Data Fusion of FLIR and LADAR in Autonomous Weapons Systems
نویسندگان
چکیده
We use data fusion in our automatic target recognition (ATR) system to identify and track airbourne objects. The fusion process allows for a much more robust conclusion to be drawn from what may well be incomplete data. The method we use for the fusion process is twofold. The Transferable belief model (TBM), which is derived from Dempster Shafer Theory (DST) is used for matching type and Kalman Filters are used for matching pose. We are not aware of the TBM being used within such a real world scenario. We also present model based matching algorithms for both 2D and 3D data obtained from disparate sensors. Results for a typical scenario are presented showing the benefits of fusing the results using the TBM and Kalman Filter.
منابع مشابه
Simulation of FLIR and LADAR Data Using Graphics Animation Software
This paper presents an implementation of Forward Looking Infrared (FLIR) and Laser Radar (LADAR) data simulation for use in developing a multi-sensor datafusion automated target recognition (ATR) system. Through the use of commercial models and software we can create a highly detailed scene model, which provides a rich data set for later processing. We embed our own modules within this software...
متن کاملA Data Fusion System for Object Recognition based on Transferable Belief Models and Kalman Filters
We examine the use of fusing data from multiple data sources for use within object recognition systems. We then continue, to illustrate the system that we have created for our own object recognition needs. The data fusion model that we use is embedded within an object recognition system that analyses simulated FLIR and LADAR data to recognise and track aircraft. The data fusion is based upon th...
متن کاملReconnaissance, Surveillance, and Target Acquisition in the UGV/Demo II Program
The UGV/Demo II program was established to develop and mature, within 5 years, the navigation and automatic target recognition technologies critical for minimally supervised, semi-autonomous, unmanned ground vehicles for military scout missions. The program, initiated in 1992, focuses on and exploits the arti cial intelligence, computer vision, and advanced processor development sponsored under...
متن کاملObject to Multisensor Coregistration with Eight Degrees of Freedom y
A new least squares procedure is presented which fuses data from a standard perspective sensor CCD camera FLIR sensor etc and a range sensor LADAR based upon correspond ing features identi ed on a D object model and in each image The algorithm solves for both the pose estimate of the object relative to the sensors and the registration between sen sors This model based coregistration process is ...
متن کاملPerformance Analysis of Next-Generation LADAR for Manufacturing, Construction, and Mobility
The NIST Construction Metrology and Automation Group (CMAG), in cooperation with the NIST Intelligent Systems Division (ISD), is developing performance metrics and researching issues related to the design and development of a Next-Generation LADAR (laser radar) sensor that will enable general automation in structured and unstructured environments. This report reviews the basic physics and imple...
متن کامل