General Metropolis-Hastings jump diffusions for automatic target recognition in infrared scenes

Lanterman, Aaron D.; Miller, Michael I.; Snyder, Donald L.

doi:10.1117/1.601302

Cited by 20 publications

(14 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The overall method effectively handles the variability issue in FLIR images, since it does not require target modelling. This is in contrast to other pattern-theoretic-based approaches to the same problem (e.g., see Lanterman et al, 1997).…”

Section: Introductioncontrasting

confidence: 41%

Automatic target detection and tracking in forward-looking infrared image sequences using morphological connected operators

Braga-Neto

Choudhary

Goutsias

2004

J. Electron. Imaging

View full text Add to dashboard Cite

We propose a method for automatic target detection and tracking in forward-looking infrared (FLIR) image sequences. We use morphological connected operators to extract and track targets of interest and remove undesirable clutter. The design of these operators is based on general size, connectivity and motion criteria, using spatial intraframe and temporal interframe information. In a first step, an image sequence is filtered on a frame-by-frame basis to remove background and residual clutter and to enhance the presence of targets. Detections extracted from the first step are passed to a second step for motion-based analysis. This step exploits the spatiotemporal correlation of the data, stated in terms of a connectivity criterion along the time dimension. The proposed method is suitable for piplined implementation or time progressive coding/transmission, since only a few frames are considered at a time. Experimental results, obtained with real FLIR image sequences, illustrating a wide variety of target and clutter variability, demonstrate the effectiveness and robustness of the proposed method.

show abstract

Section: Introductioncontrasting

confidence: 41%

Automatic target detection and tracking in forward-looking infrared image sequences using morphological connected operators

Braga-Neto

Choudhary

Goutsias

2004

J. Electron. Imaging

View full text Add to dashboard Cite

show abstract

“…9 A single ground-based target will live in the parameter space X ϭR 2 ϫ͓0,2)ϫA which specifies its position and orientation on the ground ͑assumed flat͒ and its target class. The target class will be assumed to be from a known family of target types, for instance Aϭ͕M2,M60,T62, .…”

Section: Representation Of Complex Scenesmentioning

confidence: 99%

“…[3][4][5][6] Three-dimensional CAD shape-models represented the objects of interest, a likelihood function modeling the physics of FLIR cameras encapsulated the way the objects were seen by the sensor, and a jump-diffusion 7 random sampling algorithm allowed searching over complicated parameter spaces involving unknown numbers of targets. 8,9 This project drew heavily on an earlier, parallel effort to apply these methods to airborne target tracking and recognition using radar data. 10,11 In the jump-diffusion FLIR study reported in Ref.…”

Section: Introductionmentioning

confidence: 99%

“…10,11 In the jump-diffusion FLIR study reported in Ref. 9, the radiant intensities of objects in the scene were assumed known a priori. To relax this assumption and accommodate the vast variability of target signatures under varying environmental and operational conditions, we have extended the parameter space to include variables describing the thermodynamic state of the targets.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bayesian inference of thermodynamic state incorporating Schwarz-Rissanen complexity for infrared target recognition

Lanterman

2000

Opt. Eng

Self Cite

View full text Add to dashboard Cite

The recognition of targets in IR scenes is complicated by the wide variety of appearances associated with different thermodynamic states. We represent variability in the thermal signatures of targets via an expansion in terms of ''eigentanks'' derived from a principal component analysis performed over the target's surface. Employing a Poisson sensor likelihood, or equivalently a likelihood based on Csiszar's I-divergence (a natural discrepancy measure for nonnegative images), yields a coupled set of nonlinear equations which must be solved to compute maximum a posteriori estimates of the thermodynamic expansion coefficients. We propose a weighted least-squares approximation to the Poisson loglikelihood for which the MAP estimates are solutions of linear equations. Bayesian model order estimation techniques are employed to choose the number of expansion coefficients; this prevents target models with numerous eigentanks in their representation from having an unfair advantage over simple target models. The Bayesian integral is approximated by Schwarz's application of Laplace's method of integration; this technique is closely related to Rissanen's minimum description length criteria. Our implementation of these techniques on Silicon Graphics computers exploits the flexible nature of their rendering engines. The implementation is illustrated in estimating the orientation of a tank and the optimum number of representative eigentanks for both simulated and real data.

show abstract

“…In this paper, the performance of three search algorithms namely, metropolis hastings (MH) 1,7 , simulated annealing (SA) 8 and gradual greedy (GG) 2 are evaluated for target location and identity estimation for the typical scene (Fig. 2).…”

Section: Sensor Likelihood Computation and Bayesian Fusionmentioning

confidence: 99%

Data Fusion for Identity Estimation and Tracking of Centroidusing Imaging Sensor Data

Naidu¹,

Girija²,

Raol³

2007

DSJ

View full text Add to dashboard Cite

Two aspects involved in automatic target recognition namely, (i) Location and identity estimation (LIE) of a target by fusing infrared (IR) and acoustic sensor data, and (ii) centroid tracking for target state estimation using IR sensor data are discussed in this paper. The LIE has been achieved using a combination of Bayesian fusion and one of the three search algorithms namely, metropolis hastings (MH), simulated annealing (SA) and gradual greedy (GG). It was observed that the performance of the GG search algorithms was better in terms of success rate which has been evaluated through Monte Carlo simulations. For tracking of the centroid, an algorithm, where the centroid of the gray level image is tracked using probabilistic data association filter, has been implemented. Simulated data results indicate good tracking performance of this algorithm. For robust tracking of centroid, the track from the imaging sensor was fused with the track from ground-based radar using state vector fusion. It was observed that fusion generates robust tracks even when there is data loss in one of the sensors.

show abstract

General Metropolis-Hastings jump diffusions for automatic target recognition in infrared scenes

Cited by 20 publications

References 30 publications

Automatic target detection and tracking in forward-looking infrared image sequences using morphological connected operators

Automatic target detection and tracking in forward-looking infrared image sequences using morphological connected operators

Bayesian inference of thermodynamic state incorporating Schwarz-Rissanen complexity for infrared target recognition

Data Fusion for Identity Estimation and Tracking of Centroidusing Imaging Sensor Data

Contact Info

Product

Resources

About