Laser & Optoelectronics Progress, Volume. 58, Issue 4, 0400005(2021)
Survey of Ship Detection in SAR Images Based on Deep Learning
Figures & Tables(12)
Fig. 9. Different target borders. (a) Target minimum outbound vertical border; (b) target minimum outbound rectangular border
Table 1. Existing SAR ship datasets
View tableTable 1. Existing SAR ship datasets
Dataset Open SAR ship SSDD SAR-ship-dataset AIR-SARship-1.0 Data information There are 11346 slices, including ten types of ships There are 1160 slices, including 2456 ships There are 43819 slices, including 59535 ships There are 31 scenes in Gaofen No. 3 SAR image Advantage 1st ship target dataset to provide benchmark data for researchers in this field The dataset contains SAR images with different resolution, polarization, sea condition, large sea area and landing conditions There has been a large-scale increase in the amount of data and the types of ships Including ports, islands and reefs, different levels of sea conditions, the background covers variety of scenes, such as inshore and offshore Shortcoming The number of samples among categories is not balanced, so it is difficult to train a better classification model The amount of data is still lacking Most of the datasets are offshore background, the nearshore background is less, and the background is relatively simple The types of vessels are still civilian ships
Table 2. Comparison of traditional data augmentation methods
View tableTable 2. Comparison of traditional data augmentation methods
Method Operation method Advantage Shortcoming Geometric transformation Translation G'(i',j')=G(i+x,j+y) Enrich the position and scale of objects in the image The effect is not ideal in location-sensitive tasks Rotation W'=Wcos θ+Qsin θ Q'=-Wsin θ+Qcos θ Cutting Random image clipping using a certain overlap ratio After cropping, the output needs to be scaled to a fixed size, which may cause image distortion Zoom Randomly select the expansion scale, place the original image in the lower right corner of the expansion image, and fill other blank areas with channel mean Optical transformation Hue Randomly add a real number to each point in the image with a probability of 0.5 Add images under different lights and scenes In the case that the edge of the SAR image itself is not clear, it may cause the model to be difficult to converge Saturation degree Randomly multiply each point in the image by a real number in the HSV gamut space Increase noise Gaussian/salt-and- pepper noise G'(i',j')=G(i,j)+N G'(i',j')=G(i,j)·N Generate robustness to natural disturbances and improve the generalization ability of the model Excessive noise affects the output of the model Data source expansion Change the background Combine detected objects with other background images Increase the richness of the dataset The morphological characteristics of the target itself have not been changed
Table 3. Comparison of algorithms in SAR ship target detection
View tableTable 3. Comparison of algorithms in SAR ship target detection
Category Method Advantage Shortcoming Target feature extraction Characteristic pyramid The problem of multi-scale detection is improved The lower sampling rate is large, which makes the edge of the object difficult to predict, increases the difficulty of returning to the boundary, and multiple up-sampling operations increase the difficulty of detection Super dense connection The problem of gradient disappearance has been solved to some extent; a large number of features are reused and the number of channels of the feature graph is small Multiple data replication is required, and certain video memory optimization techniques are needed CBAM Improve the accuracy of detection The speed has an impact Context fusion Integrate background information, model the relationship between objects, and improve the understanding of the scene Introduce non-target information Target border design Direction design Fit the multi-angle characteristics of warship Additional parameters need to be redesigned Scale design The anchor frame is more in line with the characteristics of the dataset itself The more the number of anchor involved in the clustering process, the higher the accuracy, but at the same time, it will increase the amount of computation
Tools
Get Citation
Copy Citation Text
Xiaohan Hou, Guodong Jin, Lining Tan. Survey of Ship Detection in SAR Images Based on Deep Learning[J]. Laser & Optoelectronics Progress, 2021, 58(4): 0400005
Paper Information
Category: Reviews
Received: Jul. 8, 2020
Accepted: Aug. 13, 2020
Published Online: Feb. 24, 2021
The Author Email: Hou Xiaohan (jinguodong_army@163.com), Jin Guodong (jinguodong_army@163.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20