An Open-Source Two-Stage Computer Vision Pipeline for Fine-Grained Vehicle Classification using Vision Transformers
Researchers have developed an open-source, two-stage computer vision pipeline for fine-grained vehicle classification. This system uses a pre-trained detector for initial localization and a fine-tuned Vision Transformer for classifying vehicles into six injury-risk-relevant categories. The pipeline demonstrated high accuracy on in-distribution data and maintained strong performance on out-of-distribution datasets, incorporating a confidence-based abstention mechanism to handle uncertainty. AI
IMPACT Provides a reusable open-source tool for analyzing traffic video data, potentially improving road safety research and applications.