Prediction of Occluded Pedestrians in Road Scenes using Human-like Reasoning: Insights from the OccluRoads Dataset
This addresses safety risks in autonomous driving by improving detection of occluded pedestrians, though it is incremental as it builds on existing detection methods with a new dataset and hybrid approach.
The paper tackles the problem of detecting occluded pedestrians in autonomous driving by introducing the OccluRoads dataset and a pipeline using knowledge graphs and Bayesian inference, achieving an F1 score of 0.91, which is up to 42% better than traditional models.
Pedestrian detection is a critical task in autonomous driving, aimed at enhancing safety and reducing risks on the road. Over recent years, significant advancements have been made in improving detection performance. However, these achievements still fall short of human perception, particularly in cases involving occluded pedestrians, especially entirely invisible ones. In this work, we present the Occlusion-Rich Road Scenes with Pedestrians (OccluRoads) dataset, which features a diverse collection of road scenes with partially and fully occluded pedestrians in both real and virtual environments. All scenes are meticulously labeled and enriched with contextual information that encapsulates human perception in such scenarios. Using this dataset, we developed a pipeline to predict the presence of occluded pedestrians, leveraging Knowledge Graph (KG), Knowledge Graph Embedding (KGE), and a Bayesian inference process. Our approach achieves a F1 score of 0.91, representing an improvement of up to 42% compared to traditional machine learning models.