MESO SCALE · CVPRW DRIVEX 2026 · TRB ANNUAL MEETING

Seeing Through the Occlusion Shadow at Urban Intersections

Upgrading an ego vehicle from a 120° forward ADAS camera to a 360° roof-mounted AV LiDAR raises urban intersection observability from 0.37 to only 0.61. Our PACO framework proves mathematically and empirically why elevated roadside 3D LiDAR (1.00) is essential to protect occluded pedestrians and cyclists.

PACO: 0.37 → 0.61 → 1.00 n = 180 Audited VRU Near-Misses CVPRW DriveX 2026 NYC Urban Intersection Testbed
Geometric occlusion shadow cast by large urban vehicles versus elevated roadside LiDAR line of sight
3D OCCLUSION GEOMETRY · EGO VS. ELEVATED V2I CLICK IMAGE TO ENLARGE
0.37 → 0.61 Ego-Only Ceiling (ADAS → AV) 39% of intersection risk remains hidden even with 360° roof LiDAR
1.00 V2I Roadside LiDAR Observability Elevated mast looks over box trucks & buses into crosswalks
41% → 100% Conflict-Partner Visibility 41% (120° ADAS), 97% (360° AV, degrades on turns), 100% (V2I)
n = 180 Proactive Near-Misses Audited Sub-meter PET & TTC conflict trajectories without waiting for crashes

INTERACTIVE OBSERVABILITY EXPLORER

Compare 120° ADAS, 360° Roof AV, and Elevated Roadside V2I LiDAR

Toggle sensor architectures below to see how a single turning freight box truck casts a dynamic blind zone across active urban crosswalks — and how elevated roadside LiDAR resolves every occluded vulnerable road user.

All Conflict Partners Tracked in Metric 3D
V2I ROADSIDE 3D LIDAR BOX TRUCK EGO Pedestrian A Cyclist B
PACO Scene Observability 1.00
Conflict-Partner Visibility 100%
Occluded Objects (Urban Freight) 0.0 unmonitored
Governing Physical Mechanism Elevated mast overlooks truck roof — occlusion cone eliminated

PHYSICS-GROUNDED METRIC · PACO

Why Expanding Ego Field-of-View Cannot Solve Occlusion

Standard autonomous-driving benchmarks weight every object equally regardless of collision risk or line-of-sight physics. PACO (Proactive Risk-Weighted Cooperative Observability) couples 3D ray-cast occlusion geometry with kinematic conflict risk on real NYC urban LiDAR data:

  • 120° ADAS (0.37) → 360° AV (0.61) → Roadside V2I (1.00): Even an ideal 360° vehicle sensor loses 39% of risk-weighted intersection observability behind buses, delivery vans, and turning queues.
  • Freight Multiplies Blind Zones: Heavy urban freight nearly doubles occluded road users per frame from 1.7 to 3.3.
  • Placement Guidance: Turns qualitative V2I arguments into quantitative mast-placement criteria for municipal DOTs.
PACO intersection observability comparison across 120 ADAS, 360 AV, and Roadside LiDAR V2I
Risk-weighted observability across 120° ADAS (0.37), 360° AV (0.61), and Roadside LiDAR V2I (1.00).
NYC urban intersection fixed roadside 3D LiDAR and camera testbed
Fixed roadside 3D LiDAR + RGB testbed overlooking a high-volume New York City intersection.

PROACTIVE SAFETY AUDITING · CVPRW DRIVEX 2026

Diagnosing 180 Near-Miss Conflicts Before a Crash Occurs

Traditional traffic safety waits years for fatal or injurious crashes to accumulate. Using continuous 3D LiDAR trajectories at a complex NYC intersection, our proactive safety auditor extracts sub-meter Post-Encroachment Time (PET) and Time-to-Collision (TTC) conflict pairs automatically:

  • Spatial Conflict Heatmaps (n = 180): Pinpoints exact crosswalk conflict pockets where permissive turning vehicles encroach on pedestrians.
  • Micro-Behavioral Kinematics: Captures vehicle deceleration failures, abrupt pedestrian hesitation, and occluded curb-entry conflicts invisible to monocular traffic cameras.
  • Actionable Signal Countermeasures: Directly supports Leading Pedestrian Intervals (LPI), protected turn phases, and curb-daylighting redesigns.
Spatial density heatmap of 180 pedestrian-vehicle near-miss conflicts captured by roadside 3D LiDAR
Spatial conflict density heatmap across n = 180 audited pedestrian-vehicle near-miss events.
Metric 3D vehicle and pedestrian conflict trajectories during a high-risk intersection near-miss
Sub-meter 3D conflict trajectories resolving instantaneous speed, clearance, and PET/TTC.

PEER-REVIEWED PUBLICATIONS & PREPRINTS

Research Outputs

CVPR Workshop (DriveX) · 2026

Proactive Urban Intersection Safety Auditing Using Roadside 3D LiDAR

Metric 3D trajectory extraction, PET/TTC surrogate conflict screening (n = 180), and crosswalk hazard localization.

TRB Annual Meeting & SSRN Preprint · 6867604

PACO: Quantifying Cooperative Intersection Observability Across Ego and Roadside Sensors

Establishes the 0.37 (120° ADAS) → 0.61 (360° AV) → 1.00 (Roadside LiDAR V2I) observability law under urban occlusion.