Many vehicle targets of interest to military Automatic Target Recognition (ATR) possess articulating components: that is, they have components that change position relative to the main body. Many vehicles also have multiple configurations wherein one or more devices or objects may be added to enhance specific military or logistical capabilities.As the expected target set for military ATR becomes more comprehensive, many additional articulations and optional components must be handled. Mobile air defense units often include moving radar antennae as well as turreted guns and missile launchers. Surface-to-Surface Missile (SSM) launchers may be encountered with or without missiles, and with the launch rails raised or lowered. Engineer and countermine vehicles have a tremendous number of possible configurations and even conventional battle tanks may vary items such as external reactive armor, long-range fuel tanks, turret azimuth, and gun elevation.These changes pose a significant barrier to the target identification process since they greatly increase the range of possible target signatures. When combined with variations already encountered due to target aspect changes, an extremely large number of possible signatures is formed. Conventional algorithms cannot process so many possibilities effectively, so in response, the matching process is often made less selective. This degrades identification performance, increases false alarm rates, and increases data requirements for algorithm testing and training. By explicitly involving articulation in the detection and identification stages of an ATR algorithm, more precise matching constraints can be applied, and better selectivity can be achieved. Additional benefits include the measurement of the position and orientation of articulated components, which often has tactical significance.In this paper, the results of a study investigating the impact of target articulation in ATR for military vehicles are presented. 3-D ladar signature data is used. An algorithmic solution is proposed and directions for further research are noted.
Correlation filters have been successfully utilized for object detection in many applications. Each sensor type, however, presents different advantages and challenges. This paper describes the application of correlation filter techniques for automatic target recognition (ATR) to Laser Radar (LADAR) sensor images. Filters are designed using synthetic models, and incorporate range and aspect tolerance for mobile objects. The model generator easily takes into account the sensor field of view (FOV), look-down angle, ground cell size, and shadows. The filters are also designed to exploit various coordinate transforms that are feasible with a LADAR sensor. The correlation algorithm has the unique potential of exploiting the intensity information in conjunction with the range measurements provided by the LADAR Examples using fixed and mobile targets are presented, along with statistical performance results.
This paper describes a conceptual real-time systems approach to LADAR automatic target recognition (ATR). Previous work has demonstrated the viability of utilizing correlation filters derived from synthetic models for detection and recognition of mobile targets in Laser Radar (LADAR) sensor images. The distance correlation classifier filter (DCCF) provides a unique potential for reducing throughput while preserving performance. The application of this concept to a real-time system, however, involves refinement, trade studies, and optimization. Refinements in the correlation filter are discussed and evaluated in terms of performance, throughput, and memory. Preliminary performance results for several mobile targets are presented.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.