Label Correction for Road Segmentation Using Road-side Cameras
This work addresses the resource-intensive challenge of dataset creation for road segmentation in all weather conditions, which is critical for autonomous vehicles and intelligent transportation systems, but it is incremental as it builds on existing annotation and image registration techniques.
The paper tackled the problem of collecting and annotating road segmentation data in varying weather conditions by proposing a semi-automatic annotation method using roadside cameras, where only one frame per camera is manually labeled and labels are transferred to other frames via frequency domain image registration; this approach boosted segmentation performance for deep learning models, validated on data from 927 cameras over 4 months in Finland.
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.