Tam Bang, Hussam Abubakr, Emiliano de la Garza Villarreal +6 more
Intersections concentrate risk. Vehicles, pedestrians and cyclists all converge with different speeds and sightlines, and the interactions are complex enough that the useful question is not how many crashes happened but which conflicts nearly became one.
That reframing is what proactive means here. Waiting for crashes to accumulate is a slow and expensive way to learn that a junction is dangerous, and near-misses are far more frequent, so a system that can spot conflicts escalating gives you evidence in weeks rather than years.
PRISA uses roadside LiDAR, and the choice carries a real advantage beyond sensing. LiDAR returns geometry rather than imagery, so it can track that a person is crossing without recording who that person is, and it works in the dark. Monitoring public space continuously is much easier to justify when the sensor cannot recognise faces in the first place.
Urban intersections are among the most hazardous locations in road networks, posing significant risks to vehicles and vulnerable road users (VRUs) such as pedestrians and cyclists. The complexity of multi-agent interactions demands continuous, real-time monitoring systems capable of anticipating conflicts before they escalate into crashes. We present PRISA, a modular infrastructure LiDAR framework leveraging privacy-preserving, low-light-robust roadside sensors for long-term…
Candidate Attended Dialogue State Tracking Using BERT
arXiv (cs.LG) · July 17, 2026Presentation, Not Mechanism: A Render Confound in Deprecation-Aware Memory Evaluation
arXiv (cs.CV) · July 17, 2026PIXIE: A Zero-Shot texture-invariant 6D pose estimation framework for unseen objects with assembly defects
arXiv (cs.AI) · July 17, 2026DPNeXt: A Lightweight Multi-Scale Feature Fusion Framework for Efficient ViT-Based Multi-Task Dense Prediction