LIDAR + CAMERA + RADAR + IMU

Sensor fusion annotation,time-synced across modalities.

Multi-modal annotation with calibration-verified cross-modality consistency. Single 3D label projects to every camera, every radar return, every thermal frame.

Scope a Data Project See sample annotations

Cross-modal consistency PTP-synchronized

A 3D label is only useful if it lands on every sensor.

Separate per-sensor jobs can look complete and still disagree in the fused frame.

YPAI draws one object in the primary sensor and projects it through verified extrinsics onto every secondary stream. The annotator confirms the landing before the label is closed.

Street intersection with signs, traffic lights, vehicles, cones and barriers, every object boxed. pickup · occluded

One camera, fully labelled Twenty objects across seven classes, with occlusion and truncation recorded. Extent, class and identity are all a single camera can give. Depth is not among them, which is where the sensors below start earning their place.

What the projection must survive

  • Camera

    The cuboid lands on the pixels that actually belong to the object, including truncated and night frames.

  • Radar

    The same identity carries Doppler velocity where radar is in the stack, not a second guessed box.

  • Thermal

    The silhouette holds when RGB fails. Heat-only classes stay available when the taxonomy needs them.

PTP time base across the recording

Illustrative readout. The engagement sets the primary sensor, the projection policy and the drift threshold the delivery must report.

The stack you buy is the stack you can train.

Paying for isolated LiDAR boxes and isolated camera boxes is the expensive way to discover they do not occupy the same object.

  1. Range LiDAR
  2. Semantics Camera
  3. Velocity Radar
  4. Motion IMU + GPS
  5. Night Thermal

Most common stack

LiDAR + camera

Geometry from LiDAR, class and attributes from camera. One 3D box is projected into every camera view through verified extrinsics.

Primary
LiDAR cuboid, camera as semantic corrector
Hard part
Projection error when extrinsics drift, truncation, and night RGB
Typical output
3D boxes with camera-view projections, class, and occlusion state
Where it is used
ADAS perception baselines, robotics scene understanding

Weather-robust stack

LiDAR + camera + radar

The same identity also carries Doppler velocity. Radar keeps the object when rain, spray or darkness take the camera down.

Primary
LiDAR geometry, radar velocity, camera class
Hard part
Associating sparse radar returns to the cuboid without splitting identity
Typical output
Fused cuboid, velocity, and per-sensor visibility flags
Where it is used
Production AD perception beyond a camera-only stack

Geo-localized stack

LiDAR + IMU + GPS

Point clouds are labelled in a trajectory that stays georeferenced. The map and the object share one coordinate frame.

Primary
LiDAR in a SLAM or GNSS-stabilised world frame
Hard part
Keeping landmarks and dynamic objects distinct as the trajectory drifts
Typical output
Georeferenced clouds, trajectory, landmarks, LAS / LAZ where required
Where it is used
Surveying, mapping, outdoor mobile robotics

Low-light stack

Camera + thermal

RGB and long-wave thermal share one identity. When the camera goes dark, the thermal silhouette is still a labelled object.

Primary
Thermal silhouette with RGB class when light allows
Hard part
Calibration across very different resolutions and the hot-spot taxonomy
Typical output
Paired boxes or masks, thermal-only classes where the schema needs them
Where it is used
Night automotive, search and rescue, perimeter perception

Surround stack

Multi-camera array

Identity continues as the object leaves one camera and enters the next. The handoff is a labelled event, not a new object.

Primary
Shared identity across a time-synced camera ring
Hard part
Handoff at overlapping FOV edges and appearance change between cameras
Typical output
Per-camera boxes plus a cross-camera identity manifest
Where it is used
Surround perception, multi-camera surveillance, sports capture

The same fused scene answers four different buying jobs.

Per-sensor annotation cannot settle a disagreement between streams. Fusion-aligned labels can.

Wet city intersection at night with a cyclist and cars.

Perception that must survive weather and night.

Vehicle, pedestrian, cyclist and lane labels share one identity across LiDAR, camera and radar. Taxonomy can follow nuScenes or Waymo schemas when the engagement asks for that alignment.

A robot needs the obstacle and the grasp in the same frame.

LiDAR + camera + IMU for indoor and outdoor SLAM. Dynamic people, navigable floor and graspable objects are labelled against one trajectory.

Identity has to survive a camera handoff at night.

Multi-camera plus thermal. Cross-camera re-identification is a labelled event. Day and night coverage share the same person ID.

The map is only useful if the cloud is georeferenced.

LiDAR + IMU + GPS + camera. Delivery can include LAS / LAZ and a georeferencing check. BIM-ready when the engagement specifies it.

Production starts after calibration holds.

Schema, projection policy and a shared subset all serve one decision: is the multi-sensor contract stable enough to scale?

White hatchback with a roof sensor rack and a standing checkerboard calibration target.

  1. Schema and multi-sensor calibration

    Class taxonomy is locked. Per-sensor intrinsics, pairwise extrinsics and PTP timestamps are verified before anyone draws a production label.

    Output. Schema plus calibration verification record.

  2. Guideline and projection policy

    Visibility rules per sensor. Which stream is primary for each class, and which stream is allowed to correct it.

    Output. Versioned annotation guideline.

  3. Calibration round

    A shared subset is labelled in the fused viewer. Cross-modal agreement and projection error are measured. The guideline is revised on what the round actually found.

    Output. Cross-modal agreement record and revision decisions.

  4. The gate

    Production starts when the calibration round clears the task-specific projection and agreement thresholds in the acceptance plan.

    The gate is a recorded decision, not a mood. Drift after this point is reported, not silently absorbed.

    Output. Gate-pass attestation.

  5. Production in the fused viewer

    One 3D label in the primary sensor, projected to every secondary. The annotator validates the landing. Work runs in a single-tenant proprietary viewer.

    Output. Multi-modal annotations.

  6. QA, cross-modal audit and delivery

    Per-class scores per modality, projection-error report, time-sync drift audit, Article 30 records and a signed DPA.

    Output. Final package plus multi-modal metrics.

Start the scoping process

The evidence package is defined before production.

These records travel with the labels. They are specified in the statement of work, not assembled afterwards.

  • Multi-sensor calibration verification

    Intrinsic and extrinsic checks per sensor, plus a PTP drift report across the recording.

    calibration-verified.log

  • Cross-modal projection consistency

    The 3D box projected to every camera, radar return and thermal frame. Per-class projection error. Velocity delta where radar is present.

    projection-error.csv

  • Per-modality and cross-modality metrics

    Per-class scores on each stream, identity preservation across sensor handoff, and a distance breakdown when the task needs it.

    per-modality-iou.csv

  • Time-sync drift audit

    Frame-pair correspondence, interpolation policy for mismatched rates, and threshold flags.

    time-sync-drift.json

  • Processing and delivery record

    Article 30 records, signed DPA, lawful-basis documentation, 30-day erasure terms, and the sub-processor list.

    article-30-records.pdf

Bring the sensor mix, the calibration state and the acceptance problem.

A short brief is enough to start.

YPAI will identify the projection policy, the open ontology decisions and the first calibration step.

We reply within one business day with the questions that must be resolved before a pilot or production scope.

You bring
  • the perception or product objective
  • the sensor mix and rates
  • calibration state, when known
  • sample streams, when available
  • classes and attributes of interest
  • expected volume
  • required output format
  • acceptance criteria
YPAI returns
  • feasibility assessment
  • recommended mix and primary sensor
  • projection-policy decisions still open
  • proposed calibration method
  • applicable quality metrics
  • reviewer and adjudication model
  • data-processing requirements
  • evidence-package proposal, schedule and price basis

Answers that belong in the first conversation.

What calibration data do you need across the sensors?

Per-sensor intrinsics, pairwise extrinsics, and PTP-synchronized timestamps with sub-millisecond skew.

Calibration is verified before annotation. Drift is checked across the recording and reported at delivery.

How do you handle disagreement between sensors?

A documented projection policy decides which sensor is primary for each class.

Annotators validate the projection before the label is finalized. Remaining disagreement is recorded in the delivery report.

Do you handle thermal and multi-spectral?

Yes. Long-wave thermal, near-infrared and multi-spectral bands from drone or satellite capture.

Calibration is verified across those modalities. The taxonomy can include thermal-only classes such as hot-spot.

Where is the data processed?

EEA-resident. Norwegian company, EEA contributor network, EEA infrastructure.

30-day GDPR Article 17 erasure SLA. Norwegian jurisdiction. Transfer controls defined per project.

What output formats do you deliver?

nuScenes JSON, KITTI-360, AV2 SDK, and custom Protocol Buffers when the engagement specifies them.

Per-modality files plus a cross-modal manifest. Time-aligned multi-sensor packages.

Can public corpora be used as taxonomy references?

Yes, when the engagement asks for alignment with corpora such as nuScenes, Waymo Open, Argoverse 2, A2D2 or KITTI-360.

Production work runs against your own streams under the engagement DPA. Public corpus licences are checked per project.

Brief the sensor mix. The reply names the projection policy and the first gate.

Scope a Data Project