TY - JOUR
T1 - CLFR-Det
T2 - Cross-level feature refinement detector for tiny-ship detection in SAR images
AU - Liu, Lingyi
AU - Fu, Lei
AU - Zhang, Yunfeng
AU - Ni, Wenxi
AU - Wu, Bin
AU - Li, Ying
AU - Shang, Changjing
AU - Shen, Qiang
N1 - Publisher Copyright:
© 2023 Elsevier B.V.
PY - 2024/1/25
Y1 - 2024/1/25
N2 - Ship detection in synthetic aperture radar (SAR) images is an important and active topic, due to the characteristics of SAR images involving all-time and all-weather imaging. However, complex backgrounds caused by speckle noise and inshore land, coupled with information deficiency of tiny ships, pose a great challenge for tiny-ship detection in SAR images. To tackle this problem, we present a cross-level feature refinement detector (CLFR-Det) that utilizes features reflecting different levels and distinct semantics (classification and localization). To enrich the semantic information of tiny ships, our approach incorporates a cross-level modulated deformable convolution to aggregate features from relevant positions across multi-level feature maps. This is supported by a spatially-informed multi-scale feature refinement mechanism that combines the features for classification and those for localization. We implement a uniform IoU-weighted adaptive training sample selection method for equitably distributing the impact of positive samples from targets of various sizes during the training process. A generalized IoU loss between ground-truth and preliminary bounding box is further proposed to supervise the learning process of the CLFR-Det, with uncertainty weights incorporated to dynamically depict the levels of disparate losses, enabling adequate training across different tasks. Also, we construct a novel tiny SAR ship detection dataset to comprehensively evaluate the effectiveness of our system, in conjunction with the use of publicly available SSDD and HRSID datasets. Experimental investigations demonstrate that CLFR-Det generally surpasses state-of-the-art performance for multi-scale ship detection, particularly for the detection of tiny ships.
AB - Ship detection in synthetic aperture radar (SAR) images is an important and active topic, due to the characteristics of SAR images involving all-time and all-weather imaging. However, complex backgrounds caused by speckle noise and inshore land, coupled with information deficiency of tiny ships, pose a great challenge for tiny-ship detection in SAR images. To tackle this problem, we present a cross-level feature refinement detector (CLFR-Det) that utilizes features reflecting different levels and distinct semantics (classification and localization). To enrich the semantic information of tiny ships, our approach incorporates a cross-level modulated deformable convolution to aggregate features from relevant positions across multi-level feature maps. This is supported by a spatially-informed multi-scale feature refinement mechanism that combines the features for classification and those for localization. We implement a uniform IoU-weighted adaptive training sample selection method for equitably distributing the impact of positive samples from targets of various sizes during the training process. A generalized IoU loss between ground-truth and preliminary bounding box is further proposed to supervise the learning process of the CLFR-Det, with uncertainty weights incorporated to dynamically depict the levels of disparate losses, enabling adequate training across different tasks. Also, we construct a novel tiny SAR ship detection dataset to comprehensively evaluate the effectiveness of our system, in conjunction with the use of publicly available SSDD and HRSID datasets. Experimental investigations demonstrate that CLFR-Det generally surpasses state-of-the-art performance for multi-scale ship detection, particularly for the detection of tiny ships.
KW - CLFR-Det
KW - Synthetic aperture radar
KW - Tiny SAR ship detection
KW - Tiny ship detection
UR - http://www.scopus.com/inward/record.url?scp=85179588129&partnerID=8YFLogxK
U2 - 10.1016/j.knosys.2023.111284
DO - 10.1016/j.knosys.2023.111284
M3 - Article
AN - SCOPUS:85179588129
SN - 0950-7051
VL - 284
JO - Knowledge-Based Systems
JF - Knowledge-Based Systems
M1 - 111284
ER -