Demonstration of Commercial-off-the-Shelf Change Detection on Railway Images

Henderson, Herbert; Borsholm, Atle

i

Demonstration of Commercial-off-the-Shelf Change Detection on Railway Images

2019-07-01
By Henderson, Herbert ; Borsholm, Atle

File Language:

English

[PDF - 22.15 MB]

Details

Creators:

Henderson, Herbert ; Borsholm, Atle
Corporate Creators:

Ensco, Inc. ; Harris Corporation
Corporate Contributors:

United States. Department of Transportation. Federal Railroad Administration. Office of Railroad Policy and Development ; United States. Department of Transportation. Federal Railroad Administration. Office of Research, Development and Technology
Subject/TRT Terms:
Publication/ Report Number:

DOT/FRA/ORD-19/22 ; SERV-REPT-0001686
Resource Type:

Tech Report
Geographical Coverage:

United States
Edition:

Technical Report, 2017
Contracting Officer:

Baillargeon, Jay
Corporate Publisher:

United States. Department of Transportation. Federal Railroad Administration
Abstract:

This study, conducted jointly by ENSCO, Inc. and Harris Corporation, assessed the potential benefits of applying commercially available change detection software to railway machine vision images. Change detection involves registering “Before” and “After” images on a pixel-by-pixel basis to isolate changed areas. Two modes of change detection were assessed: intensity-based detection that identifies change where pixel intensity differs and thematic-based detection that identifies change where pre-determined pixel themes (e.g., concrete, ballast, etc.) occur. The intensity-based mode has shown potential for use on rail-based images; the thematic-based mode has shown potential to help fill a supporting role of filtering non-relevant changes.
Format:

PDF
Funding:

DTFR53-17-C-00001
Download URL:

https://rosap.ntl.bts.gov/view/dot/41704/dot_41704_DS1.pdf
File Type:

[PDF - 22.15 MB]
Collection(s):

Federal Railroad Administration
Main Document Checksum:

urn:sha256:0fc3ccc50fb41009ba5200f4395c760a11ebf335f5cc39c07a3e5f57156f775f

File Language:

English

ON THIS PAGE

Details

Found an issue?

Send us an email at:

publishinghd@cdc.gov

ROSA P serves as an archival repository of USDOT-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by USDOT or funded partners. As a repository, ROSA P retains documents in their original published format to ensure public access to scientific information.