Automatic recognition of ISAR ship images

Musman, Scott; Kerr, Dermot; Bachmann, Charles M.

doi:10.1109/7.543860

Cited by 176 publications

(87 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The purpose is to classify targets on various types of traffic scenarios: road, marine, and air traffic. Some examples of specific techniques developed in this field could be found in [14][15][16][17][18][19][20][21][22][23]. The proposed technique is based on the extraction of several descriptors, for each target, from sequences of range-Doppler images [24], such as the radial length, the dynamics, two range-Doppler integrated image (coherent and non-coherent), and the range profiles integrated in Doppler (coherent and non-coherent).…”

Section: Introductionmentioning

confidence: 99%

Simple Traffic Surveillance System Based on Range-Doppler Radar Images

Calvo-Gallego¹,

Pérez-Martínez²

2012

PIER

View full text Add to dashboard Cite

Abstract-A simple traffic surveillance system based on the extraction of features from range-Doppler radar images is addressed. The concept exploits the High-Resolution Radars (HRR) properties. Specifically, a procedure is proposed to obtain some features from the HRR non-cooperative targets to enable their classification. These features are the distance, radial velocity, radial longitudinal dimension of the target, its integrated range-Doppler image based on a group of range-Doppler frames from each target, and both the coherent and non-coherent integrated range profiles. Experimental results from real scenarios using a high-resolution Linear-Frequency-Modulated Continuous-Wave (LFMCW) millimetre-wave radar are shown.

show abstract

Section: Introductionmentioning

confidence: 99%

Simple Traffic Surveillance System Based on Range-Doppler Radar Images

Calvo-Gallego¹,

Pérez-Martínez²

2012

PIER

View full text Add to dashboard Cite

show abstract

“…Due to the high-resolution imaging ability of remote moving targets, the inverse synthetic aperture radar (ISAR) imaging has been widely applied in military and civilian applications [1][2][3][4], which can help obtain numerous characteristics of the target. For ISAR imaging technology, a wide-band signal is transmitted to achieve high range resolution, while the cross-range resolution is based on an appropriate coherent integration angle.…”

Section: Introductionmentioning

confidence: 99%

A Robust Sub-Integer Range Alignment Algorithm Against MTRC for Isar Imaging

Hu¹,

Chen²

2017

PIER B

View full text Add to dashboard Cite

Abstract-Range alignment plays an important role in the inverse synthetic aperture radar (ISAR) imaging. The performance of the traditional range alignment algorithms decreases when the migration through resolution cells (MTRC) is much severe. In this paper, a measure of MTRC is defined, and the effect of MTRC on range alignment is analyzed. Taking MTRC into account, a robust sub-integer range alignment algorithm is proposed. Firstly, each range profile is interpolated to remove the precision limitation of integer range resolution cell. Subsequently, the matrix formed by all the range profiles is partitioned into several matrix blocks on the slow-time domain. For each matrix block, the range profiles are aligned by minimizing the entropy of the average range profile (ARP). Finally, the matrix blocks are coarsely aligned using the maximum correlation method, followed by a fine alignment based on the minimization of the ISAR image entropy. The effectiveness of the proposed algorithm is validated by simulations and real-world data. Results demonstrate that the proposed method is robust against MTRC and can reduce the alignment error. The resultant ISAR image is much better focused.

show abstract

“…Compare with vessel detection, few studies have been conducted on vessel classification. The initial attempts at vessel classification were mainly based on inverse synthetic aperture radar (ISAR) vessel images [5][6][7] and backscattering simulation images of vessels [8,9]. Recently, polarimetric SAR data have also been exploited for vessel classification [10,11].…”

Section: Introductionmentioning

confidence: 99%

Classification of Vessels in Single-Pol COSMO-SkyMed Images Based on Statistical and Structural Features

Wang

Jiang

et al. 2015

Remote Sensing

View full text Add to dashboard Cite

Vessel monitoring is one of the most important maritime applications of Synthetic Aperture Radar (SAR) data. Because of the dihedral reflections between the vessel hull and sea surface and the trihedral reflections among superstructures, vessels usually have strong backscattering in SAR images. Furthermore, in high-resolution SAR images, detailed information on vessel structures can be observed, allowing for vessel classification in high-resolution SAR images. This paper focuses on the feature analysis of merchant vessels, including bulk carriers, container ships and oil tankers, in 3 m resolution COSMO-SkyMed stripmap HIMAGE mode images and proposes a method for vessel classification. After preprocessing, a feature vector is estimated by calculating the average value of the kernel density estimation, three structural features and the mean backscattering coefficient. Support vector machine (SVM) classifier is used for the vessel classification, and the results are compared with traditional methods, such as the K-nearest neighbor algorithm (K-NN) and minimum distance classifier (MDC). In situ investigations are conducted during the SAR data acquisition. Corresponding Automatic Identification System (AIS) reports are also obtained as ground truth to evaluate the effectiveness of the classifier. The preliminary results show that the combination of the average value of the kernel density estimation and mean backscattering coefficient has good ability for classifying the three types of vessels. When adding the three structural features, the results slightly improve. The result of the SVM classifier is better than that of K-NN and MDC. However, the SVM requires more time, when the parameters of the kernel are estimated. OPEN ACCESSRemote Sens. 2015, 7 5512

show abstract

Automatic recognition of ISAR ship images

Cited by 176 publications

References 6 publications

Simple Traffic Surveillance System Based on Range-Doppler Radar Images

Simple Traffic Surveillance System Based on Range-Doppler Radar Images

A Robust Sub-Integer Range Alignment Algorithm Against MTRC for Isar Imaging

Classification of Vessels in Single-Pol COSMO-SkyMed Images Based on Statistical and Structural Features

Contact Info

Product

Resources

About