
Ficosa and indie Semiconductor team on AI smart camera
Ficosa in Spain has signed a global commercialisation deal with indie Semiconductor for scalable neural network-based edge sensing in automotive cameras.
The collaboration agreement between Ficosa and indie will develop and commercialize automotive smart camera designs with neural network-based artificial intelligence processing. The companies intend to sample the first smart camera later this year and expect to ramp into volume production by 2025
The partnership combines Ficosa’s decade of expertise in hgh volume vision technology and indie’s proprietary vision processing technology for in-camera object detection.
Government regulators and new car safety assessment programmes are seeking to specify protection for vulnerable road users (VRU) such as pedestrians and cyclists, especially for back-up and eMirror scenarios. These technologies in euroNCAP and the US National Highway Transportation Safety Administration (NHTSA) regulations are driving demand for volume scalable camera-based Advanced Driver Assistance System (ADAS) systems with active sensing of pedestrians.
- indie Semiconductor adds hardware test lab to Dresden
- indie Semiconductor buys Exalos in $65m LiDAR boost
According to S&P Global, shipments of surround view and park assist camera electronic control units (ECUs) are projected to grow from 134 million units in 2023 to 240 million units by 2033.
“As a leading supplier of cameras to the world’s largest vehicle OEMs, Ficosa brings deep expertise and industrialization capabilities to this exciting collaboration with indie to develop the next generation of smart cameras deploying NN-based detection and improve safety levels for both vehicle occupants and other road users” said Josep Maria Forcadell, CTO of Ficosa.
“indie is thrilled to partner with Ficosa, leveraging our next generation of Computer Vision solutions that integrate not only high performance image signal processing but also the dedicated AI elements required for neural networks,” said Abhay Rai, EVP and GM of indie’s Vision Business Unit.
“The camera solutions of today either deploy classical vision algorithms, with limited detection performance across challenging environmental conditions, or rely upon power-hungry host processing for object detection. indie’s NN-based AI vision solutions can enable improved detection with ultra-low power in a compact form factor for these real-world edge sensing scenarios. As a result, Ficosa and indie are well positioned to capitalize on the rapid proliferation of smart camera solutions around the vehicle.”
Founded in 1949 and with headquarters in Barcelona, Ficosa currently employs more than 8.500 people and has production and R&D centres and sales offices in Europe, North and South America, Asia and Africa for its Rear View System.
www.ficosa.com; www.indiesemi.com
