Dear videantis customer, partner, friend or other contact,

it’s December again. So it’s not only time for the next videantis newsletter, it’s also time to lean back, have a <add your favourite drink here> and reflect on the many things one may be struggling to understand these days.

There’s of course the global events, which – frankly speaking – are quite scary: countries invading other countries, countries threatening to invade other countries and countries trying to exploit this insane geopolitical mess. And all this gets amalgamated with a pandemic and the still widely neglected climate crisis. I am personally not sure whether we as a society set our priorities right…

But thankfully there are other situations where understanding might be difficult, yet more entertaining. For example, have you ever had to explain to your kids, parents, spouse or neighbour what you are doing for a living? Did you ever have to come up with an ad-hoc explanation for Machine Learning? Artificial Intelligence? Were you able to satisfactorily answer any follow-up question?

If you’re unable to instantly elaborate on these topics I have advice for you:

• Check out IBM’s webpage – they have a plethora of definitions, explanations and downloads on this topic.
• It’s not only about AI. Don’t forget (or even ignore) classical algorithms, e.g., for computer vision. Those will be around for a long time, whether it’s for legacy or safety. You want to know more? Talk to videantis!

With this, the whole videantis team and I would like to wish you a peaceful year-end, Merry Christmas, and a wonderful start into 2023. And most importantly – don’t forget to have yourself a great time!

Stephan Janouch
Director Marketing @ videantis

ps. Check out below what happened at videantis in 2022!

pps. Going to CES2023? Want to learn about videantis’ AI solutions? Send your meeting request to info@videantis.com

Automotive SoCs designed in Hannover

videantis and ADTechnology will jointly build automotive SoCs for advanced driver assistance systems (ADAS) and autonomous driving (AD) using Samsung Foundry’s advanced 5nm process.

Read the full press release

FlexAISIC AI chip tapes out with videantis processor platform

The videantis v-MP6000UDX platform is the core component of the FlexAISIC AI chip performing key perception unit functionality for autonomous driving. The chip development is part of the KI-Flex project funded by the German Federal Ministry of Education and Research (BMBF).

Read the full press release

videantis raises venture capital

videantis completed a multi-million Euro funding round to accelerate its current growth path. The funding round is supported by investors with strong semiconductor and automotive background.

Read the full press release

videantis hires CFO, focuses on growth

videantis appointed Christoph Averhaus as Chief Financial Officer (CFO) to drive company growth.

Read the full press release

Low-power AI chip tapes out with videantis processor platform

videantis announced the tape-out of a low-power AI chip based on its v-MP6000UDX unified processing platform. The chip development is part of the European TEMPO project and targets several autonomous driving use cases.

Read the full press release

The post December newsletter: AI, the Universe and Everything appeared first on videantis - processors for deep learning, computer vision and video coding.

Hannover, Germany, December 13, 2022 – videantis GmbH, provider of a unified platform for combined processing of algorithms as diverse as AI (Artificial Intelligence), multi-modal sensor data processing and fusion, or video coding on a single architecture, today announced the tape-out of the FlexAISIC AI chip based on its flexible v-MP6000UDX unified processing platform. The tape-out has been achieved in collaboration with the Fraunhofer Institute for Integrated Circuits IIS, and the chip development is funded by the German Federal Ministry of Education and Research (BMBF) within the KI-FLEX project.

KI-FLEX is part of a broader initiative driven by the German BMBF to push research of AI-based technologies for autonomous driving. KI-FLEX develops a powerful and highly energy-efficient hardware platform and the associated software framework for AI-based processing and merging of data from different sensors, resulting in fast and reliable perception and localization for autonomous driving.

The videantis v-MP6000UDX platform as the core component of the FlexAISIC is a highly scalable multi-core architecture combined with a tailored bus fabric and multi-banked shared on-chip SRAM which delivers extreme efficiency and performance for a variety of algorithm types like deep learning, computer vision, signal processing, and video coding. Within KI-FLEX, videantis’ comprehensive v‑CNNDesigner front-to-end tool flow is employed to map both camera-based image detector and lidar-based point cloud pose detector networks to distinct cores of the v-MP6000UDX architecture for simultaneous execution on the FlexAISIC chip, resulting in a highly compact and efficient solution for an autonomous vehicle perception unit.

About KI-FLEX
KI-FLEX is a research project funded by the German Federal Ministry of Education and Research with the goal to develop a powerful, energy-efficient hardware platform and the associated software framework for autonomous driving. KI-FLEX is designed to process and merge data from different sensors in cars quickly and reliably by using methods of artificial intelligence (AI; German abbreviation: KI). As a result, the vehicle always has an accurate picture of the actual traffic conditions, can locate its own position in this environment and, on the basis of this information, make the right decision in every driving situation – thus making autonomous driving safe and reliable.
The consortium to develop KI-FLEX is led by Fraunhofer Institute for Integrated Circuits IIS and includes Ibeo Automotive Systems GmbH, Infineon Technologies AG, Friedrich-Alexander-University Erlangen-Nuremberg, Technical University Munich, Fraunhofer Institute for Open Communication Systems FOKUS, Daimler Center for Automotive IT Innovations DCAITI and videantis GmbH.
For more information, please visit https://www.elektronikforschung.de/projekte/ki-flex

About videantis
Headquartered in Hannover, Germany, videantis GmbH is the originator of a unique high-performance, extreme-efficiency and fully scalable unified processing platform, which enables the implementation of leading edge algorithms for AI/deep learning, multi-modal sensor data processing and fusion as well as image and video en/decoding on the same architecture in highly efficient single-chip solutions. With its processor IP, application libraries and development tools, videantis globally supports semiconductor manufacturers, automotive OEMs and tier 1 suppliers in serial production together with customers in other high-volume embedded markets. videantis has been recognized with the Red Herring Award and multiple Deloitte Technology Fast 50 Awards as one of the fastest growing technology companies in Germany.

For more information please contact:
Stephan Janouch, Director Marketing
Email: stephan.janouch@videantis.com
Phone: +49 (511) 51 522 3-35

Featured images:

The post KI-FLEX AI chip tapes out with flexible videantis processor platform appeared first on videantis - processors for deep learning, computer vision and video coding.

Hannover, Germany, and Seoul, South Korea, October 19, 2022 – videantis GmbH, provider of a unified platform for combined processing of algorithms as diverse as AI (Artificial Intelligence), multi-modal sensor data processing and fusion, or video coding on a single architecture, and ADTechnology Co., Ltd., a global leader in ASIC (Application Specific Integrated Circuit) design services and turnkey solutions and distinguished Samsung Foundry’s Design Solution Partner, today announced a collaboration to jointly build automotive SoCs (System-on-Chip) for advanced driver assistance systems (ADAS) and autonomous driving (AD) using Samsung Foundry’s advanced 5nm process.

Based on this advanced technology node, ADTechnology and videantis will each contribute their unique expertise in implementing a scalable and customizable SoC platform targeting the full range of automotive processing requirements. From smart edge sensor data processing in decentralized vehicle architectures up to high-performance compute systems in domain and central processing units, this SoC platform will target ADAS and AD applications up to SAE L4 (Society of Automotive Engineers, Level 4).

In contrast to other SoCs addressing this market, the videantis’ v-MP6000UDX unified processing platform renders separate specialized cores for AI, vision, signal processing, graphics, or video coding obsolete. This radically cuts down overall SoC complexity and at the same time boosts flexibility to support diverse automotive use cases at equally high silicon utilization.

The SoC platform, combining videantis’ v-MP6000UDX processing subsystem and state-of-the-art automotive processors licensed from Arm, thus yields simplified, highly cost-effective single-chip solutions for ADAS/AD without the need for companion chips.

With the extreme efficiency of the videantis platform already proven in safety-relevant single-box automotive smart cameras in high-volume automotive production, seamless reuse of existing software applications, development tools, and expertise towards this upcoming SoC platform is guaranteed. New full stack development benefits from substantially reduced software development complexity due to using a single unified tool-chain for all algorithm types.

“We are very pleased to team up with ADTechnology, one of the world’s leading design houses contributing a proven expertise in the implementation of high-end SoCs as well as securing premium access to Samsung Foundry’s volume production capacities,” says Dr. Hans-Joachim Stolberg, CEO/CTO and one of the founders of videantis. “I’m convinced that this collaboration with ADTechnology, Samsung Foundry, and Arm will contribute significantly to our future business.”

“I’m very honored to announce this important collaboration work with videantis,” says JK Park, CEO of ADTechnology. “It is our duty to make our customers successful. Based on 20 years of engineering experience along with 500 employees, together with videantis we will serve global automotive OEMs and tier-1 suppliers to secure reliable mass production. With this monumental program, we will also expand the collaboration with our partners Samsung Foundry and Arm.”

videantis and ADTechnology, supported by Arm and Samsung Foundry, are working closely with leading automotive OEMs and tier-1 suppliers to develop the best fit-for-purpose, proven SoC platforms for their next generation vehicle architectures, enabling rapid customization for a wide range of automotive devices.

“This project is a successful example of the expanding Samsung Foundry ecosystem,” says Moonsoo Kang, executive vice president and head of Business Development team, Samsung Electronics. “Through close collaboration with ADTechnology, our Design Solution Partner, we will help diverse customers launch competitive products using our 5nm process technology.”

“The future of autonomous vehicle applications relies on having access to the right computing technology for the right application,” said Dennis Laudick, VP of go-to-market, Automotive Line of Business, Arm. “We’re pleased that videantis have licensed our IP to provide the right balance of performance, efficiency and leading-edge safety, and we look forward to the computing innovations to come in autonomous vehicles as a result.”

First products resulting out of this collaboration are targeting vehicles with Start of Production (SOP) 2025 and onwards.

About videantis
Headquartered in Hannover, Germany, videantis GmbH is the originator of a unique high-performance, extreme-efficiency and fully scalable unified processing platform, which enables the implementation of leading edge algorithms for AI/deep learning, multi-modal sensor data processing and fusion as well as image and video en/decoding on the same architecture in highly efficient single-chip solutions. With its processor IP, application libraries and development tools, videantis globally supports semiconductor manufacturers, automotive OEMs and tier 1 suppliers in serial production together with customers in other high-volume embedded markets. videantis has been recognized with the Red Herring Award and multiple Deloitte Technology Fast 50 Awards as one of the fastest growing technology companies in Germany.

About ADTechnology
ADTechnology is a global leading ASIC design services and manufacturing services provider which has 20 years of business history and 700+ design/tape-out engineering experiences. Headquartered in Suwon, Korea, ADTechnology has R&D offices in Korea and Vietnam and sales offices in San Jose, USA and Munich, Germany. Including subsidiaries, there are more than 500 employees globally with a target to expand to more than 700 by 2025. ADTechnology is also listed on the Korean stock market, KOSDAQ, and its sales record in 2021 was $265M. Most importantly, ADTechnology is a member of Samsung Foundry Design Solution Partner program, focusing on 4/5/8nm advanced ASIC SoCs encompassing Automotive, AI, HPC, Consumer and Industrial applications.

For more information please contact:
videantis GmbH
Stephan Janouch, Director Marketing
Email: stephan.janouch@videantis.com
Phone: +49 (511) 51 522 3-35
Web: www.videantis.com

ADTechnology Co., Ltd.
Rudy Park, Director Marketing
Email: rudy@adtek.co.kr
Phone: +82-31-219-9734
Web: http://en.adtek.co.kr

Featured image:

From left to right: James Y. Lee, Senior Vice President Strategic Marketing of ADTechnology; JK Park, CEO of ADTechnology; Dr. Hans-Joachim Stolberg, CEO of videantis; HY Lee, General Manager ADTechnology Europe; Christoph Averhaus, CFO of videantis

The post videantis and ADTechnology to build 5nm ADAS/AD SoCs appeared first on videantis - processors for deep learning, computer vision and video coding.

Hannover, Germany, September 14, 2022 – videantis GmbH, a leading supplier of unified AI/deep learning, multi-modal sensor data processing and fusion, and image and video coding solutions, today announced the completion of a multi-million Euro funding round to accelerate its current growth path. The funding round is an intermediate step on the way towards a later series B financing round aimed for in 2023.

The funding round was led by eCAPITAL and is supported by investors with strong semiconductor and automotive background, including Lower Saxony’s automotive investment fund (managed by NBank Capital GmbH) and industry veteran Dr. Anton Mindl, who previously led Elmos Semiconductor SE for 15 years with outstanding success and held executive positions at Siemens VDO and Bosch before.

Willi Mannheims, Managing Partner of eCAPITAL, says: “This investment is a strong acknowledgement of videantis’ vision from both industry leaders and venture investors. The team we invested in is world-class and continuously pushes the boundaries of technology. We are delighted to continue to support the videantis team on their impressive journey to become a global leader within the automotive processor market.“

Capitalizing on its ongoing serial production with several leading automotive OEMs and tier 1s, videantis will use the funds to capture new disruptive business opportunities arising from the rapidly changing automotive supply chain landscape as well as to expand its team in both engineering and customer-facing positions.

“Closing this funding round in the current economic and geopolitical situation is a compelling proof of the superiority of our technology and the business opportunities at hand”, says Dr. Hans-Joachim Stolberg, CEO/CTO and one of the founders of videantis. “This investment will enable videantis to engage with customers on a much larger scale so they can profit from the unique, production-proven efficiency of our unified platform over the complete range from extreme edge to high-end central compute.“

videantis’ unified processing platform enables the efficient combination of all ADAS and autonomous driving algorithms into cost-reduced single-chip solutions without the need for companion chips, profiting from a much simplified SoC architecture due to fewer components and from substantially reduced software development complexity resulting from a single unified tool-chain for all algorithm types. With the seamless multi-core scalability of the platform, software-compatible chip families are supported from extreme edge devices, directly residing near sensors, up to high-end central compute units. The ability to write, verify and certify application software only once, but being able to deploy it everywhere across the entire E/E architecture as well as entire ranges of car models is a quantum leap for automotive system and software development.

About videantis
Headquartered in Hannover, Germany, videantis GmbH is the originator of a unique high-performance, extreme-efficiency and fully scalable unified processing platform, which enables the implementation of leading edge algorithms for AI/deep learning, multi-modal sensor data processing and fusion as well as image and video en/decoding on the same architecture in highly efficient single-chip solutions. With its processor IP, application libraries and development tools, videantis globally supports semiconductor manufacturers, automotive OEMs and tier 1 suppliers in serial production together with customers in other high-volume embedded markets. videantis has been recognized with the Red Herring Award and multiple Deloitte Technology Fast 50 Awards as one of the fastest growing technology companies in Germany.

For more information please contact:
Stephan Janouch, Director Marketing
Email: stephan.janouch@videantis.com
Phone: +49 (511) 51 522 3-35

Featured image:

The post Funding round fuels videantis’ growth appeared first on videantis - processors for deep learning, computer vision and video coding.

Hannover, Germany, June 09, 2022 – videantis GmbH, a leading supplier of deep learning, computer vision, image processing, and video coding solutions, today announced the tape-out of a low-power AI chip based on its v-MP6000UDX unified processing platform. The chip development is part of the European TEMPO project and targets several autonomous driving use cases. TEMPO (Technology and hardware for neuromorphic computing) is an ECSEL JU project supported by the EU Horizon 2020 programme and by the German Federal Ministry of Education and Research (BMBF).

The tape-out of the AI chip has been achieved together with the Fraunhofer Institute for Integrated Circuits IIS. It constitutes an important milestone of the collaborative research project TEMPO on its way to strengthening the European semiconductor supply chain. Together with automotive application partners like Valeo and InnoSenT, the AI chip will be used within the TEMPO project to accelerate deep learning inference for automotive use cases at a small silicon footprint and low power consumption which previously required high-end compute devices.

The heart of the AI chip is videantis’ v-MP6000UDX unified processing platform, which will be used to run various neural networks to process radar, lidar or camera data for object detection, classification, and localization. It is a highly scalable multi-core architecture combined with a tailored bus fabric and multi-banked shared on-chip SRAM which delivers exceptional efficiency and performance for a variety of algorithm types, like deep learning, computer vision, image processing and video coding. The project also makes extensive use of videantis’ comprehensive v‑CNNDesigner front-to-end tool flow, offering automatic mapping and optimization of neural networks onto the target architecture without requiring deep programming expertise.

About TEMPO
TEMPO (Technology and hardware for neuromorphic computing) is a European innovation project. This project has received funding from the ECSEL Joint Undertaking (JU) under grant agreement No 826655. The JU receives support from the European Union’s Horizon 2020 research and innovation programme, and from Belgium, France, Germany, Netherlands, Switzerland. TEMPO was kicked off on the 1st of April 2019 and has a duration of three and a half years. The consortium of this ambitious project consists of no less than nineteen members. Imec takes the lead as the sole Belgian consortium partner. The other consortium members are, for France: CEA-LETI, ST-Microelectronics Crolles, ST-Microelectronics Grenoble, Thales Alenia Space and Valeo. For Germany: Bosch, Fraunhofer EMFT, Fraunhofer IIS, Fraunhofer IPMS, Infineon, Innosent, TU Dresden and videantis. For the Netherlands: imec the Netherlands, Philips Electronics and Philips Medical Systems. For Switzerland: aiCTX and the University of Zürich.
For more information, please visit https://tempo-ecsel.eu/.

About videantis
Headquartered in Hannover, Germany, videantis GmbH is a leading supplier of deep learning and computer vision solutions based on its unified processing platform. With its processor IP, hardware/software-based solutions for deep learning, computer vision, image processing and video coding, as well as its development tools, videantis globally supports semiconductor manufacturers, automotive OEMs and tier 1 suppliers together with customers in other high-volume embedded markets. videantis has been recognized with the Red Herring Award and multiple Deloitte Technology Fast 50 Awards as one of the fastest growing technology companies in Germany.

For more information please contact:
Stephan Janouch, Director Marketing
videantis GmbH
Email: stephan.janouch@videantis.com
Phone: +49 (511) 51 522 3-35
Web: www.videantis.com

The post TEMPO AI chip tapes out with videantis processor platform appeared first on videantis - processors for deep learning, computer vision and video coding.

Dear videantis customer, partner, friend or other contact,

it’s almost Christmas. Again. So let me start off this videantis Christmas newsletter with my best wishes – may your holidays be filled with joy this year -, and a guarantee: this text will not be about Corona.

The topic I’d like to elaborate on in this text is a challenge that most companies believed they had mastered already: supply chain. Truth is, the world is not as flat a Thomas Friedman had sketched it out in his excellent book more than 16 years ago (read the summary on Wikipedia here, in case you’re interested). Maybe it was for some time. However, “Globalization 3.0”, as Friedman called it, has proven to be a fragile and imperfect system.

A temporary change in demand forecast, some not so surprising changes in consumer behaviour and a pinch of global political friction led to some serious “supply chain turmoil”. This isn’t happening only in the semiconductor industry, but, I believe, this is where the biggest effects will be seen or are already visible:

• Big investments in semiconductor foundries, e.g. in Japan, the US and even Europe
• Governmental funding of semiconductors, e.g., in the US or in Europe
• Companies starting to develop, or at least specify, their own chips, e.g., vehicle manufacturers

Now, will this be a flash in the pan? Or is this a lessons learned on the importance of semiconductors? Or will it eventually lead to excess supply of semiconductor manufacturing resources? The future is still to be written…

Anyway, besides these intricacies, a lot of interesting stuff did happen this year. For videantis, we made exciting progress in various areas (see below) and there is more to come in 2022. Stay tuned!

Stephan Janouch, Director Marketing @ videantis

videantis achieves Automotive SPICE® Level 2 certification

videantis, a leading supplier of deep learning, computer vision, image processing, and video coding solutions, powering already more than 10 million cars on the road, announces the achievement of Automotive SPICE® Level 2 certification (Automotive SPICE® is a registered trademark of the Verband der Automobilindustrie e.V. (VDA)).
Automotive SPICE® (Software Process Improvement and Capability dEtermination) is a domain specific version of the international Standard ISO 15504 to assess automotive suppliers regarding their capabilities in design, development, testing, and maintenance of software.

Read full press release

videantis processing platform reduces cost, increases flexibility of fail-operational systems

The concept for this solution was developed within the European PRYSTINE (Programmable Systems for Intelligence in Automobiles) project.
For three years, and equipped with a budget of € 50 Million, about 60 project partners were collaborating to build a Fail-operational Urban Surround perceptION (FUSION) based on Radar and LiDAR sensor fusion and control functions, eventually enabling safe automated driving in urban and rural environments.
The output of this project helps to address advanced functional safety requirements on embedded videantis-based multiprocessor systems up to ISO26262 ASIL D.

Read full press release

videantis and Continental sign strategic supplier contract and announce SOPs with videantis-enabled camera system

videantis has been working with Continental towards developing their next-generation smart rear view cameras. The automotive-grade software and development tools for its processors, which videantis both supplied to Continental, are deployed through several OEMs and in various car platforms already starting earlier this year.
The SoCs (systems-on-chip) sourced from a leading global semiconductor supplier for a smart camera program are based on videantis’ proprietary processing architecture and are accompanied by programming tools originating from videantis.

Read the full press release

videantis passes milestone of enabling 10 million production vehicles

For the last couple of years, growth in the automotive electronics industry has been fueled by the implementation of sophisticated active and passive safety systems. Specifically, Advanced Driver Assistance Systems (ADAS), leading towards higher levels of automated driving, are relying on more sensors, more data and hence require more compute power.
More than 10 million cars have been shipped with videantis-based chips inside used for ADAS and other high-end applications. Further SOPs coming up in the following months.

Read the full press release

The post Christmas newsletter 2021 appeared first on videantis - processors for deep learning, computer vision and video coding.

• videantis software development is compliant to Automotive SPICE® Level 2
• Assessment was conducted by Continental SQM
• Automotive SPICE® Level 2 certification of videantis software offerings reduces development cost and accelerates time-to-production for Tier 1s and OEMs

Hannover, Germany, December 1, 2021 – Today, videantis, a leading supplier of deep learning, computer vision, image processing, and video coding solutions, powering already more than 10 million cars on the road, announces the achievement of Automotive SPICE® Level 2 certification (Automotive SPICE® is a registered trademark of the Verband der Automobilindustrie e.V. (VDA)).

Automotive SPICE® (Software Process Improvement and Capability dEtermination) is a domain specific version of the international Standard ISO 15504 to assess automotive suppliers regarding their capabilities in design, development, testing, and maintenance of software.

The independent assessment was conducted by Continental SQM (Supplier Quality Management), one of the world’s largest automotive suppliers for assisted and automated driving solutions. While Level 2 was the highest level this project-specific assessment was targeted for, all processes certified are already deployed on organizational level and ready to achieve Level 3 in the next assessment.

“The compliance of videantis with Automotive SPICE® Level 2 underlines the quality of our software development and the maturity of our processes”, says Dr.-Ing. Hans-Joachim Stolberg CEO/CTO at videantis. “Tier 1s and OEMs are not only ensured to obtain the most optimized software products on the market directly from videantis as the originator of the underlying processor technology, but can at the same time rely on the certified quality of our software offerings ready to be taken directly into production. This not only helps to save substantial cost for in-house development but also significantly accelerates time-to-production.”

The Automotive SPICE® Level 2 certification is just one of several initiatives at videantis to support automotive suppliers and OEMs by reducing cost and risk, managing complexity, and ensuring highest quality when developing next generation systems for electric, connected, and autonomous vehicles.

About videantis
Headquartered in Hannover, Germany, videantis GmbH is a leading supplier of deep learning and computer vision solutions based on its unified processing platform. With its processor IP, hardware/software-based solutions for deep learning, computer vision, image processing and video coding, as well as its development tools, videantis globally supports semiconductor manufacturers, automotive OEMs and tier 1 suppliers together with customers in other high-volume embedded markets. videantis has been recognized with the Red Herring Award and multiple Deloitte Technology Fast 50 Awards as one of the fastest growing technology companies in Germany.
For more information, please visit www.videantis.com.

For more information please contact:
Stephan Janouch, Director Marketing
stephan.janouch@videantis.com
Phone: +49 (511) 51 522 3-35

The post videantis achieves Automotive SPICE® Level 2 certification appeared first on videantis - processors for deep learning, computer vision and video coding.

• With fine-grain scalability and flexible redundancy, the videantis unified processing platform enables fail-operational processing and functional safety up to ASIL D for highly automated driving at reduced cost
• Both fail-operational sensor-based signal processing as well as central AI inference are supported by the videantis v‑MP6000UDX unified platform
• The technology has been validated as part of the € 50 million PRYSTINE research project

Hannover, Germany, October 25, 2021 – Today, videantis, a leading supplier of deep learning, computer vision, image processing and video coding solutions, announced availability of its technological platform for fail-operational processing at reduced cost for both smart sensors as well as highly integrated central ECUs. The concept for this solution was developed within the European PRYSTINE (Programmable Systems for Intelligence in Automobiles) project.

For three years, and equipped with a budget of € 50 Million, about 60 project partners were collaborating to build a Fail-operational Urban Surround perceptION (FUSION) based on Radar and LiDAR sensor fusion and control functions, eventually enabling safe automated driving in urban and rural environments.

The output of this project helps to address advanced functional safety requirements on embedded videantis-based multiprocessor systems up to ISO26262 ASIL D. Compared to traditional lockstep architectures, more than 50% of the cost can be saved due to the reduction of the silicon area.

The cost reduction is achieved by run-time failure detection schemes comprising of core self-test modules and a result monitoring software layer (RMSL) applied to the fine-grain and highly scalable videantis multiprocessor system. With this, faults can be detected during runtime and processing can be continued while excluding any faulty resource, without the need for duplicate hardware. E.g., with a silicon area overhead of only 3%, a multiprocessing system comprising 32 videantis cores can be turned into a fail-operational processing platform.

“PRYSTINE covers the most important aspects of autonomous driving: performance, efficiency and especially safety. We’re proud to have contributed with our highly versatile processing platform which allows for the most cost-efficient way to implement fail-operational functionality”, says Dr. Hans-Joachim Stolberg, CEO/CTO of videantis.

videantis v-MP6000UDX processing platform is highly suited for fail-operational applications such as highly automated driving. With its scalability, it can cover the full range from smart image, Radar, LiDAR sensors (1 to 16 cores) to high-performance AI inference computers (>100 cores). The unified architecture allows the implementation of various functions: video coding, image or graphics processing, computer vision, deep learning using a multitude of network topologies, or even control functions. Utilizing redundancy, self-test and other control mechanisms enables customers to build safe systems according to ISO26262 up to ASIL D, using less silicon space or hardware overhead than conventional lockstep architectures.

About videantis
Headquartered in Hannover, Germany, videantis GmbH is a leading supplier of deep learning and computer vision solutions based on its unified processing platform. With its processor IP, hardware/software-based solutions for deep learning, computer vision, image processing and video coding, as well as its development tools, videantis globally supports semiconductor manufacturers, automotive OEMs and tier 1 suppliers together with customers in other high-volume embedded markets. videantis has been recognized with the Red Herring Award and multiple Deloitte Technology Fast 50 Awards as one of the fastest growing technology companies in Germany.
For more information, please visit www.videantis.com.

About PRYSTINE
PRYSTINE (Programmable Systems for Intelligence in Automobiles) is a research and innovation project which is co-funded by the ECSEL JU (Electronic Components and Systems for European Leadership, Joint Undertaking) and the national governments of the ECSEL member states. Members of the PRYSTINE consortium comprise 60 partners from 14 countries including automotive OEMs, semiconductor manufacturers, technology partners and research institutes. The goal of PRYSTINE is to deliver a fail-operational sensor-fusion architecture, integrated with a safe AI framework for object recognition, scene understanding and decision making, supporting the transition to highly automated vehicles.
For more information, please visit https://prystine.eu/.

For more information please contact:
Stephan Janouch, Director Marketing
stephan.janouch@videantis.com
Phone: +49 (511) 51 522 3-35

The post videantis processing platform reduces cost, increases flexibility of fail-operational systems appeared first on videantis - processors for deep learning, computer vision and video coding.

• videantis and Continental signed a strategic supplier contract.
• The videantis processors, software and development tools are now being used for smart automotive cameras in SOPs with several OEMs.
• The videantis products are automotive grade, developed according to Automotive SPICE and conforming to ISO26262.

Hannover, Germany, April 26, 2021 – Today, the signing of the long-term-strategic partnership agreement between videantis GmbH and Continental was announced. videantis, a leading supplier of deep learning, computer vision, image processing and video coding solutions, has been working with Continental towards developing their next-generation smart rear view cameras. The automotive-grade software and development tools for its processors, which videantis both supplied to Continental, are deployed through several OEMs and in various car platforms already starting earlier this year.

The SoCs (systems-on-chip) sourced from a leading global semiconductor supplier for a smart camera program are based on videantis’ proprietary processing architecture and are accompanied by programming tools originating from videantis. For making optimal use of this high-performance, ultra-low-power processors platform and accelerating projects time to completion, Continental relied on the software IP, tools and unique expertise of videantis as the inventors of this technology.

“videantis processor IP was the key ingredient for us to decide on this hardware platform. During the cooperation, videantis already proved to be a vital technology partner. It is ensured that we can deliver a wide range of best-in-class features while meeting the most stringent quality and functional safety requirements to enhance the user experience and driving safety. Our partnership enabled us to win key OEM customers, and we’re looking forward to continue teaming up with videantis to bring superior technology to the market for many years to come”, said Dr. Sascha Semmler, Head of Program Management Camera from the Advanced Driver Assistance Systems business unit at Continental.

The versatility of the videantis processor architecture allows a wide variety of vision and imaging algorithms to run on the same architecture. The architecture is fully software programmable, allowing feature upgrades and algorithm improvements over time. This enabled the development of very small cameras and to address a wide range of active safety use cases such as automatic braking for pedestrians, warning for crossing traffic, and assist in driving with a trailer.

Continental licensed both computer vision and image processing software libraries, as well as development tools that aid in software development and production sign-off for the cameras. For a successful project completion, rigorous automotive quality requirements and processes that include adhering to Automotive SPICE and ISO26262 had to be fulfilled. The software libraries and tools that videantis provided meet these stringent functional safety and automotive grade quality requirements.

“We’re excited to be working with Continental. They are one of the world’s largest automotive suppliers, and we’re honored to be nominated their strategic supplier,” said Dr. Hans-Joachim Stolberg, CEO at videantis. “Continental’s adoption of our technology for automotive serial production with multiple OEMs is a testimony to the quality of our products. We are looking forward to a fruitful long-term partnership and together drive the widespread use of autonomous mobility enabling technologies.”

Due to the cooperation between the two companies, serial production with OEMs started earlier this year.

About videantis
Headquartered in Hannover, Germany, videantis GmbH is a leading supplier of deep learning and computer vision solutions based on its unified processing platform. With its processor IP, hardware/software-based solutions for deep learning, computer vision, image processing and video coding, as well as its development tools, videantis globally supports semiconductor manufacturers, automotive OEMs and tier 1 suppliers together with customers in other high-volume embedded markets. videantis has been recognized with the Red Herring Award and multiple Deloitte Technology Fast 50 Awards as one of the fastest growing technology companies in Germany.

About Continental
Continental develops pioneering technologies and services for sustainable and connected mobility of people and their goods. Founded in 1871, the technology company offers safe, efficient, intelligent, and affordable solutions for vehicles, machines, traffic and transportation. Continental generated preliminary sales of €37.7 billion in 2020 and currently employs more than 235,000 people in 58 countries and markets. In 2021, the company celebrates its 150th anniversary.

For more information please contact:
Stephan Janouch, Director Marketing
videantis GmbH
Phone: +49 (511) 51 522 3-35
Email: stephan.janouch@videantis.com
Web: www.videantis.com

Soeren Pinkow, External Communications Autonomous Mobility and Safety Business Area
Continental
Phone: +49 (69) 7603 8492
Email: soeren.pinkow@continental.com
Web: www.continental.com

Featured image

The post videantis and Continental sign strategic supplier contract and announce SOPs with videantis-enabled camera system appeared first on videantis - processors for deep learning, computer vision and video coding.