PHOTOGRAMMETRIC ENGINEERING & REMOTE SENSING
December 2019
853
Object Based Image Analysis Made Easy and Flexible
Keith Peterson, Trimble, and
Jarlath O’Neil-Dunne, University of Vermont
This workshop will provide an informative introduction to the
fundamental concepts and technologies in object-based image
analysis and iats combination with computer vision methods,
machine-learning and pixel-based operations. Attendees will
use eCognition Developer to employ a comprehensive range of
analysis tools utilizing diverse data sources, from medium to
high resolution satellite data, very high- resolution aerial and
UAV imagery, GIS, lidar, radar, and even hyperspectral data.
Combining Deep Learning with Object
Based Image Analysis (OBIA)
Keith Peterson, Trimble, and Christian Weise, Trimble
Recently, deep learning (DL) has become the fastest growing
trend in data analysis and has been widely and successfully
applied to various feature extraction tasks. In the context of
remote sensing the combination of DL with OBIA (object-based
image analysis) offers the flexibility to select the optimal work-
ing method inside the complete feature extraction workflow.
This workshop will explore the accelerated usage of deep learn-
ing with object-based image analysis using Trimble eCognition
Developer software.
Spreadsheet Demonstration of
Analytical Photogrammetry
Paul Pope, Global Geoinformatics Inc.
Photogrammetry is often explained by describing the collin-
earity condition and showing examples of final products. The
intermediate steps are rarely illustrated in detail. This work-
shop aims to make analytical photogrammetry accessible to
the layperson by using spreadsheet calculations to 1) solve for
the exterior orientation parameters of a framing camera, and 2)
determine the dimensions of an object using stereo imagery.
Generic Sensor Models for
Photogrammetric Applications
Henry Theiss, Integrity Applications Incorporated
The workshop conveys the importance of rigorous sensor mod-
eling, data adjustment, and covariance propagation in meeting
the absolute geolocation, relative mensuration, and multi-sensor
fusion objectives of the end-user. It proceeds with an overview
of the Community Sensor Model (CSM) Application Program-
ming Interface (API) which facilitates integration of multi-mo-
dality imagery and point-cloud products into geospatial exploita-
tion tools. It provides an overview of generic sensor models for
frame-sequences, linear-array scanners, SAR, and lidar.”
Total Propagated Uncertainty (TPU) and Absolute
Accuracy Assessment of 3D Lidar Point Cloud
Minsu Kim, USGS
Total Propagated Uncertainty (TPU) is the statistical estimate
of lidar positional uncertainty for each lidar point. Theoretical
details of the TPU and its application to the airborne lidar data
will be presented. Assessment of the 3D absolute accuracy of the
lidar point cloud is an important priority in USGS 3DEP pro-
gram. TPU is an important factor that affects the absolute accu-
racy of the lidar point cloud data. Techniques for the 3D absolute
accuracy assessment using various geometric features and its
inherent relationship with TPU will be discussed in the workshop.
Machine and Deep Learning Image Classification
Amr Abd-Elrahman, University of Florida
This workshop teaches participants how to (1) conduct pixel-
and object-based image classification using traditional (Support
Vector Machine and Random Forests) machine learning algo-
rithms; (2) build models for data preparation and experiment
with different classification parameters; (3) use the deeplab deep
learning architecture for image segmentation (classification).
Participants will be briefly introduced to necessary theoretical
background information as well as practical implementation
using ArcGIS Pro. Real world examples of wetland land cover
classification will be used in the demonstration.
Preparation for ASPRS Certification
- General Knowledge
Robert Burtch, Ferris State University
This workshop covers the common knowledge areas comprising
a large portion of exam content for ASPRS Certification. It is
valuable preparation for those who have never taken an ASPRS
exam, as well as for those who have expertise in a particular
specialty, such as lidar or UAS, but feel less prepared for the
general knowledge component of the exam. This workshop will
also explain the certification application process and the impor-
tance of certification in career development.
Aerial Triangulation and Data Processing
for the Unmanned Aerial System (UAS)
Qassim A Abdullah, Woolpert, Inc. and
Riadh Munjy, CSU Fresno
This workshop teaches participants to successfully design, plan
and execute an aerial mission using unmanned aerial systems
(UAS) and GPS-based aerial triangulation, including flight
planning, ground control placement, camera calibration, and
product generation. Participants will be introduced to mathe-
matical basis of simultaneous bundle block adjustment. Practi-
cal examples will be presented.
DON’T FORGET, THE DEADLINE TO SUBMIT ABSTRACTS HAS BEEN
EXTENDED TO DECEMBER 2, 2019!
For additional information, see
/ or contact
