Monocular distance estimation using pinhole camera approximation to avoid vehicle crash and back-over accidents
Rajesh Kannan Megalingam, Vignesh Shriram, Bommu Likhith, Rajesh Gangireddy, Sriharsha Ghanta · 2016
Many accidents happen while driving due to false estimation of the tailgating vehicle's distance and even while backing up or parking the vehicles in a parking lot. It is very important for the driver to know how close the tailgating vehicle. It is equally important to know the vicinity of the other vehicles and objects while parking or taking vehicle from the parking lots. The main objective of this paper is to accurately estimate the distance of a specific object by approximating the camera to be an ideal pinhole camera. In this method we use triangle similarity to estimate the distance after obtaining the focal length (in pixels) of the camera. Using image processing techniques we detect the object for which we want to estimate the distance. We input the known width of the object and using the calculated focal length, the algorithm calculates the distance after identifying the object. The experimental results are very promising that the estimation of the distance of an object using pin hole approximation would be extremely useful in vehicles to avoid accidents.