December newsletter

Happy holidays and best wishes for 2019!

We would like to send you our warmest thoughts and best wishes for a wonderful holiday season and a very happy new year. We’ve had a fantastic 2018 at videantis and we’re happy to be working with many of the best companies and people in our field. We would like to thank our customers and are looking forward to working with you all into 2019.

Our best blogs, articles and show reports

We started off our year with a bang by announcing our new v-MP6000UDX processor and tools for deep learning at CES. This new processor increases deep learning algorithm performance by up to three orders of magnitude, while maintaining compatibility with the already very powerful and successful v-MP4000HDX architecture. Reception has been very positive with the EETimes, the Linley Group, and BDTI publishing articles. Jeff Bier, founder of the Embedded Vision Alliance, called videantis a pioneer in enabling the proliferation of computer vision into mass-market applications.

In February we published “Computer Vision in Surround View Applications,” together with Embedded Vision Alliance member company AMD. In the article we go into detail on how to stitch together multiple images capturing varying viewpoints of a scene, in a variety of applications. We also published our Mobile World Congress show report – 8 things we learned. To save you a click: it can snow in Barcelona, the mobile industry is still growing, AI and face analysis are big themes, the phone’s camera remains a key differentiator, displays are moving closer to our eyes, Huawei again had the biggest booth, and there was quite a bit of automotive technology at this mobile show also.

In April we spoke and exhibited at the Linley Spring Processor Conference, for which we also wrote a show report. Linley highlighted four areas where AI plays a key role: data centers, automotive, client computing, and IoT. We presented our new v-MP6000UDX deep learning processor architecture. Our single scalable processor architecture covers both ultra-low power and low cost applications as well as extreme performance, beyond 25 TMACs per second.

In May we moved into our new office to support our growing company. We’re happy to report we’ve added several new engineering staff to our team. Another key event in May was the Embedded Vision Summit. With over 1000 attendees and 90 presentations across six tracks all focused on embedded vision, it’s a leading event of the year. We also published an introductory article to deep learning, of course one of the key topics at the show.

In September we spoke at the great AutoSens conference. Our show report gives an overview of the event, highlighting five key lessons we learned: interior cameras are coming to your car, we can’t test drive trillions of miles, we need to simulate, sensors are going to be invisible, digital mirrors, and that the automotive industry is all about self-driving, but all the talks are about ADAS.

Since deep learning consumes very high compute resources, many SOC architects are adding these accelerators to their designs. But adding a deep learning accelerator isn’t really enough. You also need a vision processor that efficiently runs image processing and classical computer vision algorithms. Last month we published an article that highlights 6 reasons deep learning accelerators need vision processors.

Onward to CES

Next up is CES in Las Vegas. We will be showing several demonstrations in our private suite at the Westgate right at the convention center. On display we’ll have automotive cameras that have our technology inside, and a plethora of demonstrations including deep learning, Structure from Motion/SLAM, video compression, optical flow, and OpenCV acceleration, all running in silicon on our own multicore, high-performance, low-power processor architecture.

We’re happy to discuss in more detail what we’ve been working on and how we can bring low power deep learning, computer vision, imaging and video coding to your devices and systems. Our schedule is pretty full, but feel free to contact us to set up an appointment. We also still have a few free entrance passes we can give away.

2019 is bound to get even better for videantis and the visual computing industry. We’re excited about next year and are wishing you all the best.

Schedule a meeting
 

Upcoming events

Schedule a meeting with us by sending an email to sales@videantis.com. We’re always interested in discussing your video, vision, and deep learning SOC design ideas and challenges. We look forward to talking with you!