Roadmap
What's shipped, what we're building, and what's planned. We only list what we're confident about.
Shipped · 1
Scene Text Recognition
Perception — single-frame winIn progress · 9
80 everyday object types, out of the box (COCO-80)
Perception — single-frame winDetection
Perception — single-frame winSegmentation
Perception — single-frame winDepth
Perception — single-frame winBasic tracking
Perception — single-frame winOne clean box per detection without tuning — Batch 3ms (NMS-free)
Batch parity, breadth, textOriented boxes (OBB)
Batch parity, breadth, textHeading / rotation detection
Batch parity, breadth, textZones and lines — in-zone count + line-cross count
Density + the spatial foundationPlanned · 19
Pose
Batch parity, breadth, textKeypoints on every class
Batch parity, breadth, textRuns on Intel chips, not just NVIDIA (OpenVINO)
Batch parity, breadth, textBehavior
Video understanding + identityMotion (optical flow)
Video understanding + identityRespiration
Video understanding + identityHeart rate
Video understanding + identityRecognition across cameras (ReID)
Video understanding + identityCounting (density estimation)
Density + the spatial foundationProximity alerts
The event core (“alert me when”)Zone enter/exit
The event core (“alert me when”)Count-in-region (incl. crowd-density-in-zone)
The event core (“alert me when”)Fires once when it matters (debounce, hysteresis)
The event core (“alert me when”)Notifies your code directly (event queue + callbacks)
The event core (“alert me when”)Dwell, appear/disappear
Relational events + verticalsThreshold alerts (speed over X, count over N)
Relational events + verticalsPossession transfer — who is holding what, and when it changes hands
Relational events + verticalsAg expansion pack
Relational events + verticalsDeepStream integration — one-line add
DeployableWant something that isn't here? Request a feature →