Next Article in Journal
Properties Analysis of Lunar Regolith at Chang’E-4 Landing Site based on 3D Velocity Spectrum of Lunar Penetrating Radar
Next Article in Special Issue
Comparison of the Remapping Algorithms for the Advanced Technology Microwave Sounder (ATMS)
Previous Article in Journal
The Determination of Aerosol Distribution by a No-Blind-Zone Scanning Lidar
Previous Article in Special Issue
Cirrus Detection Based on RPCA and Fractal Dictionary Learning in Infrared imagery
Open AccessArticle

Remote Sensing Image Ship Detection under Complex Sea Conditions Based on Deep Semantic Segmentation

Department of Information Science and Technology, Dalian Maritime University, Dalian 116026, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(4), 625; https://doi.org/10.3390/rs12040625
Received: 9 January 2020 / Revised: 7 February 2020 / Accepted: 11 February 2020 / Published: 13 February 2020
(This article belongs to the Special Issue Computer Vision and Machine Learning Application on Earth Observation)
Under complex sea conditions, ship detection from remote sensing images is easily affected by sea clutter, thin clouds, and islands, resulting in unreliable detection results. In this paper, an end-to-end convolution neural network method is introduced that combines a deep convolution neural network with a fully connected conditional random field. Based on the Resnet architecture, the remote sensing image is roughly segmented using a deep convolution neural network as the input. Using the Gaussian pairwise potential method and mean field approximation theorem, a conditional random field is established as the output of the recurrent neural network, thus achieving end-to-end connection. We compared the proposed method with other state-of-the-art methods on the dataset established by Google Earth and NWPU-RESISC45. Experiments show that the target detection accuracy of the proposed method and the ability of capturing fine details of images are improved. The mean intersection over union is 83.2% compared with other models, which indicates obvious advantages. The proposed method is fast enough to meet the needs for ship detection in remote sensing images.
Keywords: remote sensing image; semantic segmentation; convolution neural network; atrous convolution; fully connected conditional random field remote sensing image; semantic segmentation; convolution neural network; atrous convolution; fully connected conditional random field
Show Figures

Graphical abstract

MDPI and ACS Style

Chen, Y.; Li, Y.; Wang, J.; Chen, W.; Zhang, X. Remote Sensing Image Ship Detection under Complex Sea Conditions Based on Deep Semantic Segmentation. Remote Sens. 2020, 12, 625.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop