쿠키 설정
인캐빈 센싱 유럽, 베를린, 독일
Join us in Berlin at the InCabin.Sensing event for automotive specialists, where Agnes Jernström, Senior Software Engineer at Neonode, will provide a deep-dive into how Neonode creates compliant data for driver and occupant monitoring systems with pin-point accuracy.
About the Event
Staying competitive and developing new products that improve occupant safety and enhance the user experience as well as comfort have never been more important for the automotive industry. Today, the market for advanced, intelligent automotive in-cabin sensing technologies and emotional sensing, combining state-of-the-art camera and sensor technology with innovative algorithms is growing at exponential speed.
The InCabin.Sensing event is directed at executives, technical leaders, advanced engineers, practitioners and experts involved in intelligent interior systems for the automotive cabin. The event will bring together over 100 of the most influential practitioners, technical & HMI experts, OEMs, tier-one suppliers and research institutes to discuss the latest technical advancements, market trends and opportunities.
Neonode on Stage
Neonode's Machine Perception technology enables real-time evaluation of a person's alertness. By utilizing a combination of body, face, and eye perception, we can detect and thereby alert of inattentiveness and unsafe behaviors in scenarios where concentration is critical, something we use in applications including our driver monitoring system.
Data is the core of our any machine learning application. To make a machine learning model recognize patterns, objects or behaviors it needs to be trained on large amounts of data that represent what the model is supposed to learn. For computer vision tasks, this training data often consists of photos and videos gathered from the real world. However, using real-world data to train neural networks comes with several limitations and challenges with regards to quality, flexibility and privacy.
Agnes Jernström from Neonode will present at InCabin.Sensing and will explain what synthetic data is and how it can be used to overcome these challenges.
The presentation will cover:
Introduction to synthetic training data with examples of how Neonode uses synthetic data for developing highly accurate driver monitoring systems.
Compliance with the recent regulatory framework for AI by the European Commission.
How synthetic data can learn things that are hard or impossible to annotate in real-world data - and fast!
Simplifying the creation of unbiased datasets.
Avoiding the potential legal issues of using real human faces in the training data.
Making it possible to tailor the training data to the task you are solving with regards to image size, camera position and lens parameters.
아그네스 예른스트롬, 발표자
아그네스 예른스트롬은 네오노드 멀티센싱 개발팀의 수석 소프트웨어 엔지니어입니다.
멀티센싱® 는 다양한 사물, 상황, 맥락을 해석하고 이해하기 위해 자체적으로 생성한 합성 데이터와 결합된 최신 머신 러닝 기술을 활용하는 네오노드의 머신 인식을 위한 독점 기술입니다. 아그네스는 자율주행 차량의 포지셔닝, 기어박스 작동, 차량 간 통신 등 다양한 분야에서 선도적인 OEM과 함께 일하며 자동차 업계에서 폭넓은 경험을 쌓았습니다. 스웨덴 스톡홀름 왕립공과대학에서 산업공학 석사 학위를 취득했습니다.
아그네스 예른스트롬
수석 소프트웨어 엔지니어, 네오노드
이벤트 세부 정보
When: 18-20 June, 2023
Where: Titanic Chaussee, Berlin, Germany