Hybrid Geometric Optimization for Training-Free Metric Depth Recovery in Uncalibrated Roadside Monocular Cameras
Open Access
- 26 May 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 80298-80313
Abstract
Accurate metric depth recovery and camera calibration are essential for 3D perception in traffic monitoring systems, yet most roadside surveillance cameras operate without calibration targets or depth sensors. Recovering consistent metric geometry from monocular imagery in such settings is inherently ill-conditioned due to scale ambiguity and limited geometric observability. This paper introduces a practical hybrid constraint optimization framework for training-free camera calibration and metric depth alignment from static roadside monocular images. The method jointly refines camera intrinsics and affine depth scaling parameters, leveraging road planarity and geometric consistency constraints by combining learned monocular depth, semantic road segmentation, vanishing-point geometry, and vehicle keypoint priors within a robust nonlinear least-squares formulation with a problem-aware multi-start strategy. The approach requires no retraining, calibration targets, or LiDAR supervision. Experiments on the DAIR-V2X-Seq infrastructure-camera benchmark demonstrate consistent quantitative improvements. In a dedicated cross-sequence calibration transfer experiment, the proposed framework improves metric accuracy in over 70% of sequences, with an average RMSE reduction of 3.1m and a δ1 increase of 0.30. Across 28 sequences, per-frame intrinsic estimation exhibits a median focal-length coefficient of variation of 11.3%, highlighting the instability that sequence-level optimization is designed to address. Overall, the study shows that explicitly coupling learned depth with geometric and semantic constraints can improve metric 3D perception in existing uncalibrated roadside camera networks.Keywords
This publication has 29 references indexed in Scilit:
- FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent2025
- Self-supervised monocular depth estimation via multiple bilateral consistencyMultimedia Systems, 2025
- Self-supervised monocular depth estimation on water scenes via specular reflection priorDigital Signal Processing, 2024
- Traffic surveillance camera calibration by 3D model bounding box alignment for accurate vehicle speed measurementComputer Vision and Image Understanding, 2017
- Unsupervised Monocular Depth Estimation with Left-Right Consistency2017
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- VirtualWorlds as Proxy for Multi-object Tracking Analysis2016
- Multiple View Geometry in Computer Vision2004
- A flexible new technique for camera calibrationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- Bundle Adjustment — A Modern Synthesis2000