Machine Vision with on-device AI and Deep Learning
Various Artificial Intelligence and Deep Learning driven scenarios, addressed thanks to Sm_ALL with or without and embedded image sensor (camera), such as :
Live Quality inspection (defaults detection and tracking)
Live Measurements
Live squaring
Compatible with : existing IP RGB cameras
Use cases :
Live material detection (detection of context and determination of subject of focus)
Live automatic squaring (from different angles, in 2D or in 3D)
Live quality inspection (detection of specific scratches and defaults)
And last but not least : detection of what is important to detect for you on top of the objects already detected in this bundle.
The PHOENIX AI product involved :
SM_ALL with the ability to combine up to 4 detections at at time in real time with the video.
SM_ALL is a video pass-through with IP connectivity and PoE in/out with smart AI and Deep Learning processing in it at up to 60FPS in 4K :
1 PoE input with 100Mbits
1 100 Mbps output
1 PoE Output with 100Mbits
Workflow :
RJ45 IP Camera with PoE > Camera Stream Out > SM_ALL with PoE : decode, detections, encode, statistics > SM_All Stream Out with detection + statistics (JSON, XML, …) ( > VMS, UI Software, …)
Statistics & Logs for big data :
– in real time with defaults tracking, measures, …
Resolutions / Bandwidth :
From 250 pixels width, up to 4Kp60
Up to 100Mbits/stream