| dc.contributor.author | Osuto, Daniel Arani | |
| dc.contributor.author | Ouma, Heywood Absaloms | |
| dc.contributor.author | Ndungu, EN | |
| dc.date.accessioned | 2022-12-01T05:33:20Z | |
| dc.date.available | 2022-12-01T05:33:20Z | |
| dc.date.issued | 2022-04-04 | |
| dc.identifier.citation | Osuto, D. A., Ouma, H. A., & Ndungu, E. N. (2022, April). Automatic Road Traffic Density Estimation using Image Processing Algorithms. In Proceedings of the Sustainable Research and Innovation Conference (pp. 80-86). | en_US |
| dc.identifier.uri | http://repository.must.ac.ke/handle/123456789/835 | |
| dc.description.abstract | In the modern world, urban centres are growing at a very high rate. Growing with them is road traffic congestion. Traffic jams, especially at peak hours, have become routine. As a result, traffic management is one of the most pressing issues in today’s towns. Several alternatives are being sought to deal with the problem. These include: expansion of road networks, regulating the number of vehicles on the roads, and deployment of Intelligent Transportation Systems (ITSs). Other than the ITSs, the other alternatives (however effective) have many practical
challenges in their implementation. ITSs are based on a wide range of technologies such as loop sensors and video surveillance systems. Vision based ITSs have proved advantageous over the traditional methods based on loop sensors. In these modern systems, video surveillance cameras are installed along the roads and road intersections where they are used to collect traffic data. The data is then analysed to obtain traffic parameters such as the road traffic density. In this paper, a simple and elegant approach for estimating the road traffic density during daytime using image processing and computer vision algorithms is presented. The video data collected is first broken down into frames which are then pre-processed in a series of steps. Finally, the vehicles are detected and extracted from the images and counted. Then the traffic density is obtained as the number of vehicles per unit area of the road section. The proposed approach was implemented in MATLAB R2015a and average vehicle detection accuracies of 96.0% and 82.1% were achieved for fast moving and slow moving traffic scenes respectively. | en_US |
| dc.language.iso | en_US | en_US |
| dc.publisher | Proceedings of the 2016 Sustainable Research & Innovation (SRI) Conference | en_US |
| dc.subject | Image processing | en_US |
| dc.subject | intelligent transportation systems | en_US |
| dc.subject | road traffic density | en_US |
| dc.title | Automatic Road Traffic Density Estimation using Image Processing Algorithms | en_US |
| dc.type | Article | en_US |
