Train - Validate - Test
Dataset generation solution for in-cabin monitoring systems
Procedurally generated data to train your deep learning model in a fraction of the time
Specific technology for in-cabin simulation
Anyverse™ has developed specific technology for interior simulation, including wide variability in vehicles, people features, body poses, environment, lighting, and others. Interior monitoring developers can now procedurally generate thousands of images and metadata with ground truth at a reasonable cost.
Accuracy, variability and cost-efficiency
Lack of variability
Privacy issues & children
Deep learning models need lots of data
You need a vast amount of data to train and validate your driver monitoring system with a guarantee of success and real-world data is limited, expensive, and time-consuming to get, curate and label. Maybe not even completely accurate.
Anyverse™ provides close to real synthetic data with ground truth: generate as many images as you need at a fraction of the time and cost of real-world images.
Lack of variability means biased systems
Driver and occupant’s age or ethnicity, environment (including the car), time of day, illumination, etc. You need enough variability and close to reality accuracy to train your monitoring system so it can generalize to the real world they are going to face in production.
With Anyverse™ you can programmatically control your scenes and automatically generate thousands of variations of data adding variability to the interior: different cars and manufacturers, materials, colors, textures, etc. Generate all the images your system needs with almost infinite variability: countless drivers and occupants with multiple poses, behaviors, and interactions inside the cabin.
In-cabin data is difficult to get because of privacy issues... Even worse when the little ones are involved..
Privacy is an important issue when gathering data from the driver and other occupants, reaching a whole new level when children are involved... It greatly limits your possibilities to collect data from the real world.
With Anyverse™ you can reproduce non-viable in-cabin scenes in the real world due to data protection regulations, children rights or safety issues: a child left behind on the back seat, driver distractions, drowsiness, microsleeps, an activated airbag system, pets, or any other potentially hazardous situations.
The secret is that there is no secret. Technology you trust.
Proprietary Spectral Render Engine
Physically accurate representation of light and material interaction to generate photorealistic images that will help your model generalize to the real world.
Sensor simulation pipeline
Spectral information to faithfully simulate different sensor components and configurations. Experiment and choose the right sensor for your Camera-based interior monitoring systems.
Procedural scene generation & 3D car interiors library
Deep learning models need variability to learn from experience. Recreate as many car interiors and materials as you need including corner cases.
Scalable powerful cloud platform
All the synthetic data you need in a timely and costly effective way. The power of the cloud at your service, no costly hardware and maintenance.
The data you need, the way you need it, when you need it
We know this is much more than a system to fulfill the upcoming legislative requirements for driver monitoring.
You have a specific question about our technology? Just send us a message and we'll connect you to an expert!