Jul 2026· International Research Journal of Advanced Engineering and Technology· Vol 3, pp. 16-23· 0 citations
TL;DR
The study illustrates how the synergy between AI technologies and IoT-enabled sensing and communication capabilities can significantly improve the capabilities of accident detection, reduce emergency response times and contribute to overall road safety.
Abstract
Road traffic collisions are a serious public safety issue that continues to cause high rates of death, injury and economic losses around the world. Reporting systems for accidents are frequently inefficient and slow, especially in low-traffic regions and remote areas, which can delay the response to an accident. With the advent of the Internet of Things (IoT), Artificial Intelligence (AI), computer vision and intelligent transportation systems, automatic crash detection systems have been developed that have ability to monitor in real-time and report the crash quickly. A comprehensive review of the various IoT and AI-based crash detection technologies is provided including the sensing hardware, communication infrastructure, cloud and fog computing, computer vision and machine learning techniques. It reviews the latest studies on using accelerometers, GPS, surveillance cameras, CNN and YOLO-based models to detect accidents, and offers a comparative assessment of their techniques, advantages, obstacles, and suggestions. There are several research gaps identified in the review, such as limited accident severity assessment, limited multimodal sensor fusion, and scalability issues; interoperability problems, privacy concerns, and real-world validation problems in different traffic environments. Based on these findings, future research directions for the paper are discussed, focusing on Explainable AI, Real-time inference at the edge, Secure IoT communication and Scalable intelligent transportation frameworks. The study illustrates how the synergy between AI technologies and IoT-enabled sensing and communication capabilities can significantly improve the capabilities of accident detection, reduce emergency response times and contribute to overall road safety.
Road traffic accidents represent a significant global issue, the rates of which are significantly raised by the delay in emergency response existing approach are not automated and do not have advanced real-time analysis because they rely either on sensor-based detection of impact or in the CCTV monitoring. A machine learning-based road accident detection and alert system based on the YOLOv5 is proposed in the present research. Under one system, it is a mix of motion tracking and vehicle detection, estimating an accident and classifying it. Whereas MOSSE tracking is applied to maintain vehicle identity across frames, YOLOv5 is employed in vehicle detection. Crashes are estimated using velocity variation analysis and intersection over union. The Support Vector Machine is applied to identify and classify the violent flow motion descriptors to confirm collision events. Upon confirmation, crash film is stored to be monitored and analyzed, and automated email and text messages are sent to provide alerts. The technology is suitable in intelligent traffic surveillance application because experimental testing demonstrates a stable detection performance with a rapid response time.
Narayana K.E, Sathyasandar S· 2026 6th International Confe...· 0 citations
In the world, road traffic accidents are among the top causes of fatalities: There is a large risk of severe injuries and
fatalities if an emergency response is late. This paper introduces an intelligent road accident detection and emergency alert
system for a smartphone which is based on the multi-sensor data fusion and machine-learning techniques that allow the fast
detection of the accident and early alert notification. The proposed framework uses the data from the vehicle's accelerometer,
gyroscope and Global Positioning System (GPS) to continuously monitor the specific dynamics of the vehicle, recognizing the
abnormal patterns of movement involved in road accidents. The sensor noise is eliminated in a preprocessing step, and
discriminative motion features are extracted from the sensor signals, which are then classified by a Support Vector Machine
(SVM) to discriminate between the collision and normal driving events and minimize false alarms. In the case of a potential
accident being detected, the system activates a reprogrammable confirmation timer the user can use to cancel unintentional
alerts before automatically sending the location of the accident as well as emergency information to preprogrammed contacts.
The proposed method does not require any special in-vehicle hardware, and uses inexpensive sensors from existing
smartphones, which are also widely available, so it is a cost-effective and readily deployable solution. The proposed framework
is evaluated through experimentation, and the results show a high accuracy of detection with a low false-positive rate, while
remaining real-time for practical implementation. Intelligent sensor fusion, machine learning-based classification, and
automated emergency communication contribute to an enhanced road safety, minimizing emergency response time and
improving the reliability of accident detections.
Jaladi Sravanthi, B. Lakshmi· International Journal for Re...· 0 citations
Rapid urbanization and increasing vehicle numbers have led to a significant rise in road accidents, posing serious threats to human life and economic stability. Traditional accident detection systems rely on manual reporting, causing delays in emergency response. To address this, computer vision integrated with intelligent transportation systems offers an effective solution. This study analyzes pre-2018 approaches to traffic accident detection using video surveillance. The proposed system automatically detects accidents by analyzing traffic camera footage through feature extraction, motion analysis, and pattern recognition. It identifies abnormal vehicle behavior such as sudden speed drops, collisions, and irregular trajectories. Classical computer vision techniques like optical flow, background subtraction, edge detection, and machine learning methods such as Support Vector Machines (SVM) and decision trees are used. The system includes preprocessing, object detection, trajectory tracking, and classification of normal and abnormal events, supported by mathematical modeling and threshold-based decisions. Results show high detection accuracy with low false alarms, especially in controlled environments like highways and intersections. However, challenges remain in real-time implementation due to lighting, occlusion, and camera angle issues. Future work suggests incorporating deep learning and multi-sensor data fusion to improve performance. In conclusion, computer vision-based accident detection is a promising approach to enhancing road safety and reducing response time, contributing to the advancement of smart transportation systems.
Nimal Perera, Tharindu Jayasinghe· International Journal of Mod...· 0 citations
Road accidents remain one of the leading causes of injury and death worldwide, and delays in detecting and reporting them significantly increase the risk of severe outcomes. Conventional CCTV-based surveillance depends heavily on human operators, making continuous, error-free monitoring of multiple video feeds impractical. This paper presents an AI-Powered Real-Time Accident Detection and Emergency Response System with Vehicle Forensic Analysis that continuously monitors live CCTV streams using YOLOv11 for vehicle detection and DeepSORT for multi-object tracking to identify collisions automatically. Upon detecting an accident, the system assesses its severity, stores the event in a relational database, and instantly dispatches alerts through SMS, email, voice call, and a monitoring dashboard. A dedicated forensic module then reconstructs the incident by extracting collision frames, recognizing number plates through Optical Character Recognition (OCR), estimating vehicle speed, and retrieving owner records, culminating in an automatically generated digital forensic PDF report for use by police, insurers, and legal authorities. Experimental evaluation across varied traffic and lighting conditions confirms reliable accident detection, fast alert dispatch, and consistent forensic report generation, demonstrating the system's potential to shorten emergency response times and streamline post-accident investigation
Vidya M N, Prajwal Raj V, Dr Manjunath B· International Journal of Adv...· 0 citations
Road accidents are a leading cause of injury and death around the world due to the delayed emergency response and drunk
driving, without the availability of real-time monitoring systems. Traditional accident-reporting procedures rely on
manual communication and lead to longer rescue times and limited prospects of timely medical support. In order to solve
these problems, this research introduces an intelligent smart accident detection and instant alert generation system based
on an embedded system and wireless communication technologies. This proposed solution combines the use of Arduino
Uno, vibration sensors, alcohol sensors, GPS modules, GSM communication, Wi-Fi connectivity, LCD displays, and
buzzer units to enable real-time monitoring of vehicles and automated emergency responses.
The system is constantly assessing the state of the vehicle and driver's actions in real time. The vibration sensor senses
anomaly of the intensity of impact in case of collision and can immediately begin the mechanism for the detection of the
accident. The GPS module gets the exact geographical position of the vehicle and the GSM module automatically sends
out emergency call messages of the accident and the geographical coordinates of the accident to preprogrammed
emergency contacts. The framework is also designed to include an alcohol monitoring feature that detects alcohol
impaired driving conditions, and provides warnings to prevent alcohol impaired driving. Furthermore, Wi-Fi connectivity
allows for cloud-based monitoring and integration with IoT, which can facilitate real-time data analysis and intelligent
transportation solutions.
Daripally Karthik, M. Ramesh, Dr. L Jagadeesh Naik· International Journal of Dru...· 0 citations
: Road safety remains a critical global concern, with road hazards and sudden braking incidents contributing significantly to accidents. This research introduces an enhanced road safety system that combines motion sensor-based detection with computer vision algorithms to create a more comprehensive hazard alert system. The system employs smartphone sensors including accelerometers, gyroscopes, GPS, and the device camera to detect road hazards, provide lane departure warnings, and alert drivers to potential collision risks. Our application, 'RoadAware' aims to reduce accidents by offering real-time hazard alerts, mapping dangerous road conditions, and providing visual driving assistance through multiple modes including dash-mount computer vision and heads-up display reflection. This paper details the implementation of computer vision models for lane detection and forward collision warning, performance optimization techniques across various devices, and integration with existing motion-based hazard detection. Testing results demonstrate significant improvements in detection accuracy, with pothole identification reaching 93% accuracy and false positive rates for sudden braking detection reduced to 0.5%. The multi-modal approach addresses various driving contexts and environmental conditions, enhancing the system's versatility and effectiveness.
Manisha More, Aatish Bagal, Sneha Bade et al.· Proceedings of the 1st Inter...· 0 citations
