Download PDF
NLP Logix > Case Studies > Railroad Asset Identification using Computer Vision
NLP Logix Logo

Railroad Asset Identification using Computer Vision

 Railroad Asset Identification using Computer Vision - IoT ONE Case Study
Technology Category
  • Analytics & Modeling - Computer Vision Software
  • Analytics & Modeling - Machine Learning
  • Sensors - Camera / Video Systems
Applicable Industries
  • Transportation
Applicable Functions
  • Business Operation
Use Cases
  • Vehicle Telematics
The Challenge
This customer maintains a railroad network consisting of thousands of miles of track across North America. They are regulated by a primary federal agency for the safe operation and maintenance of their network. One of the many requirements is the consistent posting of signage at various locations of their tracks. The customer began capturing video of their rail network a number of years ago and updates it on a continual basis. The challenge is the ability to watch the video and determine if specific signage is in place and if it is in serviceable condition.
About The Customer
Large North American Railroad Company
The Solution
The solution that was implemented was the application of computer vision to "view" all of the thousands of miles of track and identify specific signage.

NLP Logix adapted its computer vision infrastructure, to be able to train a machine learning algorithm to identify the specific signage along the rail network. The solution was developed and tested within 60-days and proved to be very accurate and much faster than a human viewing the videos.
Operational Impact
  • [Data Management - Data Processing]
    Video data was able to be processed much faster
  • [Efficiency Improvement - Operation]
    Assets could be identified much faster

Related Case Studies.

Contact us

Let's talk!

* Required
* Required
* Required
* Invalid email address
By submitting this form, you agree that IoT ONE may contact you with insights and marketing messaging.
No thanks, I don't want to receive any marketing emails from IoT ONE.
Submit

Thank you for your message!
We will contact you soon.