scispace - formally typeset
Search or ask a question
Book ChapterDOI

A User Specific APDS for Smart City Applications

TL;DR: In this article, the authors proposed an early solution to day-to-day traffic incidents through real-time support to the people through the Internet of Things (IoT) through an Accident Prevention and Detection System (APDS).
Abstract: Road accidents are the major risk factor in day-to-day life. The prevention and quick detection of an accident is the priority in saving the lives of human beings. Advances in technologies like the internet of things (IoT) make life better for everyone but adding technologies to control and manage traffic in a smarter way is a big challenge. Accident prevention and detection system (APDS) is developed to provide real time support to the people through IoT. The APDS aims to provide an early solution to day-to-day traffic incidents. The prevention of accidents is more important as vehicles are controlled by human beings. The parameters, like change in speed, human body part movements, overtaking, rule braking, etc., are responsible for the accident. It can be managed or controlled using some rule-based techniques. The abnormal behavior of each parameter can be identified by continuous monitoring, and reporting the same well in before may reduce the occurrence of an accident. Once an accident occurs, the detail information of accident data are shared with end-users with some proper authentication. The information sharing is established through machine-to-machine (M2M) communication. The end-users will get all the data regarding location, time of the accident, and many more details by accessing the web link through the internet.
Citations
More filters
DOI
15 Dec 2022
TL;DR: In this article , a road vehicle accident detection system with location alerts to rescue accident victims is proposed, where the main hardware modules include the MPU9250, a 9 degree-of-freedom (9-DoF) micro electro mechanical system (MEMS) based inertial measurement unit (IMU), Arduino nano with ESP8266 microcontroller and GPS.
Abstract: Road accidents are one of the biggest problems in the world, in which many precious lives have been lost. This work proposes a road vehicle accident detection system with location alerts to rescue accident victims. The main hardware modules include the MPU9250, a 9 degree-of-freedom (9-DoF) micro electro mechanical system (MEMS) based inertial measurement unit (IMU), Arduino nano with ESP8266 microcontroller and GPS. The IMU’s three axis accelerometer, gyroscope and magnetometer data are programmed to determine the orientation and position of the vehicle. A Wi-Fi-based communication is established using ESP8266 to send data received from sensor units to Google Firebase cloud servers in real-time. The performance of the developed device has been evaluated using a laboratory setup and also in real-time driving scenarios. The developed sensor module performs well on accident detection and emergency alert generation, which can be used in vehicles to save many lives in the event of an accident through its automatic alert service.
Proceedings ArticleDOI
15 Dec 2022
TL;DR: In this article , a road vehicle accident detection system with location alerts to rescue accident victims is proposed, where the main hardware modules include the MPU9250, a 9 degree-of-freedom (9-DoF) micro electro mechanical system (MEMS) based inertial measurement unit (IMU), Arduino nano with ESP8266 microcontroller and GPS.
Abstract: Road accidents are one of the biggest problems in the world, in which many precious lives have been lost. This work proposes a road vehicle accident detection system with location alerts to rescue accident victims. The main hardware modules include the MPU9250, a 9 degree-of-freedom (9-DoF) micro electro mechanical system (MEMS) based inertial measurement unit (IMU), Arduino nano with ESP8266 microcontroller and GPS. The IMU’s three axis accelerometer, gyroscope and magnetometer data are programmed to determine the orientation and position of the vehicle. A Wi-Fi-based communication is established using ESP8266 to send data received from sensor units to Google Firebase cloud servers in real-time. The performance of the developed device has been evaluated using a laboratory setup and also in real-time driving scenarios. The developed sensor module performs well on accident detection and emergency alert generation, which can be used in vehicles to save many lives in the event of an accident through its automatic alert service.
References
More filters
Journal ArticleDOI
TL;DR: A methodology using Geographical Information Systems (GIS) and Kernel Density Estimation to study the spatial patterns of injury related road accidents in London, UK and a clustering methodology using environmental data and results from the first section in order to create a classification of road accident hotspots are presented.

576 citations

Proceedings ArticleDOI
04 Oct 2011
TL;DR: An Android-based application that monitors the vehicle through an On Board Diagnostics (OBD-II) interface, being able to detect accidents and is able to react to accident events in less than 3 seconds, validating the feasibility of smartphone based solutions for improving safety on the road.
Abstract: The increasing activity in the Intelligent Transportation Systems (ITS) area faces a strong limitation: the slow pace at which the automotive industry is making cars "smarter". On the contrary, the smartphone industry is advancing quickly. Existing smartphones are endowed with multiple wireless interfaces and high computational power, being able to perform a wide variety of tasks. By combining smartphones with existing vehicles through an appropriate interface we are able to move closer to the smart vehicle paradigm, offering the user new functionalities and services when driving. In this paper we propose an Android-based application that monitors the vehicle through an On Board Diagnostics (OBD-II) interface, being able to detect accidents. Our proposed application estimates the G force experienced by the passengers in case of a frontal collision, which is used together with airbag triggers to detect accidents. The application reacts to positive detection by sending details about the accident through either e-mail or SMS to pre-defined destinations, immediately followed by an automatic phone call to the emergency services. Experimental results using a real vehicle show that the application is able to react to accident events in less than 3 seconds, a very low time, validating the feasibility of smartphone based solutions for improving safety on the road.

242 citations

Journal ArticleDOI
TL;DR: A novel method for detecting road accidents by analyzing audio streams to identify hazardous situations such as tire skidding and car crashes is proposed and the obtained results confirm the effectiveness of the proposed approach.
Abstract: In the last decades, several systems based on video analysis have been proposed for automatically detecting accidents on roads to ensure a quick intervention of emergency teams. However, in some situations, the visual information is not sufficient or sufficiently reliable, whereas the use of microphones and audio event detectors can significantly improve the overall reliability of surveillance systems. In this paper, we propose a novel method for detecting road accidents by analyzing audio streams to identify hazardous situations such as tire skidding and car crashes. Our method is based on a two-layer representation of an audio stream: at a low level, the system extracts a set of features that is able to capture the discriminant properties of the events of interest, and at a high level, a representation based on a bag-of-words approach is then exploited in order to detect both short and sustained events. The deployment architecture for using the system in real environments is discussed, together with an experimental analysis carried out on a data set made publicly available for benchmarking purposes. The obtained results confirm the effectiveness of the proposed approach.

185 citations

Journal ArticleDOI
TL;DR: A support vector machine-based posterior probabilistic model (SVMPPM) aimed at transforming the drowsiness level to any value of 0~1 instead of discrete labels is proposed, indicating that the combination of the proposed SVMPPM, the EEG headband, and the wrist-worn smart device constitutes an effective, simple, and inexpensive wearable solution for DDD.
Abstract: Driver drowsiness is a major cause of mortality in traffic accidents worldwide. Many physiological signals have been proposed to detect driver drowsiness. Among these signals, an electroencephalographic (EEG) signal, which reflects the brain activities, is more directly related to drowsiness. Thus, many EEG-based driver drowsiness detection (DDD) models gained more and more attention in recent years. However, one limitation of these studies is that these models merely estimate discrete labels and, thus, did not allow for estimating the relative severity of driver drowsiness. This paper proposes a support vector machine-based posterior probabilistic model (SVMPPM) for DDD, aimed at transforming the drowsiness level to any value of $0\sim 1$ instead of discrete labels. A fully wearable EEG system which consists of a Bluetooth-enabled EEG headband and a commercial smartwatch was used to evaluate the proposed model in a real-time way. Twenty subjects who participated in a 1-h monotonous driving simulation experiment were used to develop this model with fifteen subjects for a building model and five subjects for a testing model. According to a video-based reference, the proposed system obtained an accuracy of 91.25% for an alert group (73 out of 80 data sets), 83.78% for an early-warning group (93 out of 111 data sets), and 91.92% for a full-warning group (91 out of 99 data sets). These results indicate that the combination of the proposed SVMPPM, the EEG headband, and the wrist-worn smart device constitutes an effective, simple, and inexpensive wearable solution for DDD.

151 citations

Proceedings ArticleDOI
08 Jun 2014
TL;DR: The novel approach is an extension of the Naïve Bayesian approach and results in a generative model that builds on the relations to the directly surrounding vehicles and to the static traffic environment.
Abstract: Risk estimation for the current traffic situation is crucial for safe autonomous driving systems. One part of the uncertainty in risk estimation is the behavior of the surrounding traffic participants. In this paper we focus on highway scenarios, where possible behaviors consist of a change in acceleration and lane change maneuvers. We present a novel approach for the recognition of lane change intentions of traffic participants. Our novel approach is an extension of the Naive Bayesian approach and results in a generative model. It builds on the relations to the directly surrounding vehicles and to the static traffic environment. We obtain the conditional probabilities of all relevant features using Gaussian mixtures with a flexible number of components. We systematically reduce the number of features by selecting the most powerful ones. Furthermore we investigate the predictive power of each feature with respect to the time before a lane change event. In a large scale experiment on real world data with over 160.781 samples collected on a test drive of 1100km we trained and validated our intention prediction model and achieved a significant improvement in the recognition performance of lane change intentions compared to current state of the art methods.

141 citations