A Modular Zero-Shot Pipeline for Accident Detection, Localization, and Classification in Traffic Surveillance Video
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917400003215360 |
|---|---|
| author | Thakur, Amey Talele, Sarvesh |
| author_facet | Thakur, Amey Talele, Sarvesh |
| contents | We describe a zero-shot pipeline developed for the ACCIDENT @ CVPR 2026 challenge. The challenge requires predicting when, where, and what type of traffic accident occurs in surveillance video, without labeled real-world training data. Our method separates the problem into three independent modules. The first module localizes the collision in time by running peak detection on z-score normalized frame-difference signals. The second module finds the impact location by computing the weighted centroid of cumulative dense optical flow magnitude maps using the Farneback algorithm. The third module classifies collision type by measuring cosine similarity between CLIP image embeddings of frames near the detected peak and text embeddings built from multi-prompt natural language descriptions of each collision category. No domain-specific fine-tuning is involved; the pipeline processes each video using only pre-trained model weights. Our implementation is publicly available as a Kaggle notebook. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09685 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Modular Zero-Shot Pipeline for Accident Detection, Localization, and Classification in Traffic Surveillance Video Thakur, Amey Talele, Sarvesh Computer Vision and Pattern Recognition Machine Learning We describe a zero-shot pipeline developed for the ACCIDENT @ CVPR 2026 challenge. The challenge requires predicting when, where, and what type of traffic accident occurs in surveillance video, without labeled real-world training data. Our method separates the problem into three independent modules. The first module localizes the collision in time by running peak detection on z-score normalized frame-difference signals. The second module finds the impact location by computing the weighted centroid of cumulative dense optical flow magnitude maps using the Farneback algorithm. The third module classifies collision type by measuring cosine similarity between CLIP image embeddings of frames near the detected peak and text embeddings built from multi-prompt natural language descriptions of each collision category. No domain-specific fine-tuning is involved; the pipeline processes each video using only pre-trained model weights. Our implementation is publicly available as a Kaggle notebook. |
| title | A Modular Zero-Shot Pipeline for Accident Detection, Localization, and Classification in Traffic Surveillance Video |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2604.09685 |