Streaming Camera Ogles Machine Vision Applications

Vision Research introduces its Phantom S990, which it claims is the world’s fastest machine vision camera. The S990 features a combination of fast frame rate, high resolution, and available throughput for use in demanding machine vision applications in multiple industries.


The camera delivers direct data transfer speeds up to 9 Gigapixels/second to capture 938 fps at full 9-Mpx 4,096 x 2,304 resolution. It leverages the same CMOS 9.4-megapixel sensor found in the Phantom Flex 4K high-speed camera, capturing 12-bit images and delivering exceptionally high image quality. Using up to 16 standard CoaXPress (CXP6) channels, the S990 is compliant with GenICam and streams directly into PCI Express frame grabbers.

Fierce AI Week

Register today for Fierce AI Week - a free virtual event | August 10-12

Advances in AI and Machine Learning are adding an unprecedented level of intelligence to everything through capabilities such as speech processing and image & facial recognition. An essential event for design engineers and AI professionals, Engineering AI sessions during Fierce AI Week explore some of the most innovative real-world applications today, the technological advances that are accelerating adoption of AI and Machine Learning, and what the future holds for this game-changing technology.


The camera also features a general-purpose input/output (GPIO). It includes signals beneficial in standard high-speed applications, such as Time Code In and Out, as well as signals commonly found in streaming applications. Specifications of the Phantom S990 include:

  • Up to 9 Gpx/second (66 Gbps) of streaming capability
  • 938 fps at 4,096 x 2,304 and 1,000 fps at 4,096 x 2,160
  • 9.4-megapixel CMOS sensor in color or monochrome
  • 6.75-µm pixel size
  • 12-bit or 8-bit data transfer
  • Rolling, Global and Bright Field shutter selection
  • Up to 4 banks of 4 CXP ports
  • CXP and GenICam compliant  

Of course, you can always take a gander at the S990 datasheet.

Suggested Articles

Fact.MR sees global growth for current sensors at 8% a year through 2030. The situation for ADAS sensors is bleak for now, but up over a decade.

Broadband gaps include rural areas and poor neighborhoods and at-home student access, ITIF notes in new report

HP leads the pack, but Apple sees 36% surge in notebooks, desktops compared to a year ago