Project Description

and image processing

According to a recent study, in India rail-road trespassing took more lives than compared to road accidents.In the past five years, 56271 deaths occurred because of rail-road trespassing.These incidents are increasing day by day.There was an increase of 10.59% of these fatalities from the years 2017-2018.Witnessing all the events on railway tracks is possible with large volumes of surveillance in railroad industry.But it takes immense labor effort to accurately watch and alert the trespassers in time.In order to decrease these deaths and save lives, we came up with the idea of automatic detection of trespassing using the YOLO(You Only Look Once) Algorithm.This Algorithm aids in detecting trespassers from the camera feed and thereby preventing trespassing, saving lives. In this project, we use the OpenCV Deep Neural Networks(dnn) module.OpenCV dnn, the module supports running inference on pre-trained deep learning models from popular frameworks such as TensorFlow, Torch, Darknet, and Caffe.