mlsanityData to 7 Oct 2026

A Vision-based System for Traffic Anomaly Detection using Deep Learning and Decision Trees

arXiv 2104.06856 ↗First posted 14 Apr 2021cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

Any intelligent traffic monitoring system must be able to detect anomalies such as traffic accidents in real time. In this paper, we propose a Decision-Tree - enabled approach powered by Deep Learning for extracting anomalies from traffic cameras while accurately estimating the start and end time of the anomalous event. Our approach included creating a detection model, followed by anomaly detection and analysis. YOLOv5 served as the foundation for our detection model. The anomaly detection and analysis step entail traffic scene background estimation, road mask extraction, and adaptive thresholding. Candidate anomalies were passed through a decision tree to detect and analyze final anomalies. The proposed approach yielded an F1 score of 0.8571, and an S4 score of 0.5686, per the experimental validation.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 2 of its 32 references that are in the map. First posted on arXiv 14 Apr 2021.

Builds on

2 of 32 references.

References · 2

  1. 2019Anomaly Detection in Road Traffic Using Visual Surveillance: A Surveycited by 30
  2. 2020Artificial Intelligence Enabled Traffic Monitoring Systemcited by 6

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 5; 2023: 9; 2024: 3; 2025: 4.

26 papers.

Sort:

By area:

  1. 2021The 5th AI City Challengecited by 28
  2. 2022TAD: A Large-Scale Benchmark for Traffic Accidents Detection from Video Surveillancecited by 20
  3. 2021Deep Video Anomaly Detection: Opportunities and Challengescited by 14
  4. 2023Label-Free Multivariate Time Series Anomaly Detectioncited by 14
  5. 2023Real-time Multi-Class Helmet Violation Detection Using Few-Shot Data Sampling Technique and YOLOv8cited by 13
  6. 2025MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detectioncited by 10
  7. 2022A Region-Based Deep Learning Approach to Automated Retail Checkoutcited by 9
  8. 2024Enhancing Traffic Safety with Parallel Dense Video Captioning for End-to-End Event Analysiscited by 9
  9. 2022Deep Learning based Computer Vision Methods for Complex Traffic Environments Perception: A Reviewcited by 7
  10. 2021An Uncertainty-aware Loss Function for Training Neural Networks with Calibrated Predictionscited by 6
  11. 2023DeepSegmenter: Temporal Action Localization for Detecting Anomalies in Untrimmed Naturalistic Driving Videoscited by 6
  12. 2023Robust Roadside Perception: an Automated Data Synthesis Pipeline Minimizing Human Annotationcited by 6
14 more
  1. 2025A Survey on Video Anomaly Detection via Deep Learning: Human, Vehicle, and Environmentcited by 4
  2. 2023AI-Based Framework for Understanding Car Following Behaviors of Drivers in A Naturalistic Driving Environmentcited by 3
  3. 2024Low-Light Image Enhancement Framework for Improved Object Detection in Fisheye Lens Datasetscited by 3
  4. 2025CoT-VLM4Tar: Chain-of-Thought Guided Vision-Language Models for Traffic Anomaly Resolutioncited by 3
  5. 2021Machine Learning-Based Classification Algorithms for the Prediction of Coronary Heart Diseasescited by 2
  6. 2021Classification of Anuran Frog Species Using Machine Learningcited by 1
  7. 2022Travel Time, Distance and Costs Optimization for Paratransit Operations using Graph Convolutional Neural Networkcited by 1
  8. 2023Real-Time Helmet Violation Detection Using YOLOv5 and Ensemble Learningcited by 1
  9. 2023MSight: An Edge-Cloud Infrastructure-based Perception System for Connected Automated Vehiclescited by 1
  10. 2024uTRAND: Unsupervised Anomaly Detection in Traffic Trajectoriescited by 1
  11. 2025Cerberus: Real-Time Video Anomaly Detection via Cascaded Vision-Language Modelscited by 1
  12. 2022Rethinking the Detection Head Configuration for Traffic Object Detectioncited by 0
  13. 2023SigSegment: A Signal-Based Segmentation Algorithm for Identifying Anomalous Driving Behaviours in Naturalistic Driving Videoscited by 0
  14. 2023STRIDE: Street View-based Environmental Feature Detection and Pedestrian Collision Predictioncited by 0