AI Vision for Road Traffic Accidents: Scoping Review with ☸️SAIMSARA.

Name: SAIMSARA Evidence Object digital::AI_VISION_ROAD_ACCIDENTS_SS
Creator: SAIMSARA
License: https://saimsara.com/license/

SAIMSARA

doi:10.62487/saimsara5188b0b5

AI Vision for Road Traffic Accidents: Scoping Review with ☸️SAIMSARA.

Issue 3, Volume 1, 2026

Editorial note

• Last update: 2026-05-09 19:18:07

What is this paper about

AI vision is no longer only an accident-detection tool — it is becoming a full road-safety infrastructure for crash detection, driver-state monitoring, hazard surveillance, traffic enforcement, and emergency response. The full SAIMSARA evidence map gives humans and AI agents a structured, reference-linked view of 479 original studies, showing where performance is already strong and where real-world robustness, rare scenarios, and field validation remain the critical deployment gaps.

Human-verified editorial review Verified by World ID proof-of-human. This editorial layer was submitted from a SAIMSARA account verified as a unique human.

Evidence preview · Did you know?

Realistic road-safety AI scene showing emergency response after a detected traffic accident.

Crash detection can trigger response

Did you know? One system reported 98.56% accident detection, 98.25% severity classification, and emergency notification in under 5 seconds.

This turns AI vision from passive surveillance into a possible emergency-response layer.

Dashcam-style AI vision scene showing vehicles, trajectories, and an imminent collision risk.

Some models look before impact

Did you know? A dashcam-based system anticipated accidents about 1.7 seconds before occurrence, with 80% recall and 71% precision.

The field is moving beyond detecting crashes after they happen toward predicting dangerous interactions before impact.

Realistic autonomous-driving safety scene with difficult weather, rare road hazards, and AI uncertainty.

Rare scenarios can break confidence

Did you know? In the CODA corner-case dataset, standard object detectors achieved no more than 12.8% mAR.

This is the critical deployment gap: high benchmark accuracy does not guarantee robustness in rare, adverse, or complex road scenes.

Swipe sideways on mobile · full evidence map opens after unlock

Abstract:

Keywords:

Review Stats

Final search date and database lock: 2026-05-09 19:48:39 CEST

Plan: Pro (expanded craft tokens; source: Semantic Scholar)

Source: Semantic Scholar

Total Abstracts/Papers: 2683

Downloaded Abstracts/Papers: 1000

Included original and non-original Abstracts/Papers (all): 524

Included original Abstracts/Papers (Vote counting by direction of effect): 479

Reference Index (links used in paper): 109

Total reported sample units (participants/dataset items; topic deduplicated ΣN): 171126

Get access to the full paper

Unlock the full evidence map

The full evidence review, including the Introduction, Methods, Results, Discussion, Conclusion, figures, and complete reference index, opens after purchase or sign-in. The Evidence Object JSON is a separate machine-readable evidence product: a concentrated synthesis of results, topic-level evidence, and discussion across original and non-original studies. It can be directly input into your LLM, agent, or RAG workflow.

Reference Index (109)

[2] Drowsy Driver Detection System using Computer Vision and Transfer Learning for Preventing Road Accidents — https://doi.org/10.1109/icbds61829.2024.10837100
[5] Recognition and Traffic Warning of Severe Weather using Machine Vision — https://doi.org/10.1109/itoec63606.2025.10967830
[7] IoT-Based Driver Safety System with Real-Time Drowsiness and Alcohol Monitoring via Vision and Multi-Sensor Integration — https://doi.org/10.1109/qpain66474.2025.11171722
[9] Identification of dangerous situations in the road infrastructure using unmanned aerial vehicles — https://doi.org/10.15587/2706-5448.2025.347074
[10] CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving — https://doi.org/10.48550/arxiv.2203.07724
[13] Enhanced Cyclist Safety Through Vision-Language Models: A Real-Time Advisory Framework — https://doi.org/10.1109/ic_aset65966.2025.11231823
[15] Green-EMulTO: A Next Generation Edge-Assisted Multi-Level Traffic Orchestrator for Green Computing in Consumer Autonomous Vehicles — https://doi.org/10.1109/tce.2024.3442437
[16] AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception — https://doi.org/10.1109/iccv51070.2023.01871
[17] An Autonomous Intelligent Liability Determination Method for Minor Accidents Based on Collision Detection and Large Language Models — https://doi.org/10.3390/app14177716
[21] Image Processing and Deep Learning Based Road Object Detection System for Safe Transportation — https://doi.org/10.1109/icccnt61001.2024.10726014
[28] Graph(Graph): A Nested Graph-Based Framework for Early Accident Anticipation — https://doi.org/10.1109/wacv57701.2024.00736
[32] Improving Vehicle Assistance Systems: Evaluation of Augmented Capabilities through Infrared Thermal Camera Integration — https://doi.org/10.15282/ijame.22.1.2025.20.0937
[42] Image processing-based automatic detection of asphalt pavement rutting using a novel metaheuristic optimized machine learning approach — https://doi.org/10.1007/s00500-021-06086-5
[47] Lane Detection for Autonomous Vehicle Management: PHT Approach — https://doi.org/10.1109/iccit54785.2021.9689883
[50] Intelligent Traffic Violation Detection and Explanation System Using Computer Vision and Large Language Models — https://doi.org/10.1109/icdiss68238.2025.11320729
[51] AI-Based Intelligent Surveillance System for Real-Time Traffic Violation Detection Using Deep Learning and Computer Vision — https://doi.org/10.1109/decon67170.2025.11447993
[56] Vision-Based Traffic Accident Detection and Anticipation: A Survey — https://doi.org/10.1109/tcsvt.2023.3307655
[57] Advanced Traffic Incident Detection and Classification with Real-Time Computer Vision — https://doi.org/10.32628/ijsrst2411330
[59] AI-Powered Road Surface Monitoring for Sustainable Urban Infrastructure — https://doi.org/10.65694/icgst2025-cp01-002
[61] Towards Predicting Traffic Accident Consequence Using Transformer Learning and Clear AI Technologies — https://doi.org/10.1109/icaccm61117.2024.11059092
[70] PawSense: Smart AI System for Animal Safety on Roads — https://doi.org/10.38124/ijisrt/25nov058
[74] Identification of Drunk Driving using Deep Learning Networks on Virtual Reality Simulation — https://doi.org/10.1109/itsc60802.2025.11423806
[76] Towards Safer Roads: A Machine Learning Framework for Driver Fatigue Detection — https://doi.org/10.28991/hij-2026-07-01-018
[78] PanopticVis: Integrated Panoptic Segmentation for Visibility Estimation at Twilight and Night — https://doi.org/10.1109/cvprw59228.2023.00341
[79] AI Enabled Blind Spot Detection using Rcnn Based Image Processing — https://doi.org/10.35940/ijrte.b1006.0782s519
[83] When language and vision meet road safety: leveraging multimodal large language models for video-based traffic accident analysis — https://doi.org/10.1016/j.aap.2025.108077
[85] Early Vehicle Collision Detection in Road Traffic Using Deep Learning and Explainable AI — https://doi.org/10.1109/icoiics67115.2025.11390525
[86] An Automated Approach for Predicting Road Traffic Accident Severity Using Transformer Learning and Explainable AI Technique — https://doi.org/10.1109/access.2024.3380895
[87] AI Based Pothole Detection for Road Safety Enhancement Using Computer Vision and Deep Learning — https://doi.org/10.55011/staiqc.2025.5209
[90] AI-driven Vision-based Pothole Detection for Improved Road Safety — https://doi.org/10.47836/pjst.33.3.20
[92] AI-Based Pedestrian Crossing System: A Simulation Study for Enhanced Urban Road Safety and Traffic Efficiency — https://doi.org/10.1109/icecst66106.2025.11307254
[96] Models of the classifier of prerequisites for the occurrence of road accidents to predict dangerous situations at intersections — https://doi.org/10.30837/2522-9818.2025.2.177
[106] Reducing Traffic Accident Impact: A Vision Transformer-Based Driver Distraction Detection Approach — https://doi.org/10.1109/ic2sda68097.2025.11331446
[107] Integrating Vision- Based Statistical Measures for Traffic Sign Recognition and Accident Mitigation Using YOLOv5 — https://doi.org/10.1109/iccct63501.2025.11020247
[112] Real-Time Road Accident Scene Recognition Using Computer Vision Applied to Drone Imagery — https://doi.org/10.1109/icares64249.2024.10768100
[116] Hybrid Visual-Sensor Fusion for AI-Guided Urban Traffic Flow Adjustment — https://doi.org/10.1109/icedge67252.2025.11412953
[120] Road Accident Detection Using AI and ML. — https://doi.org/10.55041/ijsrem48619
[121] A Survey on Smart Traffic Monitoring System using AI — https://doi.org/10.15680/ijircce.2025.1301129
[125] Intelligent Traffic Management System Using AI and DL Opencv to Optimize Traffic Flow and Reduce Congestion in Cities — https://doi.org/10.1109/icstsn67075.2025.11397998
[130] Road Vision: An Integrated Web-Based System for Road Accident Risk Prediction Using Multi-Algorithm Ensemble Machine Learning — https://doi.org/10.55041/isjem05355
[131] A Real-Time Computer Vision Based Approach to Detection and Classification of Traffic Incidents — https://doi.org/10.3390/bdcc7010022
[133] Traffic Signal Based on Real Time Helmet Detection Using AI — https://doi.org/10.1109/iciptm59628.2024.10563387
[139] A Cross-Modal Edge Intelligence Framework for Driver Drowsiness Assessment using Transformer-based Vision and In-Cabin Sensing — https://doi.org/10.1109/icoeca68095.2026.11485506
[159] Application And Analysis of Computer Vision Technology in Traffic Safety — https://doi.org/10.54097/65rx7v60
[160] Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques — https://doi.org/10.3390/computers10110148
[164] VRU-Accident: A Vision-Language Benchmark for Video Question Answering and Dense Captioning for Accident Scene Understanding — https://doi.org/10.1109/iccvw69036.2025.00085
[166] AI-Powered Traffic Violation Detection System Using CCTV, and Deep Learning — https://doi.org/10.55041/ijsrem58855
[167] AI-Enabled Road Damage Detection for Accident Prevention — https://doi.org/10.1109/icears67481.2026.11416523
[168] Simulated Adversarial Attacks on Traffic Sign Recognition of Autonomous Vehicles — https://doi.org/10.3390/engproc2025092015
[182] Road Safety Mechanism to Prevent Overtaking Accidents — https://doi.org/10.22214/ijraset.2020.30433
[184] Traffic Sign Detection and Recognition — https://doi.org/10.22214/ijraset.2025.69316
[185] Real-time rapid accident detection for optimizing road safety in Bangladesh — https://doi.org/10.1016/j.heliyon.2025.e42432
[194] Smart Traffic Management System — https://doi.org/10.55041/isjem05091
[200] Computer Vision Based Vulnerable Road Users Hand Signal Recognition — https://doi.org/10.1109/icirca51532.2021.9545005
[201] Vision-Based Accident Anticipation and Detection Using Deep Learning — https://doi.org/10.1109/mim.2024.10505198
[202] A Machine Learning Based Forensic System for Road Accident Detection and Reporting — https://doi.org/10.22214/ijraset.2026.78258
[208] Artificial Intelligence for Road Anomaly Detection: A Review — https://doi.org/10.1002/widm.70054
[209] Artificial Intelligence in Smart Traffic Management: A Systematic Review — https://doi.org/10.55041/ijsrem58450
[218] Automated Vehicle Collision Detection: Multi-Model Computer Vision Framework — https://doi.org/10.1109/iitcee67948.2026.11394603
[219] Vision-Based Driver Drowsiness Detection: From Deep Learning Models to Real-Time Mobile Deployment — https://doi.org/10.22214/ijraset.2026.81356
[221] A YOLO-Based Framework for Road Sign Detection and Recognition in the Context of Bangladesh — https://doi.org/10.1109/compas60761.2024.10796393
[228] A Computer Vision-based algorithm for accident detection, severity classification and rapid emergency response using YOLOv8 and Twilio Programmable Messaging API — https://doi.org/10.1109/otcon60325.2024.10687490
[230] Multi-perspective Traffic Video Description Model with Fine-grained Refinement Approach — https://doi.org/10.1109/cvprw63382.2024.00701
[236] Deep Learning Models for Mining Knowledge from Vehicle Trajectories for Traffic Accident Prediction: A Comprehensive Review — https://doi.org/10.1109/icaiccit68829.2025.11433964
[239] AI-Based Accident and Crime Detection System: A Smart Surveillance Approach — https://doi.org/10.1109/conecct65861.2025.11306525
[245] Detecting and Tracking of Road Boundary Lines Using Machine Learning Approach — https://doi.org/10.17485/ijst/v18i6.3685
[249] Vehicle Driver State Estimation Using AI and Algorithm — https://doi.org/10.1109/iccsp64183.2025.11089438
[254] Blind Spot Monitoring and Detection System using Computer Vision — https://doi.org/10.1109/ickecs65700.2025.11035679
[257] Enhancing Road Safety and Accountability Through Automated Rider and Helmet Detection: A Deep Learning Approach — https://doi.org/10.1109/iccit64611.2024.11022569
[261] Evaluating Smart Traffic Light Systems for Urban Accident Reduction: A Case Study from Manado, Indonesia — https://doi.org/10.61978/logistica.v3i1.693
[277] Traffic Management System — https://doi.org/10.55041/ijsrem47639
[290] Accident Detection and Nearby Patrol Alert System Using AI &ML — https://doi.org/10.22214/ijraset.2024.61255
[296] AI-Driven Autonomous Vehicles: A Comprehensive Review of Innovations, Challenges, and Future Pathways — https://doi.org/10.22214/ijraset.2025.74275
[297] Multi-Lane Detection and Tracking Using Vision for Traffic Situation Awareness — https://doi.org/10.1109/wimob50308.2020.9253415
[298] Insights of Deep Convolutional Neural Network for Traffic Sign Detection in Autonomous Vehicle — https://doi.org/10.1109/icaaic56838.2023.10141095
[300] IoT Based Traffic Congestion Management and Accident Detection System — https://doi.org/10.36548/jeea.2024.1.005
[301] Reducing Traffic Congestion Using Real-Time Traffic Monitoring with YOLOv8 — https://doi.org/10.14569/ijacsa.2024.01510109
[302] Artificial Intelligence for Pedestrian and Bicyclist Safety: Using AI to Detect Near-Miss Collisions — https://doi.org/10.31979/mti.2024.2350
[304] Motorcycle Blind Spot Detection Through Computer Vision Techniques — https://doi.org/10.1109/ispa58351.2023.10279254
[306] Smart Helmet Detection System for Road Safety Using YOLOv8 — https://doi.org/10.1109/i2cacis65476.2025.11100776
[314] Computer Vision-based Applications in Modern Cars for safety purposes: A Systematic Literature Review — https://doi.org/10.1109/ictas56421.2023.10082722
[317] Real-Time Deep Learning based Road Deterioration Detection for Smart Cities — https://doi.org/10.1109/wimob55322.2022.9941685
[320] A Computer Vision-Based Approach for Driver Distraction Recognition using Deep Learning and Genetic Algorithm Based Ensemble — https://doi.org/10.1007/978-3-030-87897-9_5
[321] Automatic Video Traffic Surveillance System with Number Plate Character Recognition Using Hybrid Optimization-Based YOLOv3 and Improved CNN — https://doi.org/10.1142/s021946782550041x
[322] Pedestrian Traffic Lights Classification Using Transfer Learning in Smart City Application — https://doi.org/10.1109/iccsn52437.2021.9463615
[328] Pedestrian Red-Light Violation Detection Based on Deep Learning Vision — https://doi.org/10.1109/auteee60196.2023.10407497
[330] Vehicle Crash Prediction using Vision — https://doi.org/10.1109/ciss50987.2021.9400257
[332] Adversarial Threats to AI-Driven Systems: Exploring the Attack Surface of Machine Learning Models and Countermeasures — https://doi.org/10.9734/jerr/2025/v27i21413
[342] Comparative study of pothole detection using deep learning on smartphone — https://doi.org/10.11591/ijeecs.v37.i2.pp995-1004
[345] A Review of Real-Time Vehicle Accident Detection and Insurance Claim Processing Using Artificial Intelligence and Blockchain — https://doi.org/10.1109/iccca66364.2025.11325148
[348] The Development of AI & Self Driving Technology — https://doi.org/10.55041/ijsrem18634
[349] Decision support system (DSS) for traffic prediction and building a dynamic internet community using Netnography technology in the city of Amman — https://doi.org/10.1080/0952813x.2023.2165716
[352] A Review of Driver Fatigue Detection Technologies — https://doi.org/10.1145/3773365.3773536
[354] Real-Time Driver Drowsiness and Distraction Detection Using Google ML Kit on Android Platforms — https://doi.org/10.1109/emergin67762.2025.11450791
[366] Smart Helmet Compliance System Using YOLOv8 — https://doi.org/10.1109/ice2cpt66440.2025.11340104
[377] Smart Emergency Route Optimizer System: A Systematic Literature Review — https://doi.org/10.22214/ijraset.2026.79545
[379] Lightweight Safety Assistance System for E-Scooters: Current Results and Future Directions — https://doi.org/10.1145/3748777.3748804
[402] Estimation of congestion level at intersection points using AI — https://doi.org/10.1109/icict55121.2022.10064550
[412] Image Detection and Distance Estimation for Rear Collision Avoidance using YOLOv4 on Jetson Nano — https://doi.org/10.37934/arca.32.1.2229
[421] Endangered Alert: A Field-Validated Self-Training Scheme for Detecting and Protecting Threatened Wildlife on Roads and Roadsides — https://doi.org/10.1109/lra.2025.3604697
[436] Optimizing Driver Monitoring System Performance on TI-TDA4VM Edge Device — https://doi.org/10.1109/miucc62295.2024.10783523
[437] Road Sign Detection System using Neural Networks and Tensor Flow — https://doi.org/10.22214/ijraset.2022.40672
[440] Drowsiness Detection in Low-Light Conditions Using YOLO and CLAHE Augmentation for Real-Time Applications — https://doi.org/10.1109/isriti64779.2024.10963648
[445] Detection of Distracted Driver Using Convolutional Neural Network — https://doi.org/10.1109/cvprw.2018.00150
[455] VT-Former: An Exploratory Study on Vehicle Trajectory Prediction for Highway Surveillance through Graph Isomorphism and Transformer — https://doi.org/10.1109/cvprw63382.2024.00574
[457] A Comprehensive Survey of Technologies for Wildlife Detection and Accident Prevention — https://doi.org/10.1109/isacc65211.2025.10969239
[461] Colorization Method for In-Vehicle Infrared Thermal Images Based on Conditional Generative Adversarial Networks — https://doi.org/10.1109/iaecst68792.2025.11414828
[464] Deep Learning Approaches to Detect Distracted Driving Activities: A Survey — https://doi.org/10.22214/ijraset.2023.49187
[517] On board camera perception and tracking of vehicles — https://doi.org/10.5220/0002066600570066

AI Vision for Road Traffic Accidents: Scoping Review with ☸️SAIMSARA.

Digital Health

Issue 3, Volume 1, 2026

Crash detection can trigger response

Some models look before impact

Rare scenarios can break confidence

Get access to the full paper