Taking optimal advantage of fine spatial information: promoting partial image reconstruction for the morphological analysis of very-high-resolution images

Wenzhi Liao, Jocelyn Chanussot, Mauro Dalla Mura, Xin Huang, Rik Bellens, Sidharta Gautama, Wilfried Philips

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Diverse sensor technologies have allowed us to measure different aspects of objects on Earth's surface [such as spectral characteristics in hyperspectral images and height in light detection and ranging (LiDAR) data] with increasing spectral and spatial resolutions. Remote-sensing images of very high geometrical resolution can provide a precise and detailed representation of the monitored scene. Thus, the spatial information is fundamental for many applications. Morphological profiles (MPs) and attribute profiles (APs) have been widely used to model the spatial information of very-high-resolution (VHR) remote-sensing images. MPs are obtained by computing a sequence of morphological operators based on geodesic reconstruction. However, both morphological operators based on geodesic reconstruction and attribute filters (AFs) are connected filters and, hence, suffer the problem of leakage (i.e., regions related to different structures in the image that happen to be connected by spurious links are considered as a single object). Objects expected to disappear at a given stage remain present when they connect with other objects in the image. Consequently, the attributes of small objects are mixed with their larger connected objects, leading to poor performances on postapplications (e.g., classification).
LanguageEnglish
Pages8-28
Number of pages21
JournalIEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE
Volume5
Issue number2
DOIs
Publication statusPublished - 12 Jun 2017

Fingerprint

image resolution
image reconstruction
high resolution
remote sensing
profiles
filter
filters
operators
Earth surface
spectral resolution
leakage
spatial resolution
analysis
sensor
sensors
attribute

Keywords

  • image reconstruction
  • feature extraction
  • laser radar
  • spatial resolution
  • hyperspectral Imaging

Cite this

Liao, Wenzhi ; Chanussot, Jocelyn ; Dalla Mura, Mauro ; Huang, Xin ; Bellens, Rik ; Gautama, Sidharta ; Philips, Wilfried. / Taking optimal advantage of fine spatial information : promoting partial image reconstruction for the morphological analysis of very-high-resolution images. 2017 ; Vol. 5, No. 2. pp. 8-28.
@article{aa1e421c42784a89a89708ac954e9f12,
title = "Taking optimal advantage of fine spatial information: promoting partial image reconstruction for the morphological analysis of very-high-resolution images",
abstract = "Diverse sensor technologies have allowed us to measure different aspects of objects on Earth's surface [such as spectral characteristics in hyperspectral images and height in light detection and ranging (LiDAR) data] with increasing spectral and spatial resolutions. Remote-sensing images of very high geometrical resolution can provide a precise and detailed representation of the monitored scene. Thus, the spatial information is fundamental for many applications. Morphological profiles (MPs) and attribute profiles (APs) have been widely used to model the spatial information of very-high-resolution (VHR) remote-sensing images. MPs are obtained by computing a sequence of morphological operators based on geodesic reconstruction. However, both morphological operators based on geodesic reconstruction and attribute filters (AFs) are connected filters and, hence, suffer the problem of leakage (i.e., regions related to different structures in the image that happen to be connected by spurious links are considered as a single object). Objects expected to disappear at a given stage remain present when they connect with other objects in the image. Consequently, the attributes of small objects are mixed with their larger connected objects, leading to poor performances on postapplications (e.g., classification).",
keywords = "image reconstruction, feature extraction, laser radar, spatial resolution, hyperspectral Imaging",
author = "Wenzhi Liao and Jocelyn Chanussot and {Dalla Mura}, Mauro and Xin Huang and Rik Bellens and Sidharta Gautama and Wilfried Philips",
year = "2017",
month = "6",
day = "12",
doi = "10.1109/MGRS.2017.2663666",
language = "English",
volume = "5",
pages = "8--28",
number = "2",

}

Taking optimal advantage of fine spatial information : promoting partial image reconstruction for the morphological analysis of very-high-resolution images. / Liao, Wenzhi; Chanussot, Jocelyn; Dalla Mura, Mauro; Huang, Xin; Bellens, Rik; Gautama, Sidharta; Philips, Wilfried.

Vol. 5, No. 2, 12.06.2017, p. 8-28.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Taking optimal advantage of fine spatial information

T2 - promoting partial image reconstruction for the morphological analysis of very-high-resolution images

AU - Liao, Wenzhi

AU - Chanussot, Jocelyn

AU - Dalla Mura, Mauro

AU - Huang, Xin

AU - Bellens, Rik

AU - Gautama, Sidharta

AU - Philips, Wilfried

PY - 2017/6/12

Y1 - 2017/6/12

N2 - Diverse sensor technologies have allowed us to measure different aspects of objects on Earth's surface [such as spectral characteristics in hyperspectral images and height in light detection and ranging (LiDAR) data] with increasing spectral and spatial resolutions. Remote-sensing images of very high geometrical resolution can provide a precise and detailed representation of the monitored scene. Thus, the spatial information is fundamental for many applications. Morphological profiles (MPs) and attribute profiles (APs) have been widely used to model the spatial information of very-high-resolution (VHR) remote-sensing images. MPs are obtained by computing a sequence of morphological operators based on geodesic reconstruction. However, both morphological operators based on geodesic reconstruction and attribute filters (AFs) are connected filters and, hence, suffer the problem of leakage (i.e., regions related to different structures in the image that happen to be connected by spurious links are considered as a single object). Objects expected to disappear at a given stage remain present when they connect with other objects in the image. Consequently, the attributes of small objects are mixed with their larger connected objects, leading to poor performances on postapplications (e.g., classification).

AB - Diverse sensor technologies have allowed us to measure different aspects of objects on Earth's surface [such as spectral characteristics in hyperspectral images and height in light detection and ranging (LiDAR) data] with increasing spectral and spatial resolutions. Remote-sensing images of very high geometrical resolution can provide a precise and detailed representation of the monitored scene. Thus, the spatial information is fundamental for many applications. Morphological profiles (MPs) and attribute profiles (APs) have been widely used to model the spatial information of very-high-resolution (VHR) remote-sensing images. MPs are obtained by computing a sequence of morphological operators based on geodesic reconstruction. However, both morphological operators based on geodesic reconstruction and attribute filters (AFs) are connected filters and, hence, suffer the problem of leakage (i.e., regions related to different structures in the image that happen to be connected by spurious links are considered as a single object). Objects expected to disappear at a given stage remain present when they connect with other objects in the image. Consequently, the attributes of small objects are mixed with their larger connected objects, leading to poor performances on postapplications (e.g., classification).

KW - image reconstruction

KW - feature extraction

KW - laser radar

KW - spatial resolution

KW - hyperspectral Imaging

UR - http://hdl.handle.net/1854/LU-8523665

U2 - 10.1109/MGRS.2017.2663666

DO - 10.1109/MGRS.2017.2663666

M3 - Article

VL - 5

SP - 8

EP - 28

IS - 2

ER -