Orions Systems | Orions AI
16687
page-template,page-template-full_width,page-template-full_width-php,page,page-id-16687,ajax_fade,page_not_loaded,,qode-child-theme-ver-1.0.0,qode-theme-ver-10.0,wpb-js-composer js-comp-ver-4.12,vc_responsive
 

Orions AI

THE POWER TO CREATE AND TRAIN SMART VISION ALGORITHMS

ORIONS AI is a Smart Vision Platform service to create and train video algorithms. Built to take advantage of Orions cloud-based design, Orions AI provides elastic scalability to meet the requirements of any task, from basic algorithms relying driven by simple business rules, to complex smart vision systems that require the application of human and algorithmic intelligence to hundreds of thousands of video hours.

Orions AI Capabilities:

  • Create new algorithms or train existing ones

 

  • Use in combination with OrionsCrowd to automatically integrate of human cognitive intelligence to create ground truth or provide more data when the algorithm encounters low confidence situations.

 

  • Patent pending AI combinatorial optimization to accelerate machine learning

 

  • Patent pending cloud-enabled distributed transcoding system provides elastic scalability

Algorithm Training Example – Baseball Pitches

Step 1. Use OrionsCrowd to create ground truth.

A small team of human taggers reviews and tags pitches in a subset of video segments.

Step 2. Use Orions AI to train from ground truth and automate the previous human task.

Orions AI scans the tagged video segments to identify changes in the scene, such as a single object moving at higher velocity than any other object in the scene.

Step 3. Feed Orions AI more video and identify scenes with pitches

Now the algorithm can quickly process hundreds of hours of baseball footage and identify the segments that likely have pitches based on the velocity/object detection.

Step 4. Check accuracy and create machine learning loop

Human taggers review a random sampling of both the newly identified pitch video segments as well as segments the algorithm determined to NOT include a pitch. Taggers identify segments with errors (false positives or false negatives) and feed these segments with the correct data back into the algorithm.

Step 5. Run the algorithm at scale

The machine learning cycle continues until Orions AI is achieving an acceptable level of accuracy at scale.

 

At Orions Systems, we’re always ready to answer your questions and HELP YOU SOLVE YOUR TOUGHEST VIDEO INTELLIGENCE CHALLENGES. GET IN TOUCH TODAY!