Learning to Map Vehicles into Bird's Eye View

Visual Reconstruction of an Intersection by Integrating Cameras on Multiple Vehicles

We present to generate a bird’s-eye view of road traffic scene by integrating multiple images from in-vehicle cameras for supporting traffic safety. There are many blind spots at an intersection. Such blind spots will cause accidents and traffic jams. If it is possible to obtain views from multiple vehicles coming into one intersection from different directions, we can generate a bird's-eye vie...

Bird's-Eye View Vision System for Vehicle Surrounding Monitoring

Blind spots usually lead to difficulties for drivers to maneuver their vehicles in complicated environments, such as garages, parking spaces, or narrow alleys. This paper presents a vision system which can assist drivers by providing the panoramic image of vehicle surroundings in a bird’s-eye view. In the proposed system, there are six fisheye cameras mounted around a vehicle so that their view...

Evolving Static Representations for Task Transfer

An important goal for machine learning is to transfer knowledge between tasks. For example, learning to play RoboCup Keepaway should contribute to learning the full game of RoboCup soccer. Previous approaches to transfer in Keepaway have focused on transforming the original representation to fit the new task. In contrast, this paper explores the idea that transfer is most effective if the repre...

Bird's-eye View

Cataloging Public Objects Using Aerial and Street-Level Images - Urban Trees

In this section we provide the form of the projection functions Pv(`, c) that convert from geographic locations to pixel locations in aerial view and street view images. We give the form of the inverse function P−1 v (`′, c) that converts from pixel locations to geographic coordinates. Aerial images: Aerial view imagery in Google maps is represented using a Web Mercator projection, a type of cy...