Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Camera-based positioning system using learning

a technology of learning and camera, applied in the field of wireless devices, can solve the problems of requiring substantial time and computational resources to perform effective camera-based localization, and may be difficult to communicate with a remote satellite, and achieve the effects of reducing memory overhead, significant computational efficiency, and reducing accuracy

Active Publication Date: 2020-08-13
RICE UNIV +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

[0004]A device, system, and methods are described to perform machine-learning camera-based indoor mobile positioning. The indoor mobile positioning may utilize inexact computing, wherein a small decrease in accuracy is used to obtain significant computational efficiency. Hence, the positioning may be performed using a smaller memory overhead at a faster rate and with lower energy cost than previous implementations. The positioning may not involve any communication (or data transfer) with any other device or the cloud, providing privacy and security to the device. A hashing-based image matching algorithm may be used which is cheaper, both in energy and computation cost, over existing state-of-the-art matching techniques. This significant reduction allows end-to-end computation to be performed locally on the mobile device. The ability to run the complete algorithm on the mobile device may eliminate the need for the cloud, resulting in a privacy-preserving localization algorithm by design since network communication with other devices may not be required.

Problems solved by technology

However, in some indoor situations communication with a remote satellite may prove difficult.
Camera-based localization typically requires substantial time and computational resources to perform effectively, and may further require that the computation be performed remotely (e.g., in the cloud).

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Camera-based positioning system using learning
  • Camera-based positioning system using learning
  • Camera-based positioning system using learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029]Embodiments herein describe a camera based (privacy-preserving) indoor mobile positioning system, Camera-based Positioning System using Learning (CaPSuLe), which may not involve any communication (or data transfer) with any other device or the cloud. According to some embodiments, to determine position of a device in an indoor environment accurately, instead of using GPS, Wi-Fi or any cloud based service, a user of a UE may take a picture and algorithmically determine the location of the UE, using computationally cheap on-device hash lookups of the taken image. The indoor mobile positioning may utilize inexact computing, wherein a small decrease in accuracy is used to obtain significant computational efficiency.

[0030]Embodiments herein may provide sustainable and private navigation, e.g., in mall, campuses, indoor building etc., without involving any network or cloud service. The navigation may be privacy preserving (the position of the user is never calculated outside the dev...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A device, system, and methods are described to perform machine-learning camera-based indoor mobile positioning. The indoor mobile positioning may utilize inexact computing, wherein a small decrease in accuracy is used to obtain significant computational efficiency. Hence, the positioning may be performed using a smaller memory overhead at a faster rate and with lower energy cost than previous implementations. The positioning may not involve any communication (or data transfer) with any other device or the cloud, providing privacy and security to the device. A hashing-based image matching algorithm may be used which is cheaper, both in energy and computation cost, over existing state-of-the-art matching techniques. This significant reduction allows end-to-end computation to be performed locally on the mobile device. The ability to run the complete algorithm on the mobile device may eliminate the need for the cloud, resulting in a privacy-preserving localization algorithm by design since network communication with other devices may not be required.

Description

GOVERNMENT RIGHTS IN INVENTION[0001]This invention was made with government support under Grant No. FA8750-16-2-0004 awarded by the Department of Defense-Air Force Research Laboratory (DoD-AFRL). The government has certain rights in the invention.FIELD OF THE INVENTION[0002]The present invention relates to the field of wireless devices, and more particularly to camera-based positioning systems for wireless devices.DESCRIPTION OF THE RELATED ART[0003]As mobile electronic devices become increasingly interwoven in a user's life, there have arisen a multitude of situations in which it may be desirable to locate the position of the device. Localization technology to accomplish this task is an active area of research. Many existing implementations rely on communication using satellite-based positioning technology (e.g., GPS or other technology). However, in some indoor situations communication with a remote satellite may prove difficult. Camera-based localization typically requires substa...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(United States)
IPC IPC(8): G01C21/20G06T7/73G06K9/62G06N20/00G06F16/51G06F16/532
CPCG06F16/532G06K9/6215G06T7/74G06F16/51G01C21/206G06K9/6256G06T2207/20081G06N20/00Y02D30/70G06F18/22G06F18/214
Inventor SHRIVASTAVA, ANSHUMALILUO, CHENPALEM, KRISHNAMOON, YONGSHIKNOH, SOONHYUNPARK, DAEDONGHONG, SEONGSOO
Owner RICE UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products