Visual saliency modeling for river detection in high-resolution SAR imagery

Fei Gao, Fei Ma, Jun Wang, Jinping Sun, Erfu Yang, Huiyu Zhou

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Accurate detection of rivers plays a significant role in water conservancy construction and ecological protection, where airborne Synthetic Aperture Radar (SAR) data has already become one of the main sources. However, extracting river information from radar data efficiently and accurately still remains an open problem. The existing methods for detecting rivers are typically based on rivers’ edges, which are easily mixed with those of artificial buildings or farmland. In addition, pixel based image processing approaches cannot meet the requirement of real time processing. Inspired by the feature integration and target recognition capabilities of biological vision systems, in this paper, we present a hierarchical method for automated detection of river networks in the high-resolution SAR data using biologically visual saliency modeling. For effective saliency detection, the original image is first over-segmented into a set of primitive superpixels. A visual feature (VF) set is designed to extract a regional feature histogram, which is then quantized based on the optimal parameters learned from the labeled SAR images. Afterwards, three saliency measurements based on the specificity of the rivers in the SAR images are proposed to generate a single layer saliency map, i.e., Local Region Contrast (LRC), Boundary Connectivity (BC) and Edge Density (ED). Finally, by exploiting belief propagation, we propose a multi-layer saliency fusion approach to derive a high-quality saliency map. Extensive experimental results on three airborne SAR image datasets with the ground truth demonstrate that the proposed saliency model consistently outperforms the existing saliency target detection models.

LanguageEnglish
Pages1000-1014
Number of pages15
JournalIEEE Access
Volume6
Early online date24 Nov 2017
DOIs
Publication statusE-pub ahead of print - 24 Nov 2017

Fingerprint

Synthetic aperture radar
Rivers
Target tracking
Radar
Image processing
Fusion reactions
Pixels
Water
Processing

Keywords

  • biological system modeling
  • dogs
  • feature extraction
  • filtering algorithms
  • merging
  • object detection
  • remote sensing
  • Rivers
  • visualization
  • synthetic aperture radar

Cite this

Gao, Fei ; Ma, Fei ; Wang, Jun ; Sun, Jinping ; Yang, Erfu ; Zhou, Huiyu. / Visual saliency modeling for river detection in high-resolution SAR imagery. In: IEEE Access. 2017 ; Vol. 6. pp. 1000-1014.
@article{376ca1c6a14c4a4eb8ee8f862e9cee61,
title = "Visual saliency modeling for river detection in high-resolution SAR imagery",
abstract = "Accurate detection of rivers plays a significant role in water conservancy construction and ecological protection, where airborne Synthetic Aperture Radar (SAR) data has already become one of the main sources. However, extracting river information from radar data efficiently and accurately still remains an open problem. The existing methods for detecting rivers are typically based on rivers’ edges, which are easily mixed with those of artificial buildings or farmland. In addition, pixel based image processing approaches cannot meet the requirement of real time processing. Inspired by the feature integration and target recognition capabilities of biological vision systems, in this paper, we present a hierarchical method for automated detection of river networks in the high-resolution SAR data using biologically visual saliency modeling. For effective saliency detection, the original image is first over-segmented into a set of primitive superpixels. A visual feature (VF) set is designed to extract a regional feature histogram, which is then quantized based on the optimal parameters learned from the labeled SAR images. Afterwards, three saliency measurements based on the specificity of the rivers in the SAR images are proposed to generate a single layer saliency map, i.e., Local Region Contrast (LRC), Boundary Connectivity (BC) and Edge Density (ED). Finally, by exploiting belief propagation, we propose a multi-layer saliency fusion approach to derive a high-quality saliency map. Extensive experimental results on three airborne SAR image datasets with the ground truth demonstrate that the proposed saliency model consistently outperforms the existing saliency target detection models.",
keywords = "biological system modeling, dogs, feature extraction, filtering algorithms, merging, object detection, remote sensing, Rivers, visualization, synthetic aperture radar",
author = "Fei Gao and Fei Ma and Jun Wang and Jinping Sun and Erfu Yang and Huiyu Zhou",
note = "(c) 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.",
year = "2017",
month = "11",
day = "24",
doi = "10.1109/ACCESS.2017.2777444",
language = "English",
volume = "6",
pages = "1000--1014",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "IEEE",

}

Visual saliency modeling for river detection in high-resolution SAR imagery. / Gao, Fei; Ma, Fei; Wang, Jun; Sun, Jinping; Yang, Erfu; Zhou, Huiyu.

In: IEEE Access, Vol. 6, 24.11.2017, p. 1000-1014.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Visual saliency modeling for river detection in high-resolution SAR imagery

AU - Gao, Fei

AU - Ma, Fei

AU - Wang, Jun

AU - Sun, Jinping

AU - Yang, Erfu

AU - Zhou, Huiyu

N1 - (c) 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.

PY - 2017/11/24

Y1 - 2017/11/24

N2 - Accurate detection of rivers plays a significant role in water conservancy construction and ecological protection, where airborne Synthetic Aperture Radar (SAR) data has already become one of the main sources. However, extracting river information from radar data efficiently and accurately still remains an open problem. The existing methods for detecting rivers are typically based on rivers’ edges, which are easily mixed with those of artificial buildings or farmland. In addition, pixel based image processing approaches cannot meet the requirement of real time processing. Inspired by the feature integration and target recognition capabilities of biological vision systems, in this paper, we present a hierarchical method for automated detection of river networks in the high-resolution SAR data using biologically visual saliency modeling. For effective saliency detection, the original image is first over-segmented into a set of primitive superpixels. A visual feature (VF) set is designed to extract a regional feature histogram, which is then quantized based on the optimal parameters learned from the labeled SAR images. Afterwards, three saliency measurements based on the specificity of the rivers in the SAR images are proposed to generate a single layer saliency map, i.e., Local Region Contrast (LRC), Boundary Connectivity (BC) and Edge Density (ED). Finally, by exploiting belief propagation, we propose a multi-layer saliency fusion approach to derive a high-quality saliency map. Extensive experimental results on three airborne SAR image datasets with the ground truth demonstrate that the proposed saliency model consistently outperforms the existing saliency target detection models.

AB - Accurate detection of rivers plays a significant role in water conservancy construction and ecological protection, where airborne Synthetic Aperture Radar (SAR) data has already become one of the main sources. However, extracting river information from radar data efficiently and accurately still remains an open problem. The existing methods for detecting rivers are typically based on rivers’ edges, which are easily mixed with those of artificial buildings or farmland. In addition, pixel based image processing approaches cannot meet the requirement of real time processing. Inspired by the feature integration and target recognition capabilities of biological vision systems, in this paper, we present a hierarchical method for automated detection of river networks in the high-resolution SAR data using biologically visual saliency modeling. For effective saliency detection, the original image is first over-segmented into a set of primitive superpixels. A visual feature (VF) set is designed to extract a regional feature histogram, which is then quantized based on the optimal parameters learned from the labeled SAR images. Afterwards, three saliency measurements based on the specificity of the rivers in the SAR images are proposed to generate a single layer saliency map, i.e., Local Region Contrast (LRC), Boundary Connectivity (BC) and Edge Density (ED). Finally, by exploiting belief propagation, we propose a multi-layer saliency fusion approach to derive a high-quality saliency map. Extensive experimental results on three airborne SAR image datasets with the ground truth demonstrate that the proposed saliency model consistently outperforms the existing saliency target detection models.

KW - biological system modeling

KW - dogs

KW - feature extraction

KW - filtering algorithms

KW - merging

KW - object detection

KW - remote sensing

KW - Rivers

KW - visualization

KW - synthetic aperture radar

UR - http://www.scopus.com/inward/record.url?scp=85035772244&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2017.2777444

DO - 10.1109/ACCESS.2017.2777444

M3 - Article

VL - 6

SP - 1000

EP - 1014

JO - IEEE Access

T2 - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -