Abstract:Recently, deep learning has greatly promoted the development of SAR ship detection. But the detectors are usually heavy and computation intensive which hinder the usage on the edge. In order to solve this problem, a lot of lightweight networks and acceleration ideas are proposed. In this survey, we review the papers that about real-time SAR ship detection. We firstly introduce the model compression and acceleration methods. They are pruning, quantization, knowledge distillation, low-rank factorization, lightwe… Show more
“…Similarly, Cui et al [36] proposed a model based on Dense Attention Pyramid Network and also compared its performance with Faster RCNN and SSD. Comprehensive surveys have also been conducted on SAR ship detection using deep learning techniques [37], [38].…”
Section: Related Workmentioning
confidence: 99%
“…Figure 8 shows the outputs of K-Means clustering with K = 12. (11,12), (24,13), (13,29), (16,44), (44,18), (37,35), (23,59),(107,31), (40,102),(79,53), (54,169),(199,67)…”
Section: A Custom Anchor Box Generation Strategymentioning
With the advancements in Space technology and the development of light-weight Synthetic Aperture Radar (SAR) satellites by commercial companies such as ICEYE, Capella Space and Umbra, SAR images have become available on a wide scale. Ship detection is a classic problem in the interpretation and analysis of satellite images and has its significance both in maritime as well as defense applications. In the case of SAR images, ship detection becomes even more challenging due to the presence of large-scale distortions as well as interclass similarity signature problem. Moreover, the State-of-the-Art (SOTA) object detection models have weak generalization capability over SAR datasets. To overcome these challenges, we propose a You Only Look Once (YOLO) based, optimized ship detection model called YOLO-OSD. Our optimized ship detector is based on a hybrid data-model centric approach which utilizes the statistical characteristics of the datasets under observation and has an efficient model architecture. We also carry out a detailed comparative analysis of our proposed model with other SOTA deep learning models on three well-known publicly available datasets. Our results show that the proposed YOLO-OSD outperforms YOLO5, YOLO7 and RetinaNet on all datasets under observation in terms of F1 score and mean Average Precision (mAP). YOLO-OSD also has approximately 16% fewer network parameters as compared to the original YOLO5. Moreover, our proposed model is at least 37.7% faster than YOLO7 and 41.02% faster than the YOLO8 model in terms of training time and thus suitable for real-time satellite based SAR ship detection.
“…Similarly, Cui et al [36] proposed a model based on Dense Attention Pyramid Network and also compared its performance with Faster RCNN and SSD. Comprehensive surveys have also been conducted on SAR ship detection using deep learning techniques [37], [38].…”
Section: Related Workmentioning
confidence: 99%
“…Figure 8 shows the outputs of K-Means clustering with K = 12. (11,12), (24,13), (13,29), (16,44), (44,18), (37,35), (23,59),(107,31), (40,102),(79,53), (54,169),(199,67)…”
Section: A Custom Anchor Box Generation Strategymentioning
With the advancements in Space technology and the development of light-weight Synthetic Aperture Radar (SAR) satellites by commercial companies such as ICEYE, Capella Space and Umbra, SAR images have become available on a wide scale. Ship detection is a classic problem in the interpretation and analysis of satellite images and has its significance both in maritime as well as defense applications. In the case of SAR images, ship detection becomes even more challenging due to the presence of large-scale distortions as well as interclass similarity signature problem. Moreover, the State-of-the-Art (SOTA) object detection models have weak generalization capability over SAR datasets. To overcome these challenges, we propose a You Only Look Once (YOLO) based, optimized ship detection model called YOLO-OSD. Our optimized ship detector is based on a hybrid data-model centric approach which utilizes the statistical characteristics of the datasets under observation and has an efficient model architecture. We also carry out a detailed comparative analysis of our proposed model with other SOTA deep learning models on three well-known publicly available datasets. Our results show that the proposed YOLO-OSD outperforms YOLO5, YOLO7 and RetinaNet on all datasets under observation in terms of F1 score and mean Average Precision (mAP). YOLO-OSD also has approximately 16% fewer network parameters as compared to the original YOLO5. Moreover, our proposed model is at least 37.7% faster than YOLO7 and 41.02% faster than the YOLO8 model in terms of training time and thus suitable for real-time satellite based SAR ship detection.
“…Other hyperparameters are the same as the default values in MMDetection. Four assessment indicators, precision, recall, F1 score, and AP (short for "average precision", a quality assessment index used in the literature), as given below [41], were used to gauge how well our proposed strategy performed.…”
The use of deep learning-based techniques has improved the performance of synthetic aperture radar (SAR) image-based applications, such as ship detection. However, all existing methods have limited object detection performance under the conditions of varying ship sizes and complex background noise, to the best of our knowledge. In this paper, to solve both the multi-scale problem and the noisy background issues, we propose a multi-layer attention approach based on the thorough analysis of both location and semantic information. The solution works by exploring the richness of spatial information of the low-level feature maps generated by a backbone and the richness of semantic information of the high-level feature maps created by the same method. Additionally, we integrate an attention mechanism into the network to exclusively extract useful features from the input maps. Tests involving multiple SAR datasets show that our proposed solution enables significant improvements to the accuracy of ship detection regardless of vessel size and background complexity. Particularly for the widely-adopted High-Resolution SAR Images Dataset (HRSID), the new method provides a 1.3% improvement in the average precision for detection. The proposed new method can be potentially used in other feature-extraction-based classification, detection, and segmentation.
“…S YNTHETIC Aperture Radar (SAR) stands as an active microwave remote sensing device employing virtual array and pulse compression technologies to acquire high-resolution two-dimensional images of ground objects. Because of its unique system and rich polarization information, SAR images find extensive use in various civilian and military applications [1], [2], [3] such as urban planning, environmental and natural disaster monitoring, and ship target detection. Among them, ship target detection serves the purpose of identifying and locating vessels automatically and holds significant importance in monitoring and ensuring the security of coastal areas and waterways.…”
Synthetic aperture radar (SAR) is widely used for ship target detection with the application of deep learning techniques. However, in certain complex environments such as near shore or with small ships, the problem of false alarms and missed detections still exists. To address these issues, a high-precision ship target detection method named DBW-YOLO, which builds upon YOLOv7-tiny as its foundational network, is proposed in this paper. The proposed method consists of the following main steps. Firstly, a feature extraction enhancement network based on deformable convolution network (DCNet) is introduced to obtain more comprehensive feature representations across various ship types. Secondly, an adaptive feature recognition method based on BiFormer attention mechanism is proposed to strengthen detection accuracy, which is more beneficial to capture near shore ships and small ships. Thirdly, a Wise Intersection-over-Union (Wise IoU) based on dynamic non-monotonic focusing mechanism is proposed to generate the loss function, which improves the convergence speed and generalization ability. Consequently, the DBW-YOLO method trains a more robust model that better utilizes samples from near shore and small ships. To verify the effectiveness of this method, two SAR datasets, HRSID and SSDD, are employed for performance evaluation. Compared to other widely-used methods, the mAP value of DBW-YOLO reachs 88.84% and 99.18% on the HRSID and SSDD datasets, respectively. The findings indicate that DBW-YOLO method outperforms other representative SAR ship detection methods in both accuracy and overall performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.