Hevolve AI: Self-Evolving Multimodal AI Agents

Turn your domain expertise into AI agents that keep learning. Hevolve AI lets experts build multimodal AI systems by talking to them and correcting them in real time, with no code to write.

Key Features

Quick Links

© 2024 Hevolve AI Pvt Ltd. All rights reserved.

← All research
Artificial Intelligence
arXiv (cs.CV) · July 17, 2026

CLIFE: Camera-LiDAR Fusion Framework for Edge-Deployable Roadside VRU Perception

Tam Bang, Hoang H. Nguyen, Lei Cheng +6 more

Combining a camera with LiDAR gives roadside perception the best of both: appearance from one, precise geometry from the other. The difficulty is that pedestrians and cyclists get occluded, lighting changes constantly, and weather does what it likes, so the fusion has to hold up in conditions nobody chose.

The authors identify a deployment gap rather than an accuracy gap. Existing fusion systems assume cloud or server-grade compute, and an actual intersection has a small box on a pole with a power budget and a hard latency limit. A method that works only where the hardware is generous does not get installed at the junctions that need it.

CLIFE is built edge-native for that reason, and includes targetless online calibration. That detail matters more than it sounds: poles vibrate and shift over months, and a system needing an engineer with a calibration target every time alignment drifts is not maintainable across a city.

From the arXiv (cs.CV) abstract

Reliable roadside perception of vulnerable road users (VRUs) remains challenging under occlusions, variable lighting, and diverse weather conditions, particularly under strict edge-computing and latency constraints. Existing multi-sensor fusion systems rely on cloud or server-grade infrastructure, creating a deployment gap at real-world intersections. We present CLIFE, an edge-native camera-LiDAR fusion framework that integrates targetless online calibration and lightweight…


More Artificial Intelligence papers