Vision Systems are riding technology waves

In manufacturing, when the application is right, vision systems are incredibly powerful and their benefits are obvious. They can ensure impeccable quality, seamlessly integrate into assembly lines, see defects humans can’t, and they never need a break. On the other hand, often when we think of vision systems, we think expensive, precise, difficult to maintain, and often temperamental systems that can take on a life of their own. It used to be, that the application had to be exactly right to justify the expense and the headache.

Things are changing fast

There are a few technology advancements that have made vision systems far more accessible and Overview builds products that take advantage of these developments. First is the connected system. It sounds simple, but connecting a vision system to the internet allows you to have a full time support person constantly monitoring your system. If anything goes wrong, nearly all problems can be solved remotely without any lag for travel or access to a factory. In Overview’s case, the upkeep remains the responsibility of the provider. The result is systems with excellent uptime.

Vision systems have a long history in the bottling industry where volumes are high and the position and lighting can be controlled

Deep Learning changes everything

The second reason these systems behave so differently is a new class of inspection algorithms that are much more forgiving than traditional algorithms. Based off of deep learning, the same approach used in self-driving cars, error spotting algorithms can work without controlled lighting and with much more positional variability. Before deep learning, machine vision algorithms hadn’t changed in 30 years. While computers got better (and less expensive–helpful!) the fundamentals of inspection only improved incrementally, until deep learning arrived.

Deep learning allows a much more flexible system that can be used on a whole new set of applications. Just like a computer can drive a car in all weather conditions, and on all types of roads, vision systems can handle much more lighting and positional variability. A $1,000 computer can eliminate $25,000 of lighting and fixturing cost. These systems can work on lower volumes and catch more general defects.

 Secondary benefits abound

First and foremost connected systems allow instant access from anywhere on earth. This can be very helpful for centralizing operations. Additionally, connected systems can log essentially infinite amounts of data. Every picture, and all the surrounding information can be stored in a database and easily recalled. Build rates and failure rates can be captured and easily referenced. The image archive can also be a valuable tool for engineers in all parts of the organization and can help limit the size of recall or containment if something unexpected happens in the future.

In summary

All of a sudden, vision systems are now:

  • Less expensive, due to Moore’s law and other advances
  • Painless to run, due to the connecting them to the internet, and
  • Appropriate for far more inspection applications, due to deep learning

Your factory probably has far more affordable applications than you realize. Feel free to reach out to Overview and we’ll help you figure out where you may be able to add an automated check. We run free feasibility studies through a mobile tool that you can get set up with in minutes.

About the author

Chris Van Dyke is Overview’s CEO and one of its founders. Before Overview Chris worked at Tesla for eight years where he led the team that designed the Gigafactory. Chris left Tesla to start Overview with the goal of combining the exciting promise of computer vision with the tangible benefits and satisfaction of the manufacturing field.

Contact

email – chris@overview.ai

Russell Nibbelink Overview Co-founder

Russell Nibbelink

Co-founder & Head of Engineering
Russell is a co-founder and head of engineering of Overview. At Overview, Russell helps customers implement cutting edge high speed Deep Learning algorithms. Prior to joining Overview, he was a software engineer at Salesforce where he worked on web-scale infrastructure projects. Russell received his BS from UC Berkeley’s College of Engineering, where he helped teach a class on High Performance Computing.
Chris Van Dyke Overview CEO

Chris Van Dyke

Co-founder & CEO

Chris Van Dyke is a co-founder and the CEO of Overview. Prior to founding Overview, Chris spent eight years in manufacturing engineering at Tesla. Most recently, he led the 80 person battery design team through the launch of the Model 3. During which time he was principally responsible for taking the team from battery design to high-volume production. Earlier in his career at Tesla he managed the infrastructure and equipment design for the first Gigafactory project including equipment for supporting battery cell manufacturing. Chris also launched Tesla’s Electric Vehicle Supercharger Program, which currently has more than 16,000 stations nationwide.

Chris holds several patents from his time leading custom equipment design while a Senior Engineer at H2Gen Innovations. Chris received his BS from Stanford University in Mechanical Engineering and an MS from the University of Virginia in Chemical Engineering.

Austin Appel

Co-founder & Head of Product

Austin Appel is a co-founder and head of product of Overview. At Overview, Austin leads product development and operations. Prior to Overview, Austin spent four years at Tesla in roles across battery manufacturing and R&D. He led the DFM and automation efforts for Model 3 battery pack production at Tesla’s first Gigafactory. Previously he expanded Tesla’s production of Model S and X battery packs through equipment design and implementation. He holds a dual bachelors degree in Manufacturing Engineering and Mechanical Engineering from Northwestern University.