Arbitrary-Oriented Ellipse Detector for Ship Detection in Remote Sensing Images

Zhou, Kexue; Zhang, Min; Hu, Zhao; Tang, Rui; Lin, Sheng; Cheng, Xi; Wang, Hai

doi:10.1109/jstars.2023.3267240

Cited by 8 publications

(12 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method fundamentally addressed the boundary issue of angle regression. Zhou et al [100] proposed an ellipse method, represented by (x, y, |u|, |v|, m, α), as shown in Figure 15b, where α = 0 represents that the ship belongs to the second and fourth quadrants; α = 1 represents that the ship belongs to the first and third quadrants. Furthermore, m is the difference between the length of the major axis and the focal vector.…”

Section: Obb Representation and Regression-based Methodsmentioning

confidence: 99%

Ship Detection with Deep Learning in Optical Remote-Sensing Images: A Survey of Challenges and Advances

Zhao,

Wang,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Ship detection aims to automatically identify whether there are ships in the images, precisely classifies and localizes them. Regardless of whether utilizing early manually designed methods or deep learning technology, ship detection is dedicated to exploring the inherent characteristics of ships to enhance recall. Nowadays, high-precision ship detection plays a crucial role in civilian and military applications. In order to provide a comprehensive review of ship detection in optical remote-sensing images (SDORSIs), this paper summarizes the challenges as a guide. These challenges include complex marine environments, insufficient discriminative features, large scale variations, dense and rotated distributions, large aspect ratios, and imbalances between positive and negative samples. We meticulously review the improvement methods and conduct a detailed analysis of the strengths and weaknesses of these methods. We compile ship information from common optical remote sensing image datasets and compare algorithm performance. Simultaneously, we compare and analyze the feature extraction capabilities of backbones based on CNNs and Transformer, seeking new directions for the development in SDORSIs. Promising prospects are provided to facilitate further research in the future.

show abstract

Section: Obb Representation and Regression-based Methodsmentioning

confidence: 99%

Ship Detection with Deep Learning in Optical Remote-Sensing Images: A Survey of Challenges and Advances

Zhao,

Wang,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…To further validate the effectiveness of the proposed method for ship detection, this section compares the proposed SAD-Det with several arbitrarily oriented ship detection methods on RSDD-SAR from both inshore and offshore perspectives. These methods include KeyShip [69], SaDet [27], AEDet [70], and MT-FANet [71]. Since the aforementioned methods are not open source, we reproduce the structure of SaDet and conduct experiments, citing the best experimental results from the other studies as our comparison values.…”

Section: E Comparison With Arbitrarily Oriented Ship Detection Methodsmentioning

confidence: 99%

“…Guo et al [28] introduced a new encoding representation to describe the OBB and incorporated a feature adaptive module to refine each feature pyramid layer. Zhou et al [29] presented a simple ellipse parameters representation method for objects in any direction, utilizing the YOLOX [30] algorithm for directional ship detection and yielding favourable results. Zhou et al [31] designed a new anchorfree keypoint-based detection method called KeyShip for highprecision detection of oriented ships in SAR images.…”

Section: Introductionmentioning

confidence: 99%

An Anchor-Free Method Based on Transformers and Adaptive Features for Arbitrarily Oriented Ship Detection in SAR Images

Chen,

Yu,

Zhao

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Ship detection is a crucial application of synthetic aperture radar (SAR). Most recent studies have relied on convolutional neural networks (CNNs). CNNs tend to struggle in gathering adequate contextual information through local receptive fields and are also susceptible to noise. Inshore scenes in SAR images are plagued by substantial background noise, so achieving high-accuracy ship detection of arbitrary orientations within complex scenes remains an ongoing challenge when relying solely on CNNs. To address the above challenges, this paper presents an anchor-free method based on transformers and adaptive features, namely, SAD-Det, which can detect rotationally invariant ship targets with high average precision in SAR images. Specifically, a transformer-based backbone network called the ship spatial pooling pyramid vision transformer (SSP-PVT) is proposed to enhance the long-range dependencies and obtain sufficient contextual information for ships in SAR images. In addition, a neck network called the adaptive feature pyramid network (AFPN) is designed to enhance the ability of ship feature adaptation by adding fusion factors to feature layers in SAR images. Finally, a head network called the deformable head (DeHead) is constructed to make the network more adaptable to the characteristics of ships by adaptively detecting the spatial sampling positions of the targets in SAR images. The effectiveness of the proposed method is verified by experiments on two publicly available datasets, i.e., SAR ship detection dataset (SSDD) and rotated ship detection dataset in SAR images (RSDD-SAR). Compared with other arbitrarily oriented object detection methods, the proposed method achieves state-of-the-art detection performance.

show abstract

“…The method for determining the long half-axis is reported to be too complicated, and the constraints applied to the parameters appear to be incomplete. For a detailed understanding of the constraints, further information is available in the paper [11]. Additionally, RIE introduces the concept of eccentricitywise orientation loss to achieve more-accurate orientation estimation.…”

Section: Introductionmentioning

confidence: 99%

“…Compared to ProjBB and RIE, Jiang et al's method employs a larger number of parameters to describe the oriented bounding box. In the context of synthetic aperture radar (SAR) ship detection, Zhou et al proposed a new vector-decompositionbased arbitrarily oriented object-detection method called AEDet [11]. AEDet employs six parameters (x, y, |u|, |v|, m, α) to describe the oriented bounding box.…”

Section: Introductionmentioning

confidence: 99%

Vector Decomposition-Based Arbitrary-Oriented Object Detection for Optical Remote Sensing Images

Zhou,

Zhang,

Dong

et al. 2023

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Arbitrarily oriented object detection is one of the most-popular research fields in remote sensing image processing. In this paper, we propose an approach to predict object angles indirectly, thereby avoiding issues related to angular periodicity and boundary discontinuity. Our method involves representing the long edge and angle of an object as a vector, which we then decompose into horizontal and vertical components. By predicting the two components of the vector, we can obtain the angle information of the object indirectly. To facilitate the transformation between angle-based representation and the proposed vector-decomposition-based representation, we introduced two novel techniques: angle-to-vector encode (ATVEncode) and vector-to-angle decode (VTADecode). These techniques not only improve the efficiency of data processing, but also accelerate the training process. Furthermore, we propose an adaptive coarse-to-fine positive–negative-sample-selection (AdaCFPS) method based on the vector-decomposition-based representation of the object. This method utilizes the Kullback–Leibler divergence loss as a matching degree to dynamically select the most-suitable positive samples. Finally, we modified the YOLOX model to transform it into an arbitrarily oriented object detector that aligns with our proposed vector-decomposition-based representation and positive–negative-sample-selection method. We refer to this redesigned model as the vector-decomposition-based object detector (VODet). In our experiments on the HRSC2016, DIOR-R, and DOTA datasets, VODet demonstrated notable advantages, including fewer parameters, faster processing speed, and higher precision. These results highlighted the significant potential of VODet in the context of arbitrarily oriented object detection.

show abstract

Arbitrary-Oriented Ellipse Detector for Ship Detection in Remote Sensing Images

Cited by 8 publications

References 34 publications

Ship Detection with Deep Learning in Optical Remote-Sensing Images: A Survey of Challenges and Advances

Ship Detection with Deep Learning in Optical Remote-Sensing Images: A Survey of Challenges and Advances

An Anchor-Free Method Based on Transformers and Adaptive Features for Arbitrarily Oriented Ship Detection in SAR Images

Vector Decomposition-Based Arbitrary-Oriented Object Detection for Optical Remote Sensing Images

Contact Info

Product

Resources

About