Please use this identifier to cite or link to this item:
|Title:||Identification of Night Time Poor Visibility Areas in Urban Streets|
|Abstract:||Street lightning system is very essential to improve the quality of urban life by promoting security in urban areas. It is also very helpful to promote road safety by improving night time visibility for the drivers, riders, and pedestrians. Primary purpose of street lightning system is to cast light onto roadways, parking areas, public spaces, certain areas of high security, or any area where homeland safety and security issues arise. It is a well-known fact that street lightning system helps in improving visibility and to reduce traffic accidents by a considerable amount particularly in the dark hours and it is, therefore, necessary to provide proper lighting conditions on the roads in low-lighting conditions. Current street lighting systems are having major problem of casting non-uniform light, providing low visibility of the area of interest. In this study, a machine vision system is proposed to identify the variations in the lighting of the road in dark hours. The objective of this paper is to monitor the variations in the average intensity of the light on theroad. Sample data was acquired in the forms of videos of road lightning conditions in the dark, and then frames were extracted from these sample videos. Various image processing tools were used to pre-process the raw image data and further morphological operations were performed on images to compute the average intensity of the street light on each sample frame. In this observation, the variation in average intensity values are found to be useful in identifying the low lighting conditions on the road in the dark hours. The preliminary results were very promising and clearly indicate significant variations in the light falling on the road during night time. The proposed system will be helpful in monitoring and improving irregular lighting on theroads.|
|ISSN:||0975-2412 (Online); 0771-7706 (Print)|
|Appears in Collections:||BVAAP Vol.27(1&2) [June-December 2019]|
Items in NOPR are protected by copyright, with all rights reserved, unless otherwise indicated.