Probabilistic ship detection and classification using deep learning

Kwanghyun Kim, Sungjun Hong, Baehoon Choi, Euntai Kim

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

For an autonomous ship to navigate safely and avoid collisions with other ships, reliably detecting and classifying nearby ships under various maritime meteorological environments is essential. In this paper, a novel probabilistic ship detection and classification system based on deep learning is proposed. The proposed method aims to detect and classify nearby ships from a sequence of images. The method considers the confidence of a deep learning detector as a probability; the probabilities from the consecutive images are combined over time by Bayesian fusion. The proposed ship detection system involves three steps. In the first step, ships are detected in each image using Faster region-based convolutional neural network (Faster R-CNN). In the second step, the detected ships are gathered over time and the missed ships are recovered using the Intersection over Union of the bounding boxes between consecutive frames. In the third step, the probabilities from the Faster R-CNN are combined over time and the classes of the ships are determined by Bayesian fusion. To train and evaluate the proposed system, we collected thousands of ship images from Google image search and created our own ship dataset. The proposed method was tested with the collected videos and the mean average precision increased by 89.38 to 93.92% in experimental results.

Original languageEnglish
Article number936
JournalApplied Sciences (Switzerland)
Volume8
Issue number6
DOIs
Publication statusPublished - 2018 Jun 5

Fingerprint

ships
learning
Ships
Deep learning
Fusion reactions
fusion
Neural networks
classifying
intersections
boxes
confidence
Detectors

All Science Journal Classification (ASJC) codes

  • Materials Science(all)
  • Instrumentation
  • Engineering(all)
  • Process Chemistry and Technology
  • Computer Science Applications
  • Fluid Flow and Transfer Processes

Cite this

Kim, Kwanghyun ; Hong, Sungjun ; Choi, Baehoon ; Kim, Euntai. / Probabilistic ship detection and classification using deep learning. In: Applied Sciences (Switzerland). 2018 ; Vol. 8, No. 6.
@article{920c1606008f4669b82ccbc479bd04a7,
title = "Probabilistic ship detection and classification using deep learning",
abstract = "For an autonomous ship to navigate safely and avoid collisions with other ships, reliably detecting and classifying nearby ships under various maritime meteorological environments is essential. In this paper, a novel probabilistic ship detection and classification system based on deep learning is proposed. The proposed method aims to detect and classify nearby ships from a sequence of images. The method considers the confidence of a deep learning detector as a probability; the probabilities from the consecutive images are combined over time by Bayesian fusion. The proposed ship detection system involves three steps. In the first step, ships are detected in each image using Faster region-based convolutional neural network (Faster R-CNN). In the second step, the detected ships are gathered over time and the missed ships are recovered using the Intersection over Union of the bounding boxes between consecutive frames. In the third step, the probabilities from the Faster R-CNN are combined over time and the classes of the ships are determined by Bayesian fusion. To train and evaluate the proposed system, we collected thousands of ship images from Google image search and created our own ship dataset. The proposed method was tested with the collected videos and the mean average precision increased by 89.38 to 93.92{\%} in experimental results.",
author = "Kwanghyun Kim and Sungjun Hong and Baehoon Choi and Euntai Kim",
year = "2018",
month = "6",
day = "5",
doi = "10.3390/app8060936",
language = "English",
volume = "8",
journal = "Applied Sciences (Switzerland)",
issn = "2076-3417",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "6",

}

Probabilistic ship detection and classification using deep learning. / Kim, Kwanghyun; Hong, Sungjun; Choi, Baehoon; Kim, Euntai.

In: Applied Sciences (Switzerland), Vol. 8, No. 6, 936, 05.06.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Probabilistic ship detection and classification using deep learning

AU - Kim, Kwanghyun

AU - Hong, Sungjun

AU - Choi, Baehoon

AU - Kim, Euntai

PY - 2018/6/5

Y1 - 2018/6/5

N2 - For an autonomous ship to navigate safely and avoid collisions with other ships, reliably detecting and classifying nearby ships under various maritime meteorological environments is essential. In this paper, a novel probabilistic ship detection and classification system based on deep learning is proposed. The proposed method aims to detect and classify nearby ships from a sequence of images. The method considers the confidence of a deep learning detector as a probability; the probabilities from the consecutive images are combined over time by Bayesian fusion. The proposed ship detection system involves three steps. In the first step, ships are detected in each image using Faster region-based convolutional neural network (Faster R-CNN). In the second step, the detected ships are gathered over time and the missed ships are recovered using the Intersection over Union of the bounding boxes between consecutive frames. In the third step, the probabilities from the Faster R-CNN are combined over time and the classes of the ships are determined by Bayesian fusion. To train and evaluate the proposed system, we collected thousands of ship images from Google image search and created our own ship dataset. The proposed method was tested with the collected videos and the mean average precision increased by 89.38 to 93.92% in experimental results.

AB - For an autonomous ship to navigate safely and avoid collisions with other ships, reliably detecting and classifying nearby ships under various maritime meteorological environments is essential. In this paper, a novel probabilistic ship detection and classification system based on deep learning is proposed. The proposed method aims to detect and classify nearby ships from a sequence of images. The method considers the confidence of a deep learning detector as a probability; the probabilities from the consecutive images are combined over time by Bayesian fusion. The proposed ship detection system involves three steps. In the first step, ships are detected in each image using Faster region-based convolutional neural network (Faster R-CNN). In the second step, the detected ships are gathered over time and the missed ships are recovered using the Intersection over Union of the bounding boxes between consecutive frames. In the third step, the probabilities from the Faster R-CNN are combined over time and the classes of the ships are determined by Bayesian fusion. To train and evaluate the proposed system, we collected thousands of ship images from Google image search and created our own ship dataset. The proposed method was tested with the collected videos and the mean average precision increased by 89.38 to 93.92% in experimental results.

UR - http://www.scopus.com/inward/record.url?scp=85048098070&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048098070&partnerID=8YFLogxK

U2 - 10.3390/app8060936

DO - 10.3390/app8060936

M3 - Article

AN - SCOPUS:85048098070

VL - 8

JO - Applied Sciences (Switzerland)

JF - Applied Sciences (Switzerland)

SN - 2076-3417

IS - 6

M1 - 936

ER -