EVLib is a deep learning based software library consisted of CNN models that are highly optimized in order to power AI on edge devices such as cameras, IoT devices and embedded CPUs. With over 100 learning models that are pre-trained and optimized in terms of accuracy, speed and low power performance you can unleash the power of AI and deep learning in your product or system. The runtime models are optimized for ARM based CPU platforms or GPU acceleration.
Library functions:
- Anonymizer – blurring of people in order to remove sensitive data (GDPR)
- People / Vehicle detection and counting
- Soft biometrics (male – female, age group)
- 2D/3D object detection and tracking
EVLib offers also a wide flexibility for specific object detection like food recognition, product catalogues recognition etc. Pre-trained models can be easily extended for custom object detection or specific scenario and tracking using additional data.
Portfolio:
- Industry 4.0
- Industrial automation applications
- Smart IoT devices
- 3D printing