Scalable non-parametric parsing for segmentation and recognition of high-quantity, low-cost highway assets from car-mounted video streams

Vahid Balali, Mani Golparvar-Fard

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Systematic condition assessment on high-quantity low-cost highway assets requires frequent reporting on location and up-to-date status of these assets. Recent research on video-based assessment of assets have focused primarily on detecting traffic signs during data collection and are not applicable to other assets, such as guardrails and light poles. To overcome such limitations, this paper presents fast graph-based segmentation and super-parsing algorithms, which efficiently segment highway assets from 2D video streams. Using a fast graph-based segmentation algorithm, superpixels are obtained from each frame, and their appearance is computed using a histogram of textons and dense SIFT-descriptors. A likelihood ratio score is obtained for each superpixel and an asset label that maximizes the ratio is assigned. Given a frame to be interpreted, the algorithm performs global matching against the training set, followed by superpixel-level matching and efficient Markov Random Field (MRF) optimization. The MRF simultaneously labels video frame regions into semantic and geometric classes of assets. Experimental results are presented on the Virginia Tech Smart Road research facility on a 2.2 mile highway. The work contributes to the body of knowledge by detecting 3D assets that previously have not been detectable by state-of-the-art methods. It also enables further development of techniques that can recognize subcategories of highway assets.

Original languageEnglish (US)
Title of host publicationConstruction Research Congress 2014
Subtitle of host publicationConstruction in a Global Network - Proceedings of the 2014 Construction Research Congress
PublisherAmerican Society of Civil Engineers (ASCE)
Pages120-129
Number of pages10
ISBN (Print)9780784413517
DOIs
StatePublished - Jan 1 2014
Event2014 Construction Research Congress: Construction in a Global Network, CRC 2014 - Atlanta, GA, United States
Duration: May 19 2014May 21 2014

Publication series

NameConstruction Research Congress 2014: Construction in a Global Network - Proceedings of the 2014 Construction Research Congress

Other

Other2014 Construction Research Congress: Construction in a Global Network, CRC 2014
CountryUnited States
CityAtlanta, GA
Period5/19/145/21/14

ASJC Scopus subject areas

  • Building and Construction

Fingerprint Dive into the research topics of 'Scalable non-parametric parsing for segmentation and recognition of high-quantity, low-cost highway assets from car-mounted video streams'. Together they form a unique fingerprint.

Cite this