Hierarchical ship detection and recognition with high-resolution polarimetric synthetic aperture radar imagery

Abstract

Ship surveillance by remote sensing technology has become a valuable tool for protecting marine environments. In recent years, the successful launch of advanced synthetic aperture radar (SAR) sensors that have high resolution and multipolarimetric modes has enabled researchers to use SAR imagery for not only ship detection but also ship category recognition. A hierarchical ship detection and recognition scheme is proposed. The complementary information obtained from multipolarimetric modes is used to improve both the detection precision and the recognition accuracy. In the ship detection stage, a three-class fuzzy c-means clustering algorithm is used to calculate the segmenting threshold for prescreening ship candidates. To reduce the false alarm rate (FAR), we use a two-step discrimination strategy. In the first step, we fuse the detection results from multipolarimetric channels to reduce the speckle noise, ambiguities, sidelobes, and other sources of interference. In the second step, we use a binary classifier, which is trained with prior data collected on ships and nonships, to reduce the FAR even further. In the ship category recognition stage, we concatenate texturebased descriptors extracted from multiple polarmetric channels to construct a robust ship representation for category recognition. Furthermore, we construct and release a ship category database with real SAR data. We hope that it can be used to promote investigations of SAR ship recognition in the remote sensing and related academic communities. The proposed method is validated by a comprehensive experimental comparison to the state-of-the-art methods. The validation procedure showed that the proposed method outperforms all of the competing methods by about 5% and 15% in terms of ship detection and recognition, respectively.

Characteristics of environmental factors contributing to ALOS-2 PALSAR wind speed errors

“…As a result, the ship pixels have higher NRCS values than the surrounding ocean pixels, and a strong double-bounce scattering is caused by a man-made structure such as the internal structure of ship. It raises side-lobe effect and changes the NRCS values not only of the ship pixels, but also of the surrounding ocean pixels (Lang et al 2014). The overestimation of wind speeds up to 53.1 m s −1 can be induced by the scattering of the ship.…”

Ship Classification Based on MSHOG Feature and Task-Driven Dictionary Learning with Structured Incoherent Constraints in SAR Images

“…2018, 10, x FOR PEER REVIEW 5 of 22 scattering features, are mainly based on the image characteristic mentioned above, obtaining good performance in previous work [4][5][6][7][8][9]. However, interaction of strong scatters on board and electromagnetic reflection between hull and sea surface blur the imaging, making the effective information in SAR images unavailable, as shown in the third and fourth column of Figure 1.…”

“…2D comb feature was proposed by Leng et al [7] based on scattering distributions of ship target. Hierarchical structure was introduced in Lang et al [8] to further improve the performance of scattering features. However, geometric features may fail when the ships from different classes share similar geometric shape.…”

“…The authors would like to thank H. Lang, the author of [8,9], for precious suggestions about data preprocessing.…”

DCNN Based Real-Time Adaptive Ship License Plate Recognition (DRASLPR)

“…In literature, there was some existing work using various technologies, e.g., high-resolution range profile based on radar [3], and and high-resolution polarimetric synthetic aperture radar imagery for hierarchical ship detection and recognition [4] [5]. Those radar-based technologies are limited in recognition accuracy and cost.…”