Advanced

Minimum hardware SfM/SLAM for sparse data point mapping of retail stores

Falk, Daniel LU (2016) In Master's Theses in Mathematical Sciences FMA820 20161
Mathematics (Faculty of Engineering)
Abstract
This report aims to compare methods that can be used to efficiently and accurately map digital price labels position in 3D space using a mobile robotic platform equipped with camera vision in a retail environment. The robotic platform built during the project uses four wide angle cameras to cover the full circular view in the horizontal plane. Installation of external systems for e.g. navigation can be very costly and time demanding. The accuracy, repeatability and time consumption have been evaluated for a set of methods and combinations thereof with and without external hardware. The result of the tests shows a proof-of-concept with good results but also emphasizes the need for a robust system. The mapping is done with high accuracy even... (More)
This report aims to compare methods that can be used to efficiently and accurately map digital price labels position in 3D space using a mobile robotic platform equipped with camera vision in a retail environment. The robotic platform built during the project uses four wide angle cameras to cover the full circular view in the horizontal plane. Installation of external systems for e.g. navigation can be very costly and time demanding. The accuracy, repeatability and time consumption have been evaluated for a set of methods and combinations thereof with and without external hardware. The result of the tests shows a proof-of-concept with good results but also emphasizes the need for a robust system. The mapping is done with high accuracy even when the external hardware for navigation is completely removed. As a part of the project a novel line following algorithm has been developed which shows results far better than any published results found and yet capable of running in real time utilizing limited hardware. (Less)
Popular Abstract (Swedish)
Vi har konstruerat en liten robot på hjul som kan köra runt i matbutiker och kartlägga positionen av prislappar. Roboten använder sig av kameror för att triangulera fram en 3D position för prislapparna som den har sett från flera vinklar. Roboten skapar automatiskt en karta över sin omgivning genom att optimera sin egen och omgivningens position för att minimera skillnaden mellan den matematiskt förväntade bilden och den bild som kamerorna
faktiskt har sett. En nytänkande algoritm för linjeföljning med kamera har också utvecklats och publicerats i en akademisk journal.
Please use this url to cite or link to this publication:
author
Falk, Daniel LU
supervisor
organization
alternative title
En utvärdering av SfM/SLAM för kartläggning av lågdensitets punktmoln i detaljhandel
course
FMA820 20161
year
type
H2 - Master's Degree (Two Years)
subject
keywords
structure from motion, simultaneous localization and mapping, generalized imaging device, camera pose estimation, sparse data, point clouds, path planning, artificial intelligence, intelligent agent, line following, navigation, computer vision, cognitive science, stroke width transform
publication/series
Master's Theses in Mathematical Sciences
report number
LUTFMA-3303-2016
ISSN
1404-6342
other publication id
2016:E43
language
English
id
8890475
date added to LUP
2016-11-16 10:53:04
date last changed
2016-11-16 10:53:04
@misc{8890475,
  abstract     = {This report aims to compare methods that can be used to efficiently and accurately map digital price labels position in 3D space using a mobile robotic platform equipped with camera vision in a retail environment. The robotic platform built during the project uses four wide angle cameras to cover the full circular view in the horizontal plane. Installation of external systems for e.g. navigation can be very costly and time demanding. The accuracy, repeatability and time consumption have been evaluated for a set of methods and combinations thereof with and without external hardware. The result of the tests shows a proof-of-concept with good results but also emphasizes the need for a robust system. The mapping is done with high accuracy even when the external hardware for navigation is completely removed. As a part of the project a novel line following algorithm has been developed which shows results far better than any published results found and yet capable of running in real time utilizing limited hardware.},
  author       = {Falk, Daniel},
  issn         = {1404-6342},
  keyword      = {structure from motion,simultaneous localization and mapping,generalized imaging device,camera pose estimation,sparse data,point clouds,path planning,artificial intelligence,intelligent agent,line following,navigation,computer vision,cognitive science,stroke width transform},
  language     = {eng},
  note         = {Student Paper},
  series       = {Master's Theses in Mathematical Sciences},
  title        = {Minimum hardware SfM/SLAM for sparse data point mapping of retail stores},
  year         = {2016},
}