1. / Automotive OEM Gets Accurate Video Labelling for Autonomous Vehicles
Overview

With autonomous car technology cresting the horizon, automakers are working hand-in-hand with IT partners to drive greater innovation and safety margins within every self-driving vehicle. 

One of Germany’s most well-known OEM’s launched a new technology division aimed at perfecting autonomous driving technology. The firm looked to Apexon to help them with a video labelling solution that would tag various objects in and around a car, enabling faster mobility application development.

Problem

While video labelling is not an entirely new technology, this particular project posed certain significant challenges.

  • Handling new work types with relatively unknown business rules and volume flow
  • Working with poor quality video files
  • Delivering a quality solution with a very low scope for error and zero timeline to rectify errors
  • Low resource availability, high attrition rate and short annual hiring timelines
  • Building an ODC setup to work with patented technologies and solutions
Solution

In building and deploying the solution, Apexon engineers used a number of tools to both annotate the video labels and to streamline the hiring process. Solution details include:

  • Tailoring new hiring processes to meet the requirements specific to the received work input format
  • Deploying outcome-based incentive models and cross training as a career progression indicator
  • Using a blend of proprietary toolsets and Philosys Label Editor to fully annotate objects using textural and geometric markers and classes, while delivering them in XML data format – to be used in algorithmic validation and machine learning applications
  • Leveraging the Cvedia platform to enable deep learning vehicle applications via live streaming video footage, and Vatic annotation tool to quickly build massive video sets that are deployable to Amazon cloud
Impact

Apexon successfully hit every milestone and reached all mandated targets over the course of two years, processing over 25 million labels in that time frame. Additionally, we were able to:

  • Establish stringent resource management protocols, including a 10% resource buffer
  • Drastically reduce project hiring times and infrastructure set up costs
  • Deploy a reliable data security framework with scalable options for future business growth
  • Consistently deliver an SLA target of 99.5%, with under 5 defects per 1000 labels

Other Case Studies
A large container operator implements centralized data warehouse to improve data quality by 30%

Case Studies

A large container operator implements centralized data warehouse to improve data quality by 30%

Learn how we assisted a Danish business conglomerate with activities in the transport, logistics and energy sectors to implement a centralized Data warehouse to improve their data quality, analyze the business trend and performance.

A major US bank holding company reduced data anomaly and mismatch errors by 60%.

Case Studies

A major US bank holding company reduced data anomaly and mismatch errors by 60%.

Discover how we aided a leading US bank holding company headquartered in Michigan with capability enhancements that ensure a long-term process that reduces data anomaly and mismatch errors, improves operations, and mitigates risks.

Emergency Department – Coding Improvement

Case Studies

Emergency Department – Coding Improvement

Learn how we assisted a leading revenue cycle management services company in the United States in identifying opportunities to improve documentation while also modifying and automating its reconciliation and quality procedures.

US-based Physicians Group Improves ROI by 6X

Case Studies

Healthcare & Life Sciences
US-based Physicians Group Improves ROI by 6X

Learn how we helped a large physicians group based in the US use deep learning models to improve error identification by 3x and reduce financial leakage by 40%.

Let’s head to the apex

Get in touch and let’s start a conversation!






    banner_side