Click-Calib: A Robust Extrinsic Calibration Method for Surround-View Systems

2025-01-02

AI Summary

Current offline extrinsic calibration of surround-view systems (SVS) relies heavily on physical calibration targets, suffers from operational complexity, and exhibits degraded accuracy at long distances. To address these limitations, this paper proposes a target-free, ground-feature-based offline calibration method that requires only manual clicks on natural-scene ground keypoints. We introduce the first modality-agnostic, click-driven calibration paradigm, integrating multi-view geometric modeling, ground-plane constraints, and nonlinear optimization minimizing reprojection error—supporting both single-frame and multi-frame inputs for joint near-to-far pose estimation. Experiments on our custom dataset and the public WoodScape benchmark demonstrate a 32% improvement in calibration accuracy over baseline methods, alongside strong robustness. The approach eliminates the need for specialized hardware or controlled scene setup, enabling practical, deployment-friendly SVS calibration.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation

Application Category

• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Surround-View System (SVS) is an essential component in Advanced Driver Assistance System (ADAS) and requires precise calibrations. However, conventional offline extrinsic calibration methods are cumbersome and time-consuming as they rely heavily on physical patterns. Additionally, these methods primarily focus on short-range areas surrounding the vehicle, resulting in lower calibration quality in more distant zones. To address these limitations, we propose Click-Calib, a pattern-free approach for offline SVS extrinsic calibration. Without requiring any special setup, the user only needs to click a few keypoints on the ground in natural scenes. Unlike other offline calibration approaches, Click-Calib optimizes camera poses over a wide range by minimizing reprojection distance errors of keypoints, thereby achieving accurate calibrations at both short and long distances. Furthermore, Click-Calib supports both single-frame and multiple-frame modes, with the latter offering even better results. Evaluations on our in-house dataset and the public WoodScape dataset demonstrate its superior accuracy and robustness compared to baseline methods. Code is avalaible at https://github.com/lwangvaleo/click_calib.

Problem

• Surround View System
• Offline Calibration
• Distance Region Calibration

Innovation

• Click-Calib
• Surround View System Calibration
• No-Pattern Offline Calibration