SemiSegSAR: A Semi-Supervised Segmentation Algorithm for Ship SAR Images

El, Marwa Chendeb; Giraldo, Jhony H.; Al-Saad, Mina; Darweech, Muna; Bouwmans, Thierry

doi:10.1109/lgrs.2022.3185306

Cited by 13 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Subsequently, weak supervision [159], [160] or unsupervised [161], [162] approaches have been proposed. Rai et al [163] proposed a semisupervised segmentation algorithm named SemiSegSAR, which need only label a small amount of data to obtain a satisfactory performance on public ship datasets. Chen et al [102] successfully augmented and enhanced the maritime dataset using an improved GAN.…”

Section: Data Expansion and Enhancementmentioning

confidence: 99%

Sea-Surface Object Detection Based on Electro-Optical Sensors: A Review

Lyu

Shao

Cheng

et al. 2023

IEEE Intell. Transport. Syst. Mag.

View full text Add to dashboard Cite

Sea-surface object detection is critical for navigation safety of autonomous ships. Electrooptical (EO) sensors, such as video cameras, complement radar on board in detecting small obstacle sea-surface objects. Traditionally, researchers have used horizon detection, background subtraction, and foreground segmentation techniques to detect sea-surface objects. Recently, deep learning-based object detection technologies have been gradually applied to sea-surface object detection. This article demonstrates a comprehensive overview of sea-surface object-detection approaches where the advantages and drawbacks of each technique are compared, covering four essential aspects: EO sensors and image types, traditional object-detection methods, deep learning methods, and maritime datasets collection. In particular, sea-surface object detections based on deep learning methods are thoroughly analyzed and compared with highly influential public datasets introduced as benchmarks to verify the effectiveness of these approaches. The article also proposes the direction of future research for sea-surface object detection based on EO sensors.

show abstract

Section: Data Expansion and Enhancementmentioning

confidence: 99%

Sea-Surface Object Detection Based on Electro-Optical Sensors: A Review

Lyu

Shao

Cheng

et al. 2023

IEEE Intell. Transport. Syst. Mag.

View full text Add to dashboard Cite

show abstract

“…SAR has unique imaging characteristics and can be used as complementary data to complete semantic segmentation tasks. One study [181] has proposed using the texture and statistical features as nodes of a graph based on the data distribution characteristics of RSIs. A semi-supervised approach was also used to complete the instance segmentation of ships.…”

Section: Semi-supervised Learning Models Based On Rsis For Semantic S...mentioning

confidence: 99%

Deep Learning Methods for Semantic Segmentation in Remote Sensing with Small Data: A Survey

Yu,

Quan,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

The annotations used during the training process are crucial for the inference results of remote sensing images (RSIs) based on a deep learning framework. Unlabeled RSIs can be obtained relatively easily. However, pixel-level annotation is a process that necessitates a high level of expertise and experience. Consequently, the use of small sample training methods has attracted widespread attention as they help alleviate reliance on large amounts of high-quality labeled data and current deep learning methods. Moreover, research on small sample learning is still in its infancy owing to the unique challenges faced when completing semantic segmentation tasks with RSI. To better understand and stimulate future research that utilizes semantic segmentation tasks with small data, we summarized the supervised learning methods and challenges they face. We also reviewed the supervised approaches with data that are currently popular to help elucidate how to efficiently utilize a limited number of samples to address issues with semantic segmentation in RSI. The main methods discussed are self-supervised learning, semi-supervised learning, weakly supervised learning and few-shot methods. The solution of cross-domain challenges has also been discussed. Furthermore, multi-modal methods, prior knowledge constrained methods, and future research required to help optimize deep learning models for various downstream tasks in relation to RSI have been identified.

show abstract

“…Min et al [44] improves the performance of SSD algorithm by redesigning the shallow network structure and enlarging the receptive field of features, which raises the accuracy about 7% while reduce the model's size. For the cases of overcoming fewer training samples, Rai et al [45] proposes a semi-supervised segmentation algorithm for ship SAR images which requires only a few labeled samples to outperforms the current mainstream semi-supervised and supervised models. Chen et al [46] devises a semi-supervised learning strategy which makes full use of unlabeled ship data and iteratively outputs higher-quality labeled samples, and the comprehensive results shows the superiority of the proposed model.…”

Section: Related Workmentioning

confidence: 99%

A Novel Anchor-Free Model With Salient Feature Fusion Mechanism for Ship Detection in SAR Images

Gao,

Wu,

Ren

2023

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

View full text Add to dashboard Cite

Ship detection in synthetic aperture radar (SAR) images has gained great attention in civil and military fields. Anchor-based detection algorithms usually rely on preset candidate boxes, and a large amount of anchor boxes with different sizes will result in a large amount of computing resources being consumed. Recently, anchor-free algorithms have found wide applications in ship detection from SAR images. However, there are still some problems which limit the ship detection performance to a certain extent, such as how to effectively fuse salient features and unbalanced distribution of positive samples. In order to tackle the above problems, we propose a novel anchor-free model named SFF-YOLOX with salient feature fusion (SFF) mechanism. Firstly, we redesign the network of YOLOX to obtain the best balance between detection accuracy and running speed. Secondly, a saliency region extraction (SRE) module is introduced to generate the corresponding salient guide map of the input image. Besides, the SFF mechanism is proposed by fusing deep features and salient features to better enhance the discrimination of the multiscale targets. Finally, we improve the SimOTA mechanism by combining the predicted IoUs (intersection over union) and the anchor IoUs to the ground truth bounding boxes to instruct label assignment. We evaluate the detection accuracy and running speed of SFF-YOLOX on the public dataset SSD and test the generalization ability on HRSID and two complex large-scale SAR images, the experimental results prove the model's effectiveness for ship detection task in SAR images.

show abstract

SemiSegSAR: A Semi-Supervised Segmentation Algorithm for Ship SAR Images

Cited by 13 publications

References 31 publications

Sea-Surface Object Detection Based on Electro-Optical Sensors: A Review

Sea-Surface Object Detection Based on Electro-Optical Sensors: A Review

Deep Learning Methods for Semantic Segmentation in Remote Sensing with Small Data: A Survey

A Novel Anchor-Free Model With Salient Feature Fusion Mechanism for Ship Detection in SAR Images

Contact Info

Product

Resources

About