Multi-Size Convolution and Learning Deep Network for SAR Ship Detection From Scratch

Abstract

Synthetic aperture radar (SAR) ship detection is a popular branch of SAR interpretation. A growing number of scholars are devoting themselves to applying convolutional neural network (CNN) to SAR ship detection. Currently, most CNN-based SAR ship detectors are variants of object detectors in optical images; however, the essential differences between SAR and optical images restrict their performance. To this end, by focusing on the attribute of SAR image's "point" property which is determined by its imaging mechanism, we design a novel SAR ship detector from scratch. The innovatively designed PCB-MSK (parallel convolutional block of multi-size kernels) consists of two groups of convolutions, each group is composed of four convolutional layers corresponding to kernel sizes of 3, 5, 7, and 9; the stride is 1 for one group and 2 for another. In the designed convolutional module with features reused (CMFR), the output and input feature maps of the previous block are concatenated for current layer to reduce information loss during forward propagation and to strengthen the supervision for shallow layers during parameter optimization. For each source prediction layer, the binary classification is first conducted to alleviate the positive/negative imbalance; deconvolution and feature fusion are utilized to enhance the feature representation. Then, we perform fine detection. Experiments on RDISD-SAR and SSDD, in which RDISD-SAR is meticulously constructed by us based on two open-access datasets, show that our method achieves a state-of-the-art accuracy and competitive speed, the average precision (AP) reaches 88.70% and 90.57% for RDISD-SAR and SSDD, respectively. These APs are 10.43% and 4.23% higher than DSOD, and 6.64% and 1.70% higher than ScratchDet. The detection speed is 58.2 FPS on a GTX 1080Ti GPU, the number of parameters is 18.19M and the amount of computations is 21.33G. In addition, experimental results show that the robustness of our detector is very excellent.

An Efficient Center-Based Method With Multilevel Auxiliary Supervision for Multiscale SAR Ship Detection

“…In the future, the fast detection of ship targets in SAR images with fewer omissions of extremely small ships will be investigated. VGG16 256×256 ------------------0.7880 Jiao [32] ResNet101 512×512 75.00 ------0.9670 0.8340 0.8960 ---Zhang [44] LSSD 300×300 ------------------0.8012 Cui [34] Resnet101 ---------------------0.8980 Han [47] PCBMSK 320×320…”

“…Chang et al [46] propose a You Only Look Once (YOLO)-based ship detector, where the depth of DCNN is significantly reduced to save the computation cost of target detection. In [47], Han et al design a new DCNN structure with the parallel convolutional blocks to improve the robustness of detection performance of ship targets versus various background conditions. Recently, Mao et al [48] use two simplified U-nets as the backbone network and adopt the center-based framework [25,27].…”

SAR Ship Detection Dataset (SSDD): Official Release and Comprehensive Data Analysis

“…Such a rule can also maintain the distribution consistency of the training set and test set, which is conducive to network feature learning. More information on distribution consistency can be found in the work of Han et al [66][67][68]. Moreover, the official released SSDD does not provide the unique validation set.…”

Deep ensemble model-based moving object detection and classification using SAR images

“…Some quality factors of the image are contrast, brightness, spatial resolution, noise, and artifacts. Remote sensing is also used in various studies, such as oceanography, geography, agriculture, geology, and ecology, to interpret objects or patterns and detect those that may be more informative (Han et al, 2020;Saha et al, 2021). In image processing, the first task is high-level analysis like reorganization, identification, and interpretation.…”