The extended Kalman filter has been applied extensively to the tracking of non-maneuvering targets. Although the filter tracks these targets accurately, its computational burden is generally heavy. In this regard, several suboptimal filtering schemes have been proposed in the literature. In this paper, the authors point out some of the shortcomings of the Baheti filter and present modifications to arrive at a computationally more efficient algorithm with improved performance. The proposed filter is compared with several suboptimal Kalman filtering schemes which require less computational burden than the extended Kalman filter while yielding near optimal performance during both transient and steady state filtering. It is shown that these suboptimal filters are viable alternatives to the extended Kalman filter for target tracking. In addition, an off-line technique for decoupling of the filtering algorithms based upon the correlation coefficient analysis is included in this paper.

The accurate parametrization of the shapes within an image is a necessary requirement in many image processing applications including sorting, manufacturing, and quality control. As the adoption of image processing techniques increases, the need for accurate identification and definition of shapes and objects will undoubtedly increase. A technique is presented for the accurate determination of the parameters of circles and circular arcs within an image. The approach is based on an adaptation of L/sub 1/ estimation techniques.<>

The standard Kalman filter has been applied extensively to the tracking of nonmaneuvering targets. Although the filter tracks such targets accurately, it creates a heavy computational burden. A study is made of several suboptimal Kalman filtering schemes which require less computational effort than the standard Kalman filter while yielding nearly optimal performance during both transient and steady-state filtering. It is shown by simulation results and by analysis that the suboptimal filters are viable alternatives to the standard Kalman filter.< >

A tightly coupled multiple structure adaptive filtering technique that is amendable to real-time tracking of a maneuvering target is described. The procedure provides coherent offline segmentation of a hemisphere in three-dimensional space to yield decision regions, which are then utilized to select an appropriate filter structure. The purpose of using a multiple structure technique is to minimize the computational burden while maintaining tracking accuracy and stability

This paper presents a new technique, the authors have developed for curve fitting based on minimum absolute deviations. The developed technique is a non iterative technique which is easy and simple to apply. The computing time and the computer storage requirements are very small compared to the other available techniques, such as least square curve fitting technique and the standard LAV algorithm which uses linear programming (LP).