&lt;title&gt;Quadratic distance classifier for multiclass SAR ATR using correlation filters&lt;/title&gt;

Mahalanobis, Abhijit; Forman, Arthur V.; Bower, Mark R.; Day, Nathalie; Cherry, Richard A.

doi:10.1117/12.145517

Cited by 7 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These distortions are reflected in the output as variations in the structure and shape of the corresponding correlation planes, g1 , and are quantified by ASM as shown in Eq. (15). Another interpretation can be made by treating H as a linear transformation.…”

Section: The Choice Of the Best Desired Shapementioning

confidence: 97%

“…(14) Applying Parseval's theorem to Eq. (13), it can be easily shown that hSh = H*x1 _H*m2 g1 _2 (15) iN where H is diagonal matrix with the elements of h along its main diagonal, m = is the "average" or "mean" training image vector, and g1 and are vector representations of the correlation surfaces of the i-th training image and the mean image respectively. The quantity hSh is referred to as the Average Similarity Measure (ASM)1° because it is a metric for the average similarity in the shapes of the in-class correlation surfaces.…”

Section: The Choice Of the Best Desired Shapementioning

confidence: 99%

“…The DCCF approach has demonstrated promising performance on both infra-red (IR) [14] as well as synthetic aperture radar (SAR) [15,16] imagery. Test results showed that DCCFs outperform other correlation filters in recognizing targets while rejecting noise, clutter and other confusing objects.…”

Section: Distance Classifier Correlation Filtersmentioning

confidence: 99%

See 2 more Smart Citations

<title>Automatic target recognition using correlation filters</title>

Mahalanobis

1995

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

Section: The Choice Of the Best Desired Shapementioning

confidence: 97%

Section: The Choice Of the Best Desired Shapementioning

confidence: 99%

See 1 more Smart Citation

<title>Automatic target recognition using correlation filters</title>

Mahalanobis

1995

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…This can be done by forcing every image in the training set x to have a similar correlation output to its prototype in AICH which is x2 -f3m. The discrete Fourier transform of the ith prototype correlation output is gj = (X2 -3M)h* (16) where the superscript represents the complex conjugate.…”

Section: Extended Machmentioning

confidence: 99%

<title>Improving the false alarm capabilities of composite correlation filters</title>

1999

Self Cite

View full text Add to dashboard Cite

Despite much prior work, one of the problems that still persists in using composite correlation filters for Automatic Target Recognition (ATR) is the high false alarm rate due to clutter. In this paper, we propose two methods (one based on clustering and another based on extending the maximum average correlation height or MACH filter) to improve the clutter rejection capability of composite filters. Initial numerical results are presented to illustrate the potential improvements.

show abstract

“…The research on SAR includes imaging, target detection, target recognition, time-frequency analysis, and many other aspects [1][2][3][4][5][6][7][8]. The research on Automatic Target Recognition (ATR) of SAR started around 1990 [9][10][11]. ATR is still one of the most challenging research topics.…”

Section: Introductionmentioning

confidence: 99%

A Vehicle Target Recognition Algorithm for Wide-Angle SAR Based on Joint Feature Set Matching

Peng

2019

Electronics

View full text Add to dashboard Cite

Target recognition is an important area in Synthetic Aperture Radar (SAR) research. Wide-angle Synthetic Aperture Radar (WSAR) has obvious advantages in target imaging resolution. This paper presents a vehicle target recognition algorithm for wide-angle SAR, which is based on joint feature set matching (JFSM). In this algorithm, firstly, the modulus stretch step is added in the imaging process of wide-angle SAR to obtain the thinned image of vehicle contour. Secondly, the gravitational-based speckle reduction algorithm is used to obtain a clearer contour image. Thirdly, the image is rotated to obtain a standard orientation image. Subsequently, the image and projection feature sets are extracted. Finally, the JFSM algorithm, which combines the image and projection sets, is used to identify the vehicle model. Experiments show that the recognition accuracy of the proposed algorithm is up to 85%. The proposed algorithm is demonstrated on the Gotcha WSAR dataset.

show abstract

<title>Quadratic distance classifier for multiclass SAR ATR using correlation filters</title>

Cited by 7 publications

References 0 publications

<title>Automatic target recognition using correlation filters</title>

<title>Automatic target recognition using correlation filters</title>

<title>Improving the false alarm capabilities of composite correlation filters</title>

A Vehicle Target Recognition Algorithm for Wide-Angle SAR Based on Joint Feature Set Matching

Contact Info

Product

Resources

About