Abstract
In this emerging world, peoples are running behind the time and wasted their time in travelling. Drastic increase in population results in rapid increase of number of vehicles. A semantic based road traffic model is proposed to predict the traffic and to inform the public about the current traffic condition to all persons who belongs to the same lane. Real time data is acquired from Ultrasonic, PIR sensor and camera. Proposed system uses the vehicle count, distance between the vehicles and speed of the vehicle from both sensors and camera and it applies semantic interpretation of those data uses moving weighted average model to predict the traffic condition. To have time efficient prediction, the work is experimented in Apache Spark which will reduce disk latency when compared to Hadoop. Prediction result is sent it as alert message to the public as a location-based messages. So, public will receive message even they don’t have smart phone. Therefore, the traffic prediction system results are more helpful in goods transportation and accident prediction system etc.
Highlights
In this fast-moving world, where people can find everything in their fingertips draws them to a congested environment
A semantic based road traffic model is proposed to predict the traffic and to inform the public about the current traffic condition to all persons who belongs to the same lane
Results and discussions traffic prediction are discussed for the following data combinations like sensor data and video data separately and with both sensor and video data and integrating semantics with both sensor and video data
Summary
In this fast-moving world, where people can find everything in their fingertips draws them to a congested environment. The [4] provides a field study about nonintrusive sensors for traffic data collection and they measured the following: volume, speed of the vehicle and the classification results based on many field deployment and test under various road traffic conditions. Road infrastructure details, planned events in city from website of city, vehicle information from various sensors integrated in roads and historical traffic data to predict the traffic congestion. System uses Gaussian mixture model to detect the smoke based on color pixels of images and it uses dynamic feature extraction method to find smoke area, thereby it improves system accuracy and decreases false detection These methodologies may be useful in video processing of traffic data. Ontology is created to identify both sensor data and video data from the same lane and same location and it has to be integrated with geospace ontology to provide location specific message
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
