Event-Based Machine Vision in Industry 4.0 Applications

Prophesee introduces reference system for implementing event-based machine vision

Prophesee SA (formerly Chronocam), known for neuromorphic vision systems, today introduced its first commercial implementation of the company’s event-based vision technology for machines.

The reference system, called Onboard, is aimed at developers of vision-enabled industrial automation systems such as robots, inspection equipment, and monitoring and surveillance devices. It features a VGA-resolution camera combined with a Qualcomm Snapdragon processor and can be integrated into a production camera system design.

Market forecasters estimate the overall industrial machine vision market to be valued at USD $7.91 billion in 2017 and is expected to reach $12.29 billion by 2023, at a CAGR of 7.61% between 2017 and 2023 (source: Research and Markets). Factors driving this growth include the increasing need for quality inspection and automation, growing demand for AI and IoT integrated machine vision systems, the increasing adoption of Industrial 4.0 technologies, development of new connected technologies, growing demands for predictive maintenance and government initiatives to support smart factories.

Prophesee’s Onboard reference system intends to provide a guide for developers to implement Prophesee’s neuromorphic vision technology for a variety of use models, including area monitoring, high-speed counting, vibration measurement, or real-time arc welding monitoring. Based on the company’s proprietary technique that uses a bio-inspired approach based on capturing events that change in the field of view of individual pixels (and avoiding the transmission of redundant data), machine vision systems that utilize Prophesee’s image data acquisition and processing solutions may save computational power, bandwidth, memory and energy.

The event-based approach also enables sensors to achieve much higher dynamic ranges than commonly associated with high-speed vision. And it allows cost-efficient sensors and systems to record events that would otherwise require conventional cameras to run at 10,000 frame/s and more.

The solution may also have applications in monitoring and surveillance. According to the company, the vision sensor’s high dynamic range allows operation in difficult lighting environments while producing much less data than a traditional frame-based approach and reducing the computational burden of scene analysis processing.

The company hopes to break into a wide array of markets, including accelerating quality assessment on production lines; reducing recalibration for high-speed inspection systems; positioning, sensing and movement guidance for robots to enable better human collaboration; and equipment monitoring (e.g. caused by vibration, kinetic deviations) making the system an asset for predictive maintenance and reduced machine downtime.

Onboard specifications

The Onboard reference systems consists of a VGA resolution, 640 x 480 pixel sensor with 15 μm pixels in a 3/4” optical format.

The dynamic range of the Prophesee vision sensor is greater than 120dB, with the ability to operate down to 100 millilux of scene illumination. The sensor is able to capture fast motions thanks to its sub-millisecond temporal resolution.

The Onboard reference system supports comprehensive connectivity options, including Ethernet, USB, HDMI and Wi-Fi.

For more robotics and automation news, follow @engcom_automate on twitter!