Robust automatic target recognition using learning classifier systems

Ravichandran, B.; Gandhe, Avinash; Smith, Robert E.; Mehra, Raman K.

doi:10.1016/j.inffus.2006.03.001

Cited by 36 publications

(18 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ravichandran et al in [13] do a similar thing. They compare the accuracy and robustness of LCS against a PCA-based distance classifier and find that LCS on its own can outperform PCA on its own.…”

Section: Related Workmentioning

confidence: 71%

PCA for improving the performance of XCSR in classification of high-dimensional problems

Behdad

French

Barone

et al. 2011

Proceedings of the 13th Annual Conference Companion on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

XCSR is an accuracy-based learning classifier system (LCS) which can handle classification problems with real-value features. However, as the number of features increases, a high classification accuracy comes at the cost of more resources: larger population sizes and longer computational running times. In this research, we present a PCA-enhanced LCS, which uses principal component analysis (PCA) as a preprocessing step for XCSR, and examine how it performs on complex multi-dimensional real-world data. The experiments show that this technique, in addition to significantly reducing the computational resources and time requirements of XCSR, maintains its high accuracy and even occasionally improves it. In addition to that, it reduces the required population size needed by XCSR.

show abstract

Section: Related Workmentioning

confidence: 71%

PCA for improving the performance of XCSR in classification of high-dimensional problems

Behdad

French

Barone

et al. 2011

Proceedings of the 13th Annual Conference Companion on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…For EOCs, where the target backscattering or shadow shape is distorted, the use of only the target image is more suitable to avoid the confusion from the shadow. For example, the image captured at a low depression angle has a much larger shadow than that at the larger depression angle [45]. Under this condition, the shadow should not be used because it may introduce more confusing information than the discriminative information.…”

Section: Information-decoupled Representationmentioning

confidence: 99%

Target Recognition in SAR Images Based on Information-Decoupled Representation

Chang

You

2018

Remote Sensing

View full text Add to dashboard Cite

This paper proposes an automatic target recognition (ATR) method for synthetic aperture radar (SAR) images based on information-decoupled representation. A typical SAR image of a ground target can be divided into three parts: target region, shadow and background. From the aspect of SAR target recognition, the target region and shadow contain discriminative information. However, they also include some confusing information because of the similarities of different targets. The background mainly contains redundant information, which has little contribution to the target recognition. Because the target segmentation may impair the discriminative information in the target region, the relatively simpler shadow segmentation is performed to separate the shadow region for information decoupling. Then, the information-decoupled representations are generated, i.e., the target image, shadow and original image. The background is retained in the target image, which represents the coupling of target backscattering and background. The original image and generated target image are classified using the sparse representation-based classification (SRC). Then, their classification results are combined by a score-level fusion for target recognition. The shadow image is not used because of its lower discriminability and possible segmentation errors. To evaluate the performance of the proposed method, extensive experiments are conducted on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset under both standard operating condition (SOC) and various extended operating conditions (EOCs). The proposed method can correctly classify 10 classes of targets with the percentage of correct classification (PCC) of 94.88% under SOC. With the PCCs of 93.15% and 75.03% under configuration variance and 45 • depression angle, respectively, the superiority of the proposed is demonstrated in comparison with other methods. The robustness of the proposed method to both uniform and nonuniform shadow segmentation errors is validated with the PCCs over 93%. Moreover, with the maximum average precision of 0.9580, the proposed method is more effective than the reference methods on outlier rejection.

show abstract

“…Learning classifier systems also have military applications. Smith and colleagues [237,238] applied them to the discovery of novel fighter maneuvering strategies and recently to target recognition [109,213,214].…”

Section: Other Applicationsmentioning

confidence: 99%