CaltechAUTHORS
  A Caltech Library Service

Annotated Reconstruction of 3D Spaces Using Drones

Nair, Suraj and Ramachandran, Anshul and Kundzicz, Peter (2017) Annotated Reconstruction of 3D Spaces Using Drones. In: MIT IEEE Undergraduate Technology Research Conference 2017, November 3-5, 2017, Cambridge, MA. (In Press) http://resolver.caltech.edu/CaltechAUTHORS:20171110-152713005

[img] PDF - Accepted Version
See Usage Policy.

5Mb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20171110-152713005

Abstract

As the fields of robotics and drone technologies are continually advancing, the challenge of teaching these agents to learn and maneuver in the real world becomes increasingly important. A critical component of this is the ability for a robot to map and understand its surrounding unknown environment, both in terms of physical structure and object classification. In this project we tackle the challenge of mapping a 3D space with annotations using only 2D images acquired from a Parrot Drone. In order to make such a system operate efficiently in close to real time, we address a number challenges including (1) creating a optimized version of Faster RCNN that can operate on drone hardware while still being accurate, (2) developing a method to reconstruct 3D spaces from 2D images annotated with bounding boxes, and (3) using generated 3D annotations to complete drone motion planning for unknown space exploration.


Item Type:Conference or Workshop Item (Paper)
Subject Keywords:Computer Vision, Robotics, Motion Planning
Record Number:CaltechAUTHORS:20171110-152713005
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20171110-152713005
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:83135
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:10 Nov 2017 23:39
Last Modified:10 Nov 2017 23:39

Repository Staff Only: item control page