Skip to content
Review Open access

Spatiotemporal Calibration, Fusion Strategies, and Future Sensing Modalities for Robust Roadside 3-D Object Detection: A Review

Nov 2026 · IEEE Sensors Journal · Vol 26, pp. 32065-32084 · 0 citations · 130 references

TL;DR

This survey identifies the physical sensing gap of current visible-light systems in extreme lighting conditions and proposes the integration of thermal imaging as a frontier modality for achieving true all-weather robustness.

Abstract

Infrastructure-based perception systems are pivotal to the advancement of vehicle-to-everything (V2X) cooperative autonomous driving, providing a comprehensive macroscopic perspective that mitigates the blind spots and limited sensing horizon inherent to onboard sensors. LiDAR and camera fusion has become the mainstream solution for reliable traffic monitoring. By leveraging complementary geometric and semantic information, this approach significantly enhances 3-D object detection performance. However, unlike vehicle-side perception, roadside systems confront unique challenges regarding long-term robustness, specifically spatiotemporal misalignment caused by the mechanical instability of sensor poles and feature degradation under adverse weather conditions. This article provides a comprehensive survey of technologies aimed at achieving robust roadside 3-D object detection. First, we systematically review existing infrastructure-side datasets, revealing a critical scarcity of data covering adverse weather and multispectral modalities compared to vehicle-side benchmarks. Second, we provide an in-depth analysis of spatiotemporal calibration technologies, identifying trajectory-based online calibration as the most viable solution for maintenance-free operation against dynamic sensor drift. Third, we categorize state-of-the-art multimodal fusion architectures, elaborating on the paradigm shift from feature-level projection to unified bird’s-eye-view (BEV) representations and Transformer-based interactions. Furthermore, we discuss infrastructure-specific optimization strategies, including height-aware view transformation, static background suppression, and scenario generalization. Crucially, this survey identifies the physical sensing gap of current visible-light systems in extreme lighting conditions and proposes the integration of thermal imaging as a frontier modality for achieving true all-weather robustness. Finally, open challenges such as edge–cloud synergy and collaborative perception are discussed.

Read PDF

Similar papers

Open access Nov 2026

GRNet: Global Resolution LiDAR--Camera Drift Correction Using Mixed Loss Network

Multisensor fusion of LiDAR and cameras plays a crucial role in advancing technologies such as environmental perception and 3-D reconstruction in autonomous vehicles and robotic systems. Achieving precise extrinsic calibration for heterogeneous sensors is essential, since it is the foundational step for effective and p...

Zi Wang, Ping-Ping Pan, You Li et al. · 0 citations
Open access 2026

Aerial Imagery-Based Validation of an Infrastructure-Based Highway Traffic Perception System

There is an increasing need for robust validation methods for smart roads (road infrastructure integrated with sensors and communication technologies), digital twins (virtual replicas of traffic participants and infrastructure), and advanced driver assistance systems (ADAS) to ensure their reliability within intelligen...

Z. Páncsics, Máté Fugerth, Bálint Patkó et al. · 0 citations
Preprint Nov 2026

Refining Roadside 4D Radar Vehicle Classification Using Point-Cloud Dispersion

A Neyman-Pearson-based binary classifier is proposed on the temporally-smoothed 2D positional standard deviation of radar point cloud clusters, reducing classification error from 52.1% to 42.7% and lays the foundation for future camera-radar fusion.

Mohammed Alsakabi, Andreia Figueiredo, António Almeida et al. · 0 citations
Review Open access 2026

How Emergent Architectures Solve the Bird’s Eyes View Shortcomings: A Systematic Review

Autonomous driving requires robust, accurate and real-time environmental perception. Although cameras, LiDAR, and radar provide complementary sensing capabilities, individual modalities remain vulnerable to limitations such as depth ambiguity, point-cloud sparsity, adverse weather, and restricted angular resolution. Mu...

A. Sahbani, Rihem Sebai, T. Bejaoui et al. · 0 citations
Review Open access Nov 2026

LiDAR–Monocular Camera Fusion for Non-Cooperative Target Perception: A Review

Relative pose measurement and 3D structural perception of space non-cooperative targets provide core technical support for on-orbit servicing, space debris removal, and defunct satellite capture. A single sensor can hardly achieve high-precision ranging and high-resolution texture perception simultaneously. Fusion of L...

Rui Zhou, Wan-Yun Li, Can Xu · 0 citations
Open access Oct 2026

From RGB to reliable road maps: pseudo-LiDAR enhanced domain adaptive detection

SPADA-Road is proposed, an unsupervised framework that integrates Superpixel-guided segmentation with a novel Pseudo-LiDAR (PL) generation module that synthesizes depth cues from monocular RGB inputs, effectively augmenting training data without requiring physical LiDAR sensors.

Yun-Gang Tian, Zheng-Qiang Li, Bai-Han Yang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.