Technical Note: 300FPS Video Recording/Streaming System

Our teammates at DAVE Embedded Systems have been working hard on new applications and prototypes during lockdown. They are always striving to improve their skills and knowledge around video manipulation and camera design including Machine Learning features on their products.

This particular Technical Note illustrates a Proof-of-Concept (PoC) that DAVE Embedded Systems engineered for a customer operating in the industrial automation market. The goal was to build a prototype of a high-frame-rate video recording/streaming system.

In a typical scenario, illustrated in the following diagram, this device would be used in fast automatic manufacturing lines for two purposes:

• Remote monitoring
• Detailed off-line "post-mortem" failure analysis.

In essence, the system consists of a high-frame-rate image sensor interfaced to a Linux-based embedded platform also denoted as PP in the rest of the document. The sensor frames a specific area of the production line and sends a constant-rate flow of frames to the PP for further processing, as detailed in the following sections.

Resolution and frame rate of this stream have to be carefully determined in function of the characteristics of the scene to shoot, first and foremost the speed of moving objects framed by the sensor and its lens. In the case under discussion, the customer specified a resolution of 1280x720, a frame rate of 300 fps, and the use of a global shutter. 

Read the full Technical Note here.

FPGA Event: Implementing Machine Vision with FPGA and SoC Platforms

Date: May 18, 2017
Time: 9am - 4.30pm
Location: MBDA, Six Hills Way, Stevenage, SG1 2DA

About
Machine Vision (MV) systems are ubiquitous, encompassing a wide range of applications from smart phones to ADAS and drones. Increasingly, these applications require intelligence at the edge or in the cloud, with FPGA and SoC based solutions forming the core of many MV systems.

Join NMI at MBDA facilities for the upcoming meeting of the FPGA Network to explore not only MV systems but also how FPGA and SoC can implement intensive applications including Machine Learning and Neural Networks.

Key themes will include:
OpenCV with FPGA / SoC, ADAS, Robotic Guided Vision / Drones, Industry 4.0, Defence, Machine Learning and much more.

**Non-member Early Bird Tickets are now on sale. Offer expires on 30th March**

Confirmed Speakers include:
MBDA Systems, Roke Manor Research, Dyson Robotics Lab (Imperial College), APTcore and Myrtle.


Register your interest here.

About NMI