Google Chrome is the preferred browser for this session.

Tickets for this workshop must be claimed in advance.

This workshop will be broken down into 4 parts:

1. Introduction to ERDAS IMAGINE

2. Spatial Modeling for Wildlife Applications

3. Using AI, Spatial Modeling and Python to Break Down Big Data Barriers

4. Q & A

Spatial Modeling for Wildlife Applications Using FLIR Imagery and ERDAS IMAGINE

Wildlife biologists are often tasked with providing population counts. This can be extremely tedious and labor intensive. Combining thermal imagery with spatial modeling provides a simple solution to this task.

In this session, learn how this alternative approach provides a quick answer, so you can focus on more important work.

• What type of imagery is optimal for counting populations

• How to interpret the imagery

• How to build a spatial model that can quickly provide population counts

• How spatial models can be used by a multitude of people without any programming experience

Using Artificial Intelligence, Spatial Modeling and Python to break down Big Data Barriers.

“In five years, there may be a million times more than the amount of geospatial data that we have today.” Robert Cardillo, sixth director of the National Geospatial-Intelligence Agency, said these words in his 2017 keynote address at the United States Geospatial Intelligence Foundation’s GEOINT Symposium.

To keep up with the data deluge, we need the help of AI, machine learning, and deep learning to create repeatable, batchable processes to extract accurate, actionable information from imagery.

Join this training by Hexagon’s Geospatial division to learn how spatial modeling and AI can increase productivity and efficiency. See a complete demonstration of an image analyst’s typical workflow with this example:

An analyst might receive 200 images a day and need to analyze them for a vehicle of interest. See how automated object detection in ERDAS IMAGINE’s Spatial Modeler will highlight which images need to be manually inspected and analyzed, then learn the process to train and execute the Object Detection model. See how Python scripts can be incorporated into IMAGINE’s Spatial Modeler to watch the input imagery folder and execute the model as each image becomes available. Python can also be used to send an email notification to alert the analyst once the model has found the vehicle of interest on an image. By integrating AI, spatial modeling, and Python, it’s possible to lessen the time from data production to operational use.