PHOTOGRAMMETRIC ENGINEERING & REMOTE SENSING
November 2019
779
PHOTOGRAMME TR I C ENG I NE ER I NG & REMOT E SENS I NG
The official journal for imaging and geospatial information science and technology
November 2019 Volume 85 Number 11
FEATURE
See the Cover Description on Page
ANNOUNCEMENTS
Call for Abstracts Extended
Join us in welcoming our newest members to
ASPRS.
DEPARTMENTS
PEER-REVIEWED ARTICLES
Liangliang Tao, Guojie Wang, Xi Chen, Jing Li, and Qingkong Cai
In order to eliminate the influences of surface roughness and vegetation on radar signal
in the vegetation-covered soil moisture estimation, the present paper proposes a com-
bining method based on modified particle swarm optimization (MPSO) and back-propaga-
tion (BP) neural network algorithm.
Zhixin Qi, Anthony Gar-On Yeh, and Xia Li
Aiming at steering the selection of optimal combinations of polarimetric SAR (PolSAR)
frequency bands for different land cover classification schemes, this study investigates
the land cover classification capabilities of all the possible combinations of L-band
ALOS PALSAR fully PolSAR data, C-band RADARSAT-2 fully PolSAR data, and X-band
TerraSAR-X HH SAR data.
Mi Wang, Beibei Guo, Ying Zhu, Yufeng Cheng, and Chenhui Nie
The GaoFen1 (GF1) optical remote sensing satellite is equipped with four wide-field-of-view
(WFV) cameras. The cameras work together to obtain an image 800 km wide, with a resolu-
tion of 16 m. To achieve the high accuracy calibration of WFV camera on GF1, the calibration
field should have high resolution and broad coverage based on the traditional calibration
method. In this study, a self-calibration scheme for the WFV camera on GF1 is developed.
Ningning Zhu, Yonghong Jia, and Xia Huang
We propose utilizing the feature points of road lamp and lane to register MMS LiDAR
points and panoramic image sequence.
Ying Cui, Xiaowei Ji, Kai Xu, and Liguo Wang
Applying limited labeled samples to improve the classification results is a challenge in
the hyperspectral images. Active learning (AL) and semisupervised learning (SSL) are
two promising techniques to achieve this challenge. While the traditional method, such
as Collaborative Active and Semisupervised Learning algorithm (CASSL) may introduce
many incorrect pseudolabels and appears premature convergence. To overcome these
drawbacks, a novel framework named Double-Strategy-Check Collaborative Active and
Semisupervised Learning (DSC-CASSL) is proposed in this paper.
linkedin.com/groups/2745128/profile
COLUMNS
This month we look at The Republic of Suriname.
Education &
Professional
Development
at ASPRS
by Stan Hovey
In Memoriam
Charles Nelson
