A Novel Coarse-to-Fine Method of Ship Detection in Optical Remote Sensing Images Based on a Deep Residual Dense Network

Chen, Liqiong; Shi, Wenxuan; Fan, Cien; Zou, Lian; Deng, Dexiang

doi:10.3390/rs12193115

Cited by 10 publications

(11 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Optical remote sensing image, with its high spatial resolution, makes up for the shortage of other remote sensing data to a great extent and thus is widely used [10,11]. Still, the traditional ship classification algorithm of optical remote sensing images mostly uses manually designed features [9,[12][13][14], these features are easily affected by some clouds and waves, and the robustness is poor [15], which is not suitable for large-scale and multi-scene ship target recognition [16].…”

Section: Introductionmentioning

confidence: 99%

“…The latest research found that using a multi-scale feature extraction network to extract multi-scale features, the capacity to enhance model accuracies in ship extraction [28]. However, most networks only distinguish between ships and non-ships, with high intra-class variation causing misclassification [16]. Multiclass methods [12,16,29] provide a viable solution because the results have more categories, and more detailed ship information can be extracted.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multilayer Feature Extraction Network for Military Ship Detection From High-Resolution Optical Remote Sensing Images

Qin¹,

Cai²,

Liu³

et al. 2021

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

View full text Add to dashboard Cite

Rapid and accurate detection of maritime military targets is of great significance for maintaining national defence security. Few studies have used high-resolution optical images for the detailed classification of maritime military targets. This paper, inspired by EfficientDet trackers, presents a method to classify military targets on the sea from high-resolution optical remote sensing images. In the first stage, a multi-layer feature extraction network is constructed to extract various features. At the same time, residual connection and dilation convolution are introduced to prevent the deep network features from disappearing. Moreover, we use multi-level attention mechanism approaches to make more effective use of multi-layer features. ReLU is introduced to replace the original swish activation function to reduce the computational cost in the pretreatment stage; After this, deep feature fusion networks and prediction networks are constructed to locate and distinguish different types of ships. Different types of ships use different degrees of data expansion methods to solve the problem of sample shortage and imbalance; The multi-classification method is used to solve low classification accuracy caused by little difference between civil and military ships. Experimental results suggested that the proposed method can accurately identify multiple types of military ships.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multilayer Feature Extraction Network for Military Ship Detection From High-Resolution Optical Remote Sensing Images

Qin¹,

Cai²,

Liu³

et al. 2021

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

View full text Add to dashboard Cite

show abstract

“…However, the noisy response and low resolution of SAR images [11] may limit their utilizations. In recent years, attributing to the improvement of high-resolution technology, some researchers [12][13][14][15][16] have paid more attention to using optical remote sensing images because they could provide more details and spatial contents for detecting ships than SAR images.…”

Section: Introductionmentioning

confidence: 99%

“…Due to the massive amount of generated ROIs, the computation is time-consuming and the model efficiency may be reduced. Chen et al [16] also designed a hierarchical detection process which applied discrete wavelet transform (DWT) to extract ship candidate regions and proposed deep residual dense network (DRDN) to improve the ship detection accuracy. The aforementioned two-stage detection methods mainly focus on improving the ship detection accuracy; however, they may ignore the detection speed.…”

Section: Introductionmentioning

confidence: 99%

Improved YOLOv3 Based on Attention Mechanism for Fast and Accurate Ship Detection in Optical Remote Sensing Images

2021

Self Cite

View full text Add to dashboard Cite

Ship detection is an important but challenging task in the field of computer vision, partially due to the minuscule ship objects in optical remote sensing images and the interference of clouds occlusion and strong waves. Most of the current ship detection methods focus on boosting detection accuracy while they may ignore the detection speed. However, it is also indispensable to increase ship detection speed because it can provide timely ocean rescue and maritime surveillance. To solve the above problems, we propose an improved YOLOv3 (ImYOLOv3) based on attention mechanism, aiming to achieve the best trade-off between detection accuracy and speed. First, to realize high-efficiency ship detection, we adopt the off-the-shelf YOLOv3 as our basic detection framework due to its fast speed. Second, to boost the performance of original YOLOv3 for small ships, we design a novel and lightweight dilated attention module (DAM) to extract discriminative features for ship targets, which can be easily embedded into the basic YOLOv3. The integrated attention mechanism can help our model learn to suppress irrelevant regions while highlighting salient features useful for ship detection task. Furthermore, we introduce a multi-class ship dataset (MSD) and explicitly set supervised subclass according to the scales and moving states of ships. Extensive experiments verify the effectiveness and robustness of ImYOLOv3, and show that our method can accurately detect ships with different scales in different backgrounds, while at a real-time speed.

show abstract

“…Different excellent deep learning networks have been applied for feature extraction. For instance, in [13] a residual dense network is exploited to learn the features of different levels. Similarly, a pyramid structure is used to learn features of multi-scale rotating targets, which can accurately detect dense targets in various complex scenes [14].…”

Section: Introductionmentioning

confidence: 99%

Salient Ship Detection via Background Prior and Foreground Constraint in Remote Sensing Images

Zhi

Zhang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Automatic ship detection in complicated maritime background is a challenging task in the field of optical remote sensing image interpretation and analysis. In this paper, we propose a novel and reliable ship detection framework based on a visual saliency model, which can efficiently detect multiple targets of different scales in complex scenes with sea clutter, clouds, wake and islands interferences. Firstly, we present a reliable background prior extraction method adaptive for the random locations of targets by computing boundary probability and then generate a saliency map based on the background prior. Secondly, we compute the prior probability of salient foreground regions and propose a weighting function to constrain false foreground clutter, gaining the foreground-based prediction map. Thirdly, we integrate the two prediction maps and improve the details of the integrated map by a guided filter function and a wake adjustment function, obtaining the fine selection of candidate regions. Afterwards, a classification is further performed to reduce false alarms and produce the final ship detection results. Qualitative and quantitative evaluations on two public available datasets demonstrate the robustness and efficiency of the proposed method against four advanced baseline methods.

show abstract

A Novel Coarse-to-Fine Method of Ship Detection in Optical Remote Sensing Images Based on a Deep Residual Dense Network

Cited by 10 publications

References 46 publications

Multilayer Feature Extraction Network for Military Ship Detection From High-Resolution Optical Remote Sensing Images

Multilayer Feature Extraction Network for Military Ship Detection From High-Resolution Optical Remote Sensing Images

Improved YOLOv3 Based on Attention Mechanism for Fast and Accurate Ship Detection in Optical Remote Sensing Images

Salient Ship Detection via Background Prior and Foreground Constraint in Remote Sensing Images

Contact Info

Product

Resources

About