Open AccessOBJECT RECOGNITION OF ROAD INFRASTRUCTURE USING A FULLY CONVOLUTIONAL NEURAL NETWORK
Author(s) -
Andrey Azarchenkov,
Maxim Lyubimov,
Владислав Лушков
Publication year - 2019
Publication title -
avtomatizaciâ i modelirovanie v proektirovanii i upravlenii
Language(s) - English
Resource type - Journals
eISSN - 2658-6436
pISSN - 2658-3488
DOI - 10.30987/2658-3488-2019-2019-4-38-43
Subject(s) - convolutional neural network , computer science , artificial intelligence , pedestrian , computer vision , artificial neural network , bounding overwatch , key (lock) , object (grammar) , scale (ratio) , section (typography) , pattern recognition (psychology) , transport engineering , engineering , geography , computer security , cartography , operating system
This article presents a method for recognizing key objects of the road infrastructure using a fully convolutional neural network. The result of the neural network is a segmented image, where the desired objects are highlighted in certain colors. At the post-processing stage, a section of the roadway along which the car moves is selected, as well as the calculation of the parameters of the bounding rectangles for each of the objects. This method allows you to localize the road, pedestrian crossing, cars, traffic signs, traffic lights, pedestrians. Testing of the developed algorithm was carried out on a model of the urban infrastructure at a scale of 1:18, where a wheeled robot acted as a car.