# Label Correction for Road Segmentation Using Road-side Cameras

arXiv: https://arxiv.org/abs/2502.01281 · HTML: https://mlsanity.com/paper/2502.01281/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 3 Feb 2025.

## Builds on (most cited first, 15 of 15)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2312.04265/) (2023)
- [Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task](https://mlsanity.com/paper/2203.13608/) (2022)
- [Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions](https://mlsanity.com/paper/2208.01166/) (2022)
- [V-STRONG: Visual Self-Supervised Traversability Learning for Off-road Navigation](https://mlsanity.com/paper/2312.16016/) (2023)
- [Learning Off-Road Terrain Traversability with Self-Supervisions Only](https://mlsanity.com/paper/2305.18896/) (2023)
- [Self-Supervised Traversability Prediction by Learning to Reconstruct Safe Terrain](https://mlsanity.com/paper/2208.01329/) (2022)
- [Real-time Full-stack Traffic Scene Perception for Autonomous Driving with Roadside Cameras](https://mlsanity.com/paper/2206.09770/) (2022)
- [TUMTraf Event: Calibration and Fusion Resulting in a Dataset for Roadside Event-Based and RGB Cameras](https://mlsanity.com/paper/2401.08474/) (2024)
- [IDD-AW: A Benchmark for Safe and Robust Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather](https://mlsanity.com/paper/2311.14459/) (2023)
- [Integration of Roadside Camera Images and Weather Data for Monitoring Winter Road Surface Conditions](https://mlsanity.com/paper/2009.12165/) (2020)
- [Evaluating Roadside Perception for Autonomous Vehicles: Insights from Field Testing](https://mlsanity.com/paper/2401.12392/) (2024)
- [Road Surface Friction Estimation for Winter Conditions Utilising General Visual Features](https://mlsanity.com/paper/2404.16578/) (2024)
- [Trajectory-based Road Autolabeling with Lidar-Camera Fusion in Winter Conditions](https://mlsanity.com/paper/2412.02370/) (2024)

## Abstract (arXiv)

Reliable road segmentation in all weather conditions is critical for intelligent transportation applications, autonomous vehicles and advanced driver's assistance systems. For robust performance, all weather conditions should be included in the training data of deep learning-based perception models. However, collecting and annotating such a dataset requires extensive resources. In this paper, existing roadside camera infrastructure is utilized for collecting road data in varying weather conditions automatically. Additionally, a novel semi-automatic annotation method for roadside cameras is proposed. For each camera, only one frame is labeled manually and then the label is transferred to other frames of that camera feed. The small camera movements between frames are compensated using frequency domain image registration. The proposed method is validated with roadside camera data collected from 927 cameras across Finland over 4 month time period during winter. Training on the semi-automatically labeled data boosted the segmentation performance of several deep learning segmentation models. Testing was carried out on two different datasets to evaluate the robustness of the resulting models. These datasets were an in-domain roadside camera dataset and out-of-domain dataset captured with a vehicle on-board camera.