Collaborative Transient Event Detection, Localization and Classification in Distributed Sensor Networks
Agency / Branch:
DOD / ARMY
A critical need for the U.S. forces operating in hostile urban environments, e.g. in MOUT, is the development of an innovative smart acoustic sensor system that provides capability to accurately detect, localize and identify battlefield transient events such as gunshots, RPG and artillery fires as well as other sources of interest including vehicles. A system-level solution for distributed fixed-site and/or portable acoustic sensors is sought that can provide soldiers with real-time assessment of commonly occurring transient events in complex battlefield environments. The algorithms should be able to handle a wide range of transient events exploiting their muzzle blast, ballistic shockwave or both components. Based upon our successful Phase I research, Information System Technologies, Inc. (ISTI) will further develop and fine-tune our innovative distributed sensor processing algorithms to (a) dynamically and adaptively form an optimal local distributed sensor network for a specific military situation, (b) accurately and rapidly self-localize the sensor nodes, (c) detect and agree on different transient events in presence of ambient noise and urban multipath effects, (d) perform accurate real-time collaborative transient event localization using time difference of arrival (TDOA) , time of arrival (TOA), and/or Direction of arrival (DOA) methods robust to non-line-of sight and multipath problems, (e) restore transient signals from noisy and faded signatures, (f) extract salient time-frequency features, (g) perform multi-expert transient event recognition, (h) and develop an overall battlefield transient event assessment system. This research will also lead to the design, development, prototyping, and extensive testing of dedicated sensor boards using the existing low-cost low-power wireless sensors, e.g. motes, with the overall targeted cost of $300 per sensor node. We shall demonstrate the effectiveness of our algorithms in two field testing using a moderate number of fixed-site and/or soldier-portable sensor nodes forming various distributed sensor network configurations and for different acoustic transient events and vehicles.
Small Business Information at Submission:
M. R. Azimi-Sadjadi
CEO & President
INFORMATION SYSTEMS TECHNOLOGIES, INC.
5412 Hilldale Court Fort Collins, CO 80526
Number of Employees: