Annotated Bibliography

Voice-over: ../assets/audio/bibliography.mp3

References are listed in ACM citation style, in order of first appearance. Each includes a synopsis and reliability rating.

1. K. Romić, I. Galić, H. Leventić, and M. Habijan. 2021. Pedestrian Crosswalk Detection Using a Column and Row Structure Analysis in Assistance Systems for the Visually Impaired. Acta Polytechnica Hungarica 18, 7. DOI: PDF
   Synopsis: Rule-based detection using row/column intensity and periodicity; evaluates in assistive settings.
   Reliability: Peer-reviewed journal (High).
2. M. Haider et al. 2025. Advanced Zebra Crosswalk Detection Using Deep Learning Techniques. International Journal of Engineering and Science Education 13, 3. DOI: PDF
   Synopsis: Deep learning pipeline (detection + segmentation) tested under occlusion and varied lighting.
   Reliability: Academic venue (Medium; confirm peer-review).
3. H. Hwang, S. Kwon, Y. Kim, and D. Kim. 2024. Is it safe to cross? Interpretable Risk Assessment with GPT-4V for Safety-Aware Street Crossing. arXiv preprint arXiv:2402.06794. DOI: arXiv
   Synopsis: Applies GPT-4V for assessing crossing safety and generating explanations.
   Reliability: Preprint (Medium).
4. M. Liu, J. Jiang, C. Zhu, and X.-C. Yin. 2023. VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023). DOI: PDF
   Synopsis: Vision-language supervision improves pedestrian detection under occlusion and crowding.
   Reliability: Top-tier conference (High).
5. C. Zhang et al. 2023/2024. Vision-Language Models in Autonomous Driving: A Survey and Outlook. arXiv preprint arXiv:2310.14414. DOI: arXiv
   Synopsis: Comprehensive survey of VLMs in autonomous driving, covering perception, planning, and open challenges.
   Reliability: Survey preprint (Medium).
6. J. Fan, J. Wu, J. Gao, J. Yu, Y. Wang, H. Chu, and B. Gao. 2024. MLLM-SUL: Multimodal LLM for Scene Understanding and Risk Localization in Traffic. arXiv preprint arXiv:2412.19406. DOI: arXiv
   Synopsis: Demonstrates a multimodal LLM that narrates traffic scenes and highlights risk zones.
   Reliability: Preprint (Medium).
7. Z.-D. Zhang, M.-L. Tan, Z.-C. Lan, H.-C. Liu, L. Pei, and W.-X. Yu. 2022. CDNet: A Real-Time and Robust Crosswalk Detection Network on Jetson Nano Based on YOLOv5. Neural Computing and Applications. DOI: 10.1007/s00521-022-07007-9
   Synopsis: YOLOv5-based crosswalk detector optimized for Jetson; reports strong FPS and accuracy.
   Reliability: Peer-reviewed journal (High).