In self-driving vehicles, vehicle-to-vehicle communication is a key to solving
traffic jams, avoiding accidents, choosing a perfect routine to destination and many
other problems. In vehicle-to-vehicle scenarios, people usually use microwave
communication which works well but is subject to times of low SNR in cluttered
radio frequency(RF) environment and cost is high, so optical communication can be
used to improve SNR. While laser transmission has direction restriction. Tracking
techniques can be deployed to narrow the transmitting angle of the laser, enhancing
the intensity level at receiver.If the transmitter can be tracked under vehicular
environments, the performance of free space optical(FSO) communication will be
enhanced to a large extent. According to frames caught by camera on car, we try
using feature identifying and extraction techniques to locate the positions of multiple
markers on other cars from caught frame and using object tracking algorithm to
predict the moving of markers to guide the direction of laser’s transmitting.
