Wu, Yin (Karlsruhe Institute of Technology), Slieter, Daniel (CARIAD SE), Abouelazm, Ahmed (FZI Research Center for Information Technology), Hubschneider, Christian (FZI Research Center for Information Technology), Zöllner, J. Marius (FZI Research Center for Information Technology; KIT Karlsruhe In)

LanePerf: A Performance Estimation Framework for Lane Detection

Scheduled for presentation during the Regular Session "S42a-Safety and Risk Assessment for Autonomous Driving Systems" (FR-LM-T42), Friday, November 21, 2025, 11:50−12:10, Broadbeach 3

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Abstract

Lane detection is a critical component of Advanced Driver-Assistance Systems (ADAS) and Automated Driving Systems (ADS), providing essential spatial information for lateral control. However, domain shifts often undermine model reliability when deployed in new environments. Ensuring the robustness and safety of lane detection models typically requires collecting and annotating target domain data, which is resource-intensive. Estimating model performance without ground-truth labels offers a promising alternative for efficient robustness assessment, yet remains underexplored in lane detection. While previous work has addressed performance estimation in image classification, these methods are not directly applicable to lane detection tasks. This paper first adapts five well-performing performance estimation methods from image classification to lane detection, building a baseline. Addressing the limitations of prior approaches that solely rely on softmax scores or lane features, we further propose a new Lane Performance Estimation Framework (LanePerf), which integrates image and lane features using a pretrained image encoder and a DeepSets-based architecture, effectively handling zero-lane detection scenarios and large domain-shift cases. Extensive experiments on the OpenLane dataset, covering diverse domain shifts (scenes, weather, hours), demonstrate that our LanePerf outperforms all baselines, achieving a lower Mean Absolute Error (MAE) of 0.117 and a higher Spearman’s rank correlation coefficient ρ of 0.727. These findings pave the way for robust, label-free performance estimation in ADAS, supporting more efficient testing and improved safety in challenging driving scenarios.