Driver State
Understand complex and nuanced states of driver impairment. Provide "quantified driver" services that provide insight into what driving modes, vehicles settings, routes, and times get you to your destination in the best emotional state.
- Detect increased levels of drowsiness in a driver
- Detect driver distraction due to cellphone use
- Understand driver mood and reactions
Occupant State
Insight into the state of the occupants helps improve their comfort by adapting music, lighting, temperature. Understanding passenger engagement with content allows for personalized recommendations and for opportunities to monetize media data.
- Detect when passengers are getting drowsy or are asleep
- Understand occupant mood and reactions
- Personalize and monetize passenger engagement with content
Cabin State
Insight into the state of the cabin helps personalize safety features (seatbelt, airbag), content (video, music and advertising), and the environment of the cabin (heating and lighting). It can also detect if a child or objects have been left behind.
- Detect number of people, who they are, and where they are sitting.
- Identify an occupied infant or child seat.
- Identify personal objects that are left behind in a vehicle.
Data
Affectiva's deep learning algorithms are trained and tested with our large, proprietary data set that is representative of human appearance variances and real-world use cases. Global in nature, our data is diverse in age, gender and ethnicity, helping us mitigate for bias.
- Captured in real world conditions
- Acquired with opt-in and consent
- Automotive in-cabin data: 20k+ hours, 4k+ unique individuals
- Foundational data: 9.7M+ faces, 90 countries, 5B+ facial frames, 6 years of video data
Camera Position
As the industry moves to holistic in-cabin sensing, interior cameras will be placed where they have a view of the entire cabin, including the driver and passengers in it. Overhead camera positions are proving ideal, and Affectiva has tuned its models for this location.
- Affectiva's AI supports both RGB and NIR cameras
- Enables OEMs to use one camera for detecting both state of the driver, state of the cabin, and state of the occupants in it
- Overhead cameras are typically integrated in the rear view mirror or roof module
Embedded Systems
Affectiva's deep learning models are tuned to run on automotive Systems on Chip (SoC). We have optimized our footprint to run alongside other services, in real time, with automotive grade accuracy. Our models support TensorFlow Lite deep learning runtime.
- Affectiva models are quantized
- Embedded deep learning runtime supports ARM® or Intel CPU
- Embedded deep learning runtime can be swapped with hardware specific runtime to make use of accelerators available in target System on Chip (SoC)
Rideshare Experience
With In-Cabin Sensing, ridesharing drivers and brands can deliver five-star rides that keep their customers feeling safe, happy, comfortable and entertained.
Teen Drivers
Distractions are a major risk for teen drivers. Parents can’t always be along for the ride, but In-Cabin Sensing can reinforce good driving habits for them and keep teens safe.
Family Car Rides
In-Cabin Sensing can make family trips safer and more relaxing by powering the systems that control driver and passenger safety and cabin conditions.
