PROJECT TITLE :

An Embedded Vision System for Real-Time Autonomous Localization Using Laser Profilometry

ABSTRACT:

During this paper, we have a tendency to propose an embedded vision system primarily based on laser profilometry in a position to urge the create of a vehicle and its relative displacements near to the constitutive media of a structured surroundings. Fundamental equations for laser triangulation are developed and encoded for their actual implementation on an embedded system. It is made of a laser supply that projects a line-formed beam onto the surroundings and an on-chip camera in a position to frame the laser lightweight. Pictures are then sent to the inexpensive Raspberry Pi onboard pc, that is responsible for processing tasks. For the first time, laser profilometry is including the correlation of laser signatures on an occasional-price and low-resource processing board for vehicle localization functions. Several validation tests of the proposed sensor have proven the effectiveness of the system with respect to commercially on the market sensors like inductive sensors and normal odometers, which fail when the vehicle crosses path interceptions or its wheels bear unavoidable slippages. Moreover, further comparisons with other vision-based techniques have conjointly proven the good performances of this embedded system for real-time localization of vehicles.