ArcGIS Survey123

ArcGIS Survey123 smart camera: Machine learning meets field data collection

While machine learning tasks in the office may replace some human activities, in the field they more likely will compliment or enhance field work activities. Using the Survey123 smart camera, you can use an image classification model on your mobile device while in the field and even while disconnected from the network.  Real time inferences can be used to accelerate field data collection or to provide guidance to field users. 

The new Learn ArcGIS lesson, Train a model to identify street signs, shows you how to both create and use an image classification model in the field.  

First, you’ll acquire a representative collection of training images captured using Survey123. Next, you’ll use the images to train a model with ArcGIS Notebooks. Once the necessary model files are created, you’ll use them in conjunction with the Survey123 smart camera to test the model’s predictions and classify survey photos. 

Sign classification in Survey123

About the authors

Marika Vertzonis is a product engineer at Esri focusing on the research and development of field apps. After studying environmental engineering at university Marika spent the early part of her career working in local government, regional water authorities, and engineering consulting as a GIS professional. Her own time in the field has made her a passionate advocate for using the most suitable technology available in scientific and engineering fieldwork. She is also the author of Fieldwork Handbook: A practical guide on the go (Esri Press, 2024).

Ismael Chivite joined Esri in 2002. A geographer by training, he loves helping people leverage GIS to improve the way they work. As a Senior Product Manager, Ismael is always looking for ideas to create new and improve existing Esri products. Outside working hours: Legos, rock climbing, Romanesque architecture and jamon iberico. On occasion, he enjoys jamon during working hours too.

Connect:
1 Comment
Oldest
Newest
Inline Feedbacks
View all comments

Next Article

Pop-ups: the essentials

Read this article