Open AccessReal-Time Lane Detection and Object Recognition in Self-Driving Car using YOLO neural network and Computer Vision
Publication year - 2020
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.g1010.0597s20
Subject(s) - artificial intelligence , computer vision , hough transform , computer science , object detection , canny edge detector , viola–jones object detection framework , minimum bounding box , cognitive neuroscience of visual object recognition , context (archaeology) , object (grammar) , enhanced data rates for gsm evolution , artificial neural network , edge detection , robotics , robot , pattern recognition (psychology) , image processing , image (mathematics) , face detection , facial recognition system , paleontology , biology
The Darwinism of Artificial Intelligence and robotics has grown up incredibly. Recently, there are a lot of progress have been undertaken in the context of Autonomous vehicle. Robo-car or self driving car consist many module like localization and mapping, scene understanding, movement planning, and driver state. In movement planning lane perception and recognition of the object plays vital role. This proposed state-of-art recognizes the road track in the video‘s frame and perform lane detection using canny edge detector and Hough transform algorithm. In this paper, Object recognition is possible with help of YOLO (you only look once) which is one of the real time CNN methods aims to detect object inside the image as part of road track. The result manifests the road lane detection guidance and object recognition along with prediction probability and bounding box