How an OEM used Sama to improve a Multi-Class Object Detection (MCOD) System

How an OEM used Sama to improve a Multi-Class Object Detection (MCOD) SystemAbstract background shapes

2-pixel

tolerance

98%

Quality SLA

<1 month

agent ramp time

Table of Contents
Talk to an Expert

GOAL

A large auto OEM was building a Multi-Class Object Detection (MCOD) system, with cameras that captured a 360° view of the road, and needed help scaling annotations for millions of samples for semantic segmentation, object tracking, and object detection.

WORKFLOWS

Sama ramped thousands of agents within a month and:

  • Built a quality rubric with a 2-pixel tolerance
  • Provided full scene semantic segmentation and MCOD metadata tagging
  • Annotated objects using bounding boxes for sequence object tracking and object detection, plus polylines and polygons for key map feature sets

RESULTS

Sama achieved a 98% quality SLA and helped the client:

  • Annotate millions of samples at scale
  • Significantly improve object tracking and detection
  • Improve model accuracy and efficiency

at

at
RESOURCES

Related Case Studies

Object Tracking and Edge Case Detection
CASE STUDY
2
MIN READ

Object Tracking and Edge Case Detection

Learn More
PolyPerception’s Accurate Data Gives Sorting Facilities Better Waste Stream Visibility
CASE STUDY
MIN READ

PolyPerception’s Accurate Data Gives Sorting Facilities Better Waste Stream Visibility

Learn More
Swift Cost-Effectively Scaled Annotations Without Compromising Accuracy
CASE STUDY
MIN READ

Swift Cost-Effectively Scaled Annotations Without Compromising Accuracy

Learn More
How Indoor Robotics Improved Training Data To Enhance Model Performance
CASE STUDY
MIN READ

How Indoor Robotics Improved Training Data To Enhance Model Performance

Learn More