A Hierarchical Convolution Neural Network (CNN)-Based Ship Target Detection Method in Spaceborne SAR Imagery

Jun Wang,Peng Lei,Xiao Bai,Tong Zheng

doi:10.3390/rs11060620

Jun Wang, Peng Lei + Show 2 more

Open Access

https://doi.org/10.3390/rs11060620

Copy DOI

Journal: Remote sensing	Publication Date: Mar 14, 2019
Citations: 29	License type: CC BY 4.0

Affiliation: Beihang University

Abstract

The ghost phenomenon in synthetic aperture radar (SAR) imaging is primarily caused by azimuth or range ambiguities, which cause difficulties in SAR target detection application. To mitigate this influence, we propose a ship target detection method in spaceborne SAR imagery, using a hierarchical convolutional neural network (H-CNN). Based on the nature of ghost replicas and typical target classes, a two-stage CNN model is built to detect ship targets against sea clutter and the ghost. First, regions of interest (ROIs) were extracted from a large imaged scene during the coarse-detection stage. Unwanted ghost replicas represented major residual interference sources in ROIs, therefore, the other CNN process was executed during the fine-detection stage. Finally, comparative experiments and analyses, using Sentinel-1 SAR data and various assessment criteria, were conducted to validate H-CNN. Our results showed that the proposed method can outperform the conventional constant false-alarm rate technique and CNN-based models.

Highlights

Synthetic aperture radar (SAR) is an active microwave sensor, whose resolution—both in range and azimuth—can be improved via the pulse compression technique and synthetic aperture principle, to obtain high resolution remote sensing images
According to the ghost generating principle and characteristics, we provided a hierarchical convolutional neural network (CNN)-based ship target detection method in spaceborne SAR imagery, i.e., hierarchical convolutional neural network (H-CNN)
Hyperparameters of convolutional kernels play a key role in the H-CNN performance

Summary

Introduction

Synthetic aperture radar (SAR) is an active microwave sensor, whose resolution—both in range and azimuth—can be improved via the pulse compression technique and synthetic aperture principle, to obtain high resolution remote sensing images. Li et al [18,19] improved detection performance using Faster R-CNN, to successfully provide a densely connected multi-scale neural network [19] This method is used to solve multi-scale and multi-scene problems in SAR ship detection. Hamza and Cai used YOLOv2 for ship detection [21], which introduced a multitude of enhancements into the original YOLO model These methods may be no longer effective when ghost replicas exist in an imaged scene. The Doppler frequency, which is higher than pulse repetition frequency (PRF), may lead to azimuth ambiguity [25] This phenomenon is relevant for high reflectivity targets, which appears in SAR images as ghosts in low reflectivity areas [26]. According to the ghost generating principle and characteristics, we provided a hierarchical CNN-based ship target detection method in spaceborne SAR imagery, i.e., H-CNN. We conduct detection experiments to validate the H-CNN, and compare it to conventional CFAR technique and CNN models

Ghost Phenomenon in Spaceborne SAR

Dataset

G-4 T-2 T-5

Discussion of Parameter Configuration of H-CNN

H-10-7 H-10-8 H-10-9

H-10-10 H-10-11

Detection Result Comparison