Results 261 to 270 of about 739,642 (309)

On target classification using kinematic data

Information Fusion, 2004
Abstract The use of kinematic measurements for target classification has been explored recently by several authors. This paper formulates the general framework for optimal Bayesian estimation of target state and class. Since target class is a non-evolutionary attribute, the solution is conceptually based on a static multiple-class filter.
Branko Ristic, Neil T Gordon
exaly   +2 more sources

Classification with probabilistic targets

2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2012
Modern robotic platforms, deployed for environmental monitoring and mapping, are able to rapidly accumulate large data sets. Whilst the data sets collected by these platforms are highly descriptive, they are often too large for human experts to analyse exhaustively.
Asher Bender   +2 more
openaire   +1 more source

The Influence of Target Orientation on the Underground Targets Classification

2019 IEEE 19th International Conference on Communication Technology (ICCT), 2019
Underground target detection and classification have been widely used in various fields. With the development of industrialization, The require for accurate classification of underground targets in various fields is becoming more and more urgent. The orientation of the underground targets are unknown and has an influence on the classification result ...
Shihong Duan   +5 more
openaire   +1 more source

Resource-Constrained Target Classification on Distant Aerial Targets

2021 17th International Conference on Distributed Computing in Sensor Systems (DCOSS), 2021
As UAVs are expected to expand, there is a need to perform efficient target classification within a resource-constrained environment. This paper investigate developing, training, and testing custom classifier models. These lightweight models offer reduced computation resource consumption and processing delay while improving inference accuracy over ...
Nicholas A. Speranza   +2 more
openaire   +1 more source

Acoustic classification of submerged targets

ICASSP '82. IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005
Broadband signal processing techniques have introduced new possibilities in acoustic classification through detailed examination of the target's form function (backscattered pressure vs frequency). The form function is unique for a body of given size, shape and composition and correlation with analytically or empirically obtained form function ...
Susan K. Numrich   +2 more
openaire   +1 more source

A hybrid system for target classification

Pattern Recognition Letters, 1997
Abstract We describe a template-matching based system for discriminating among a number of ground vehicles using their one-dimensional vertical-profile signatures obtained from airborne HRR sensors. We present results obtained by using optimal-sized, variable-width sub-targets and multiple profiles from the target for recognition.
Raj Bhatnagar   +2 more
openaire   +1 more source

A Possibilistic Approach to Target Classification

2000
Abstract: This chapter describes an alternative to the Bayesian approach to target classification that is based on possibility theory. A possibilistic classifier minimizes the maximum cost of the classification decision taking into account the a posteriori possibilities of the target classes given the measured target attributes.
Huizing, A.G., Groen, F.C.A.
openaire   +2 more sources

Home - About - Disclaimer - Privacy