Dynamic Agent Classification and Tracking Using an Ad Hoc Mobile Acoustic Sensor Network

Friedlander, David; Griffin, Christopher; Jacobson, Noah Tobias; Phoha, Shashi; Brooks, Richard

doi:10.1155/s1110865703212099

Cited by 31 publications

(26 citation statements)

References 11 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Li et al [7] estimate target position by solving a non-linear least squares problem and assuming that sensors are pre-calibrated. Target localization based on time-of-arrival (TOA) [4] or the direction-of-arrival (DOA) of acoustical/seismic signals has also been explored in the past [16]. In [17], a spanning tree rooted at the sensor node close to a target is used and N = 8 for target tracking, with target position estimated by the location of the root sensor.…”

Section: Related Workmentioning

confidence: 99%

Multi-Modal Calibration of Surveillance Sensor Networks

et al. 2006

View full text Add to dashboard Cite

Abstract-Target detection and localization is one of the key research challenges in sensor networks. In this paper we propose a heterogeneous wireless sensor network integrating imaging and non-imaging sensors to accomplish the detection and localization task in complex urban environments. The lowcost non-imaging sensors provide early detection and partial localization of potential targets and direct imaging sensors to focus on them. Accurate target location estimated by the imaging sensors is subsequently used for in-situ calibration of the non-imaging sensors so that localization error is minimized over time. We evaluate our approach through simulation and our preliminary results reveal that coordination across different sensing modalities increases localization accuracy and can reduce the amount of imaging data that must be carried by the network.

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-Modal Calibration of Surveillance Sensor Networks

et al. 2006

View full text Add to dashboard Cite

show abstract

“…Acoustic Sensor Networks (ASNs) have been prototyped for many military and civilian applications such as animal vocalization recognition [13,22,24], military vehicle classification [12,5], tracking [14] and indoor activity classification [20,35]. Because the sampling rates of ASNs (e.g., 10kHz or above) are several orders of magnitude higher than those of traditional Wireless Sensor Networks (WSNs) (e.g., 0.1Hz for microclimate sensing applications), enormous amount of data are collected by ASNs.…”

Section: Introductionmentioning

confidence: 99%

“…The purpose of real-time classification in ASNs is two-fold. First, some ASN applications such as military vehicle tracking [12,5,14] require real-time event reporting. Second, a node needs to finish processing the captured audio signal in real-time because the audio signal input is a continuous stream.…”

Section: Introductionmentioning

confidence: 99%

Real-time classification via sparse representation in acoustic sensor networks

Wei

Yang

Shen

et al. 2013

Proceedings of the 11th ACM Conference on Embedded Networked Sensor Systems

View full text Add to dashboard Cite

Acoustic Sensor Networks (ASNs) have a wide range of applications in natural and urban environment monitoring, as well as indoor activity monitoring. In-network classification is critically important in ASNs because wireless transmission costs several orders of magnitude more energy than computation. The main challenges of in-network classification in ASNs include e↵ective feature selection, intensive computation requirement and high noise levels. To address these challenges, we propose a sparse representation based featureless, low computational cost, and noise resilient framework for in-network classification in ASNs. The key component of Sparse Approximation based Classification (SAC),`1 minimization, is a convex optimization problem, and is known to be computationally expensive. Furthermore, SAC algorithms assumes that the test samples are a linear combination of a few training samples in the training sets. For acoustic applications, this results in a very large training dictionary, making the computation infeasible to be performed on resource constrained ASN platforms. Therefore, we propose several techniques to reduce the size of the problem, so as to fit SAC for in-network classification in ASNs. Our extensive evaluation using two real-life datasets (consisting of calls from 14 frog species and 20 cricket species respectively) shows that the proposed SAC framework outperforms conventional approaches such as Support Vector Machines (SVMs) and k-Nearest Neighbor (kNN) in terms of classification accuracy and robustness. Moreover, our SAC approach can deal with multi-label classification which is common in ASNs. Finally, we explore the system design spaces and demonstrate the real-time feasibility of the proposed framework by the implementation and evaluation of an acoustic classification application on an embedded ASN testbed.

show abstract

“…Energy conservation is achieved by switching off the redundant nodes, which have overlapping coverage. A dynamic space time clustering algorithm [29] is used for target tracking. The algorithm performs the node clustering based on closest point of approach (CPA)…”

Section: Target Tracking Using Wireless Sensor Networkmentioning

confidence: 99%

Energy-Efficient Self-Organization of Wireless Acoustic Sensor Networks for Ground Target Tracking

Walpola¹

View full text Add to dashboard Cite

Dynamic Agent Classification and Tracking Using an Ad Hoc Mobile Acoustic Sensor Network

Cited by 31 publications

References 11 publications

Multi-Modal Calibration of Surveillance Sensor Networks

Multi-Modal Calibration of Surveillance Sensor Networks

Real-time classification via sparse representation in acoustic sensor networks

Energy-Efficient Self-Organization of Wireless Acoustic Sensor Networks for Ground Target Tracking

Contact Info

Product

Resources

About