Transaction engine · the core intelligence

Tollscopic binds evidence to the vehicle path before it creates the transaction.

Most tolling systems still match device events using time windows. That works until a real road gets messy. Tollscopic uses the physical trajectory as the organizing object: track the vehicle first, then ask which evidence belongs to it.

01 · What goes wrong

Timing windows fail exactly when transactions matter most.

Roads do not produce clean event sequences. The hard problem is not collecting signals — it is deciding which plate read, tag read, axle event, and classification output belong to the same vehicle.

01
Trucks block plate views

The plate camera sees the wrong vehicle in the window where it expected to see the right one.

02
Two vehicles overlap

Tag and plate reads arrive with overlapping timestamps. Timing windows do not know which is which.

03
Lane straddles

A vehicle drifts across lane markings. Lane-keyed correlation cannot decide where the evidence belongs.

04
Missing reads

A plate read fails. A tag is absent. Timing windows still try to assemble a transaction from whatever they have.

02 · Trajectory correlation

The vehicle path is the correlation key.

Tollscopic tracks each vehicle through the toll zone as a physical object. Plate, tag, axle, LiDAR, and video evidence then attach to the vehicle that was actually present at the relevant position and time.

Legacy · timing-window correlation
L1 L2 L3 L4 gantry PLATE TAG AXLE PLATE TAG DEVICE EVENTS · TIME-NEAR Match by lane and timestamp Same window. Which events belong together? AMBIGUOUS · EXCEPTION QUEUE 3 transactions, 2 explainable
Tollscopic · trajectory binding
L1 L2 L3 L4 gantry PLATE T1 TAG AXLE T2 TAG PLATE T3 VEHICLE TRAJECTORIES · PHYSICAL Match by vehicle path Same evidence. Each event is bound to its vehicle. RESOLVED · 3 TRANSACTIONS each carries its evidence and provenance
Figure. Same toll zone, same evidence. Legacy timing-window correlation treats device events as the primary object and tries to match them by lane and timestamp; Tollscopic treats the vehicle trajectory as the primary object and binds evidence to the path that produced it. Lane straddles, occlusion, and dense traffic become tractable cases instead of exceptions.
03 · AVDC fusion

Classification is a fused decision with evidence behind it.

Tollscopic combines available signals — axle evidence, vehicle dimensions, visual classification cues, LiDAR measurements where configured, and trajectory context — and outputs class, confidence, and provenance. Never a black-box label.

EVIDENCE INPUTS
Five signals, one decision.
Axle evidence
Per-axle counts and spacing from vision or LiDAR
Vehicle dimensions
Length, height, width estimates
Visual classification
Body-class cues — truck, car, motorcycle
LiDAR (where configured)
Geometry confirmation independent of lighting
Trajectory context
Lane, speed, position through the zone
SCHEMATIC OUTPUT · avdc.classification.v1
{
  "txn_id":      "tx_2026_05_20_a8c2f",
  "class":       "TRUCK_3AX",
  "confidence":  0.92,
  "provenance": {
    "axle":      "vision · 0.95",
    "dimension": "lidar · 0.88",
    "visual":    "vlm · 0.91",
    "trajectory":"edge · 1.00"
  },
  "fallback":    null,
  "model_ver":   "avdc-2026.04-a"
}
RESOLVED · class agreement schematic
04 · From evidence to transaction

Five stages. The transaction is a derived record at the end of the chain.

The original evidence remains available for audit. The transaction itself carries the references back to it.

01 Capture

Each device produces timestamped evidence with confidence and provenance.

02 Bind to trajectory

Evidence attaches to the vehicle path that produced it.

03 AVDC fusion

Classification is decided from the fused evidence on the trajectory.

04 Assemble

Transaction record carries class, identifiers, evidence refs, and confidence.

05 Publish + acknowledge

Adapter posts the transaction to the back office. State is tracked.

EDGE CASES
Low confidence is a first-class state. If evidence is missing or contradictory, the platform preserves the uncertainty and routes the record for review rather than guessing.
05 · Back-office interface

The back office stays where it is. The roadside logic does not depend on it.

Transactions publish through a stable adapter. The operator's BOS / OBO remains the source of truth for billing. Tollscopic can change roadside logic, models, and devices without forcing the back office to change.

01
Webhook

HTTPS · HMAC-signed · idempotent. The default integration for modern BOS.

02
Event bus

Kafka topic. At-least-once delivery, dedupe on transaction id. Operators who already run an event-driven back office.

03
Custom adapter

For operators with non-modern interfaces. The roadside logic stays the same; the adapter normalizes the output to whatever the back office expects.

See it on a real toll zone.

Bring us the zone, the devices, and the back office. We will show how trajectory binding handles the cases your current system treats as exceptions.