Can Foundation Models Reliably Identify Spatial Hazards? A Case Study on Curb Segmentation
This work addresses a critical safety issue for persons with blindness and low vision by identifying limitations in foundation models for curb segmentation, though it is incremental as it proposes solutions like filtered bounding boxes rather than a breakthrough.
The study evaluated foundation models for curb segmentation, finding they struggle with high false-positive rates up to 95% and slow inference times averaging 3.70 seconds, which hinders real-time assistive navigation for persons with blindness and low vision.
Curbs serve as vital borders that delineate safe pedestrian zones from potential vehicular traffic hazards. Curbs also represent a primary spatial hazard during dynamic navigation with significant stumbling potential. Such vulnerabilities are particularly exacerbated for persons with blindness and low vision (PBLV). Accurate visual-based discrimination of curbs is paramount for assistive technologies that aid PBLV with safe navigation in urban environments. Herein, we investigate the efficacy of curb segmentation for foundation models. We introduce the largest curb segmentation dataset to-date to benchmark leading foundation models. Our results show that state-of-the-art foundation models face significant challenges in curb segmentation. This is due to their high false-positive rates (up to 95%) with poor performance distinguishing curbs from curb-like objects or non-curb areas, such as sidewalks. In addition, the best-performing model averaged a 3.70-second inference time, underscoring problems in providing real-time assistance. In response, we propose solutions including filtered bounding box selections to achieve more accurate curb segmentation. Overall, despite the immediate flexibility of foundation models, their application for practical assistive technology applications still requires refinement. This research highlights the critical need for specialized datasets and tailored model training to address navigation challenges for PBLV and underscores implicit weaknesses in foundation models.