Event-based vision sensor caters to edge AI
Prophesee has launched the GenX320, an event-based Metavision sensor architected for integration into ultra-low-power edge AI vision devices. Offered in a tiny 3×4-mm die size, the back-side illuminated (BSI) stacked sensor provides a 320×320 6.3-µm pixel array in a 1/5-in. optical format.
The GenX320 is the fifth generation of the company’s event-based Metavision sensing technology, promising the speed, low latency, dynamic range, and power efficiency required by embedded at-the-edge vision systems. It also brings the privacy benefits of event-based vision to numerous applications, including AR/VR headsets, security and monitoring/detection systems, touchless displays, and always-on smart IoT devices, to name a few.
On-chip intelligent power management modes, such as wake-on-event, deep sleep, and standby, reduce power consumption to as low as 36 µW. Typical operating power is 3 mW. The GenX320 provides a dynamic range of >120 dB and a timestamp resolution of 1 µs. MIPI or CPI data-output interfaces enable low-latency connectivity to embedded processing platforms, including low-power MCUs and neuromorphic processor architectures.
The GenX320 event-based Metavision sensor is available for purchase from Prophesee and its sales partners. It is supported by a variety of development tools, as well as adapter kits for connecting to a range of embedded platforms, such as STM32 MCUs.
Find more datasheets on products like this one at Datasheets.com, searchable by category, part #, description, manufacturer, and more.
googletag.cmd.push(function() { googletag.display(‘div-gpt-ad-native’); });
–>
The post Event-based vision sensor caters to edge AI appeared first on EDN.
