invariants in sparse image flow fields and image edge effect reduction. It was previously shown that normalized convolution produces a description of the neighbourhood which is optimal in a least square sense. The algebraic relation to normalized differential convolution presented in this paper proves that the latter method is also optimal in the same sense as well.
|
|
