StradVision, an AI-based camera perception software supplier, has announced a collaboration with South Korean social enterprise Testworks, which it says will help improve the data processing efficiency and accuracy of road safety technology such as its SVNet deep learning-based software.
The company notes that one of SVNet’s key features is to quickly and accurately identify hazardous and potential road conditions using a deep-learning algorithm. In order to train the deep neural network by generating annotated data, the company uses its own Auto Labeling Tool to automatically detect and label 94% of objects at eight times the speed of a human labeler. The remaining 6% requires human intervention, which is where the Testworks’ partnership comes in.
“I was looking for a company to entrust with manually labeling StradVision’s detail-sensitive data, and Testworks immediately came to mind because of their stellar reputation with data processing. We support Testworks’ social mission and the quality of their work is world-class, so it is an easy decision for us to develop this partnership,” said StradVision CEO Junhwan Kim.
StradVision notes that it works with Testworks on data labeling while also providing inclusive employment opportunities for developmentally disabled individuals, such as those with autism, as well as those who may have difficulty finding work after a hiatus, such as retirees and mothers returning to the workplace.
Testworks says it has refined its operational procedures through trial and error as it met with challenges over the course of the “beta” period. For example, it introduced layers of data reviews and the addition of a project manager to the team, who could help communicate with full-time developmentally disabled employees to ensure the integrity of data processed for StradVision.
“Autistic individuals tend to have unique sensitivity that allows them to notice small things that non-autistic people would simply overlook, including minute errors in StradVision’s data,” explained Testworks CEO Yoon Seok-won. He flags up the example of the project manager, a mother who returned to the workplace, who was particularly patient with her colleagues and ensured their work ran smoothly – which was immensely helpful in setting up a positive and accepting work environment.
The Testworks’ team now processes data from StradVision, correcting any labeling errors and adding important information – ensuring that the AI-based software learns from its mistakes and improves over time.
The company highlights that the project allows developmentally disabled individuals to make a significant contribution to the advancement of AV technology by pushing AI-based software to self-correct after the initial stage of human labeling. This significantly speeds up the growth of deep-learning advanced machine algorithms.