MDL approach for multiple low observable track initiation

Chen, H.; Bar‐Shalom, Yaakov; Pattipati, Krishna R.; Kirubarajan, T.

doi:10.1109/taes.2003.1238742

Cited by 30 publications

(19 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multiple LO track initiation can be done with the MDL criterion without the risk of "overfitting" [248].…”

Section: A Survey Of Pda Techniques Was Carried Out [270]mentioning

confidence: 99%

Estimation With Multisensor Fusion

Bar‐Shalom¹,

Pattipati²,

Willett³

2003

View full text Add to dashboard Cite

Public reportmg burden for this collection of infonnaSon is estimatia to average I hour per response, including the Ime for reviewing instnictions, seard the collection of information. Send comments regarding this bo«en estimate or my other aspect of this coflection of information, including snggesThe research effort reported here focused on the development of practical advanced algorithms for optimal processmg of the information obtained from various remote sensing devices (radar, ESM or electro-optical) for surveillance and tracking targets. The processing consists of integration/filtermg of the sensor data across time and fusion across sensors with the main goal being overcoming the inherent limitations of real-world sensors (accuracy and reliability) due to noise." which cause false alarms, and other factors, such as low observable (LQ) targets, which lead to low detection probability. We developed algorithms for: association and fusion of measurements from multiple, asynchronous heterogeneous sensors based on discrete mathematical optimization techniques (multidimensional matching/assignment techniques) for practical high density scenarios target tracking for the case of multipath; phased array radar resource allocation for the case of unresolved targets; track formation of LO targets from EQ sensor (latd; radar waveform design for optimized tracking (i.e., system level) performance; track before detect approach for VLO targets with flucmating amplitude; generalization of the CRLB iii the presence of false measurements to iion-Gaussian distribution; an efficient estimator (that meets the CRI'B) for acquisition by an ESA radar of a LQ TBM prior to reentry; SAM identification for timely countermeasures; bias estimation for multiple radars using targets of opportunity; exact incorporation of target classification into multidimensional assigiunent. ABSTRACT The research effort reported here focused on the development of practical advanced algorithms for optimal processing of the information obtained from various remote sensing devices (radar, ESM or electro-optical) for surveillance and tracking targets. The processing consists of integration/filtering of the sensor data across time and fusion across sensors with the main goal being overcoming the inherent limitations of real-world sensors (accuracy and reliabiUty) due to noise, which cause false alarms, and other factors, such as low observable (LO) targets, which lead to low detection probability. We developed algorithms for: association and fusion of measurements from multiple, asynchronous heterogeneous sensors based on discrete mathematical optimization techniques (multidimensional matching/assignment techniques) for practical high density scenarios; target tracking for the case of multipath; phased array radar resource allocation for the case of unresolved targets; track formation of LO targets from EO sensor data; radar waveform design for optimized tracking (i.e., system level) performance; track before detect approach for VLO targets with fluctuating a...

show abstract

“…Multiple LO track initiation can be done with the MDL criterion without the risk of "overfitting" [248].…”

Section: A Survey Of Pda Techniques Was Carried Out [270]mentioning

confidence: 99%

Estimation With Multisensor Fusion

Bar‐Shalom¹,

Pattipati²,

Willett³

2003

View full text Add to dashboard Cite

show abstract

“…The TBD-based algorithms jointly process more consecutive scans and jointly declare the presence of a target and, eventually, its track. The popular approaches of the TBD-based strategy are mainly Hough transform [7], maximum likelihood (ML) estimation [8], dynamic programming [9], and hypothesis testing [10]. These TBD-based algorithms achieved well performance since that temporal profiles of pixels through which targets pass will be distinct from those through which clutter passes.…”

Section: Introductionmentioning

confidence: 99%

Track Initiation for Dim Small Moving Infrared Target Based on Spatial-Temporal Hypothesis Testing

et al. 2009

J Infrared Milli Terahz Waves

View full text Add to dashboard Cite

Track initiation for dim small moving target particularly in a heavy clutter environment is a theoretical and technological challenge for diverse tracking systems. The different spatial-temporal characteristics presenting in sequence scans are utilized to recognize target and initialize track in this paper. In spatial domain, the small target mapped in the image is a uniform gray spot other than pixel-sized object with high congregated degree, whereas, the false alarm is independent, irrelative and lower congregated degree. In temporal domain, the target's trajectory projected on image sequence is continuous for the continuity of target motion and will appear in the neighborhood at consecutive instants with the maximum probability, on the contrary, the false alarm is disorderly, and occurs in the neighborhood at consecutive instants is impossible. Based on the spatial-temporal characteristics mentioned above, a track initiation algorithm for dim small moving target based on spatial-temporal hypothesis testing, which consists of neighborhood clustering and trajectory continuity, is derived and analyzed in detail. The theory analysis and experimental results show that this method could effectively initialize the track for dim small moving target in heavy clutter environment.

show abstract

“…Track initiation techniques have been reported in [5], [6], [7] and [8]. The first two approaches ( [5], [6]), formulate the track initiation problem as multiple composite hypothesis testing using the maximum likelihood estimator with probabilistic data association (ML-PDA).…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…The first two approaches ( [5], [6]), formulate the track initiation problem as multiple composite hypothesis testing using the maximum likelihood estimator with probabilistic data association (ML-PDA). In [5], the hypotheses are based on the minimum description length (MDL) criterion, and in [6] a new method called optimal gating is proposed. Furthermore, the authors in [7] propose a track initiation method based on Hough Transform (HT), and in [8], enumeration strategies (kd-trees) are utilized to link together observations from different time steps and initiate tracks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning moving objects in a multi-target tracking scenario for mobile robots that use laser range measurements

Kondaxakis

Baltzakis

Trahanias

2009

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-This paper addresses the problem of real-time moving-object detection, classification and tracking in populated and dynamic environments. In this scenario, a mobile robot uses 2D laser range data to recognize, track and navigate moving targets. Most previous approaches either rely on pre-defined data features or off-line training of a classifier for specific data sets, thus eliminating the possibility to detect and track different-shaped moving objects. We propose a novel and adaptive technique where potential moving objects are classified and learned in real-time using a Fuzzy ART neural network algorithm. Experimental results indicate that our method can effectively distinguish and track moving targets in cluttered indoor environments, while at the same time learning their shape.

show abstract

MDL approach for multiple low observable track initiation

Cited by 30 publications

References 16 publications

Estimation With Multisensor Fusion

Estimation With Multisensor Fusion

Track Initiation for Dim Small Moving Infrared Target Based on Spatial-Temporal Hypothesis Testing

Learning moving objects in a multi-target tracking scenario for mobile robots that use laser range measurements

Contact Info

Product

Resources

About