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

2026-07-17

AI Summary

This work addresses the challenge of reliable perception of vulnerable road users (VRUs) under occlusion, illumination variations, and adverse weather conditions on edge devices. The paper proposes CLIFE, the first fully edge-native camera–LiDAR fusion framework, which achieves online, target-agnostic calibration and lightweight late-fusion tracking. Implemented on a Jetson AGX Thor platform, the system aligns multi-sensor data and associates trajectories with per-frame complexity of O(N log N), entirely without cloud offloading. Evaluated across 12 intersections in Chattanooga under diverse lighting and weather conditions, CLIFE significantly enhances perception range and robustness while achieving 53.2 FPS in its late-fusion core—meeting real-time, intersection-scale deployment requirements and substantially reducing both bandwidth demands and hardware barriers.

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 late-fusion tracking entirely on a single embedded device, without cloud offloading. CLIFE adaptively refines camera-LiDAR alignment on demand and performs multi-sensor fusion and track association with O(N log N) per-frame cost. We deploy CLIFE across 12 signalized intersections in Chattanooga and conduct an in-depth evaluation at a representative intersection using synchronized camera-LiDAR data that spans diverse daytime, nighttime, and weather conditions. Our experiments demonstrate that the fusion architecture substantially enhances the perceptual range and robustness of the individual sensors under varied environmental and traffic conditions. The late-fusion core operates at 53.2 FPS on the Jetson AGX Thor, ensuring high throughput for real-time intersection-scale applications. By centering perception at the edge, CLIFE provides a deployable foundation for downstream safety applications, while reducing bandwidth and calibration overhead for agencies operating multi-intersection corridors.

Problem

• Vulnerable Road Users
• Edge Computing
• Camera-LiDAR Fusion
• Roadside Perception
• Occlusion

Innovation

• edge-native fusion
• targetless online calibration
• lightweight late-fusion tracking
• camera-LiDAR alignment
• real-time VRU perception