When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos

Yu Yao, Xizi Wang, Mingze Xu, Zelin Pu, Ella Atkins +1 more
4/6/2020
cs.CV

Official code: MoonBlvd/Detection-of-Traffic-Anomaly (281 stars, MIT, last commit 2023-12-28).

Abstract

Video anomaly detection (VAD) has been extensively studied. However, research on egocentric traffic videos with dynamic scenes lacks large-scale benchmark datasets as well as effective evaluation metrics. This paper proposes traffic anomaly detection with a \textit{when-where-what} pipeline to detect, localize, and recognize anomalous events from egocentric videos. We introduce a new dataset called Detection of Traffic Anomaly (DoTA) containing 4,677 videos with temporal, spatial, and categorical annotations. A new spatial-temporal area under curve (STAUC) evaluation metric is proposed and used with DoTA. State-of-the-art methods are benchmarked for two VAD-related tasks.Experimental results show STAUC is an effective VAD metric. To our knowledge, DoTA is the largest traffic anomaly dataset to-date and is the first supporting traffic anomaly studies across when-where-what perspectives. Our code and dataset can be found in: https://github.com/MoonBlvd/Detection-of-Traffic-Anomaly

View on arXivView PDF

Code Implementations(1)

MoonBlvd/Detection-of-Traffic-AnomalyOfficial100%
MIT

This is the repo for our Detection of Traffic Anomaly (DoTA) dataset.

28139PythonApr 6, 20202 years agoMIT

Similar Papers

Uncovering what, why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly

87% match2 repos872024

Text-Driven Traffic Anomaly Detection with Temporal High-Frequency Modeling in Driving Videos

86% match1 repo72024

Latency-aware Road Anomaly Segmentation in Videos: A Photorealistic Dataset and New Metrics

86% match2024

MTFL: Multi-Timescale Feature Learning for Weakly-Supervised Anomaly Detection in Surveillance Videos

85% match1 repo112024

SigSegment: A Signal-Based Segmentation Algorithm for Identifying Anomalous Driving Behaviours in Naturalistic Driving Videos

85% match2023

Hybrid Video Anomaly Detection for Anomalous Scenarios in Autonomous Driving

85% match2024

Cite this paper

@article{yao2020when,
  title  = {When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos},
  author = {Yu Yao and Xizi Wang and Mingze Xu and Zelin Pu and Ella Atkins and David Crandall},
  year   = {2020},
  eprint = {2004.03044},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2004.03044}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2004.03044.svg)](https://codeofpaper.com/paper/2004.03044)

Discussion