Precise Matching of 3 - D Target Models to Multisensor Data yz
نویسندگان
چکیده
This paper presents a 3-D model-based ATR algorithm which operates simultaneously on imagery from three heterogeneous, approximately boresight aligned, sensors. An iterative search matches models to range and optical imagery by repeatedly predicting detectable features, measuring support for these features in the imagery, and adjusting the transformations relating the target to the sensors in order to improve the match. The result is a locally optimal and globally consistent set of 3-D transformations which precisely relate the best matching target features to combined range, IR and color images. Results show the multisensor algorithm recovers 3-D target pose more accurately than does a traditional single-sensor algorithm. Errors in registration between images are also corrected during matching.
منابع مشابه
Precise matching of 3-D target models to multisensor data
This paper presents a three-dimensional (3-D) model-based ATR algorithm that operates simultaneously on imagery from three heterogeneous, approximately boresight aligned sensors. An iterative search matches models to range and optical imagery by repeatedly predicting detectable features, measuring support for these features in the imagery, and adjusting the transformations relating the target t...
متن کاملPrecise Matching of 3 - D Target Models to Multisensor Data yzMark
permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. z This material is presented electronically to ensure timely dissemination of scholarly and technical work. Copyright and all ...
متن کاملRSTA Research of the Colorado State, University of Massachusetts and Alliant Techsystems Team
The complementary nature of LADAR, FLIR and color data for ATR is being exploited by new algorithms in a three stage recognition system. The stages are initial detection, target class and pose hypothesis generation, and precise model to multisensor coregistra-tion matching. Coregistration globally aligns 3D target models with range, IR and color imagery while simultaneously reening registration...
متن کاملComputer Science Technical Report A Coregistration Approach to Multisensor Target Recognition with Extensions to Exploit Digital Elevation Map Data
A target recognition capability is described that performs: color target detection, target type and pose hypothesis generation, and target type veri cation by 3-D alignment of target models to range and electro-optical imagery. The term `coregistration' is introduced to describe target, range and electro-optical (color and IR) sensor alignment correction. Online model feature prediction using 3...
متن کاملUsing Multisensor Occlusion Reasoning in Object Recognition
An iterative predict and match system renders CAD models to re ne predictions about detectable features in both optical and range sensor data Predicted features adapt to a scene speci c interpretation which includes a time of day lighting model and reasoning about un modeled occluding surfaces During rendering links between the rendered image and the D CAD model are retained to propagate inform...
متن کامل