ROAD MARKING EXTRACTION USING A MODEL&DATA-DRIVEN RJ-MCMC
We propose an integrated bottom-up/top-down approach to road-marking extraction from image space. It is based on energy minimization using marked point processes. A generic road marking object model enable us to define universal energy functions that handle various types of road-marking objects (das...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2015-03-01
|
| Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/II-3-W4/47/2015/isprsannals-II-3-W4-47-2015.pdf |
| _version_ | 1818149267363069952 |
|---|---|
| author | A. Hervieu B. Soheilian M. Brédif |
| author_facet | A. Hervieu B. Soheilian M. Brédif |
| author_sort | A. Hervieu |
| collection | DOAJ |
| description | We propose an integrated bottom-up/top-down approach to road-marking extraction from image space. It is based on energy minimization
using marked point processes. A generic road marking object model enable us to define universal energy functions that handle
various types of road-marking objects (dashed-lines, arrows, characters, etc.). A RJ-MCMC sampler coupled with a simulated annealing
is applied to find the configuration corresponding to the minimum of the proposed energy. We used input data measurements to
guide the sampler process (data driven RJ-MCMC). The approach is enhanced with a model-driven kernel using preprocessed autocorrelation
and inter-correlation of road-marking templates, in order to resolve type and transformation ambiguities. The method is
generic and can be applied to detect road-markings in any orthogonal view produced from optical sensors or laser scanners from aerial
or terrestrial platforms. We show the results an ortho-image computed from ground-based laser scanning. |
| first_indexed | 2024-12-11T13:04:19Z |
| format | Article |
| id | doaj.art-275210e86582470baee28f4bcc0c8a22 |
| institution | Directory Open Access Journal |
| issn | 2194-9042 2194-9050 |
| language | English |
| last_indexed | 2024-12-11T13:04:19Z |
| publishDate | 2015-03-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-275210e86582470baee28f4bcc0c8a222022-12-22T01:06:22ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502015-03-01II-3/W4475410.5194/isprsannals-II-3-W4-47-2015ROAD MARKING EXTRACTION USING A MODEL&DATA-DRIVEN RJ-MCMCA. Hervieu0B. Soheilian1M. Brédif2Université Paris-Est, IGN, SRIG, MATIS, 73 avenue de Paris, 94160 Saint Mandé, FranceUniversité Paris-Est, IGN, SRIG, MATIS, 73 avenue de Paris, 94160 Saint Mandé, FranceUniversité Paris-Est, IGN, SRIG, MATIS, 73 avenue de Paris, 94160 Saint Mandé, FranceWe propose an integrated bottom-up/top-down approach to road-marking extraction from image space. It is based on energy minimization using marked point processes. A generic road marking object model enable us to define universal energy functions that handle various types of road-marking objects (dashed-lines, arrows, characters, etc.). A RJ-MCMC sampler coupled with a simulated annealing is applied to find the configuration corresponding to the minimum of the proposed energy. We used input data measurements to guide the sampler process (data driven RJ-MCMC). The approach is enhanced with a model-driven kernel using preprocessed autocorrelation and inter-correlation of road-marking templates, in order to resolve type and transformation ambiguities. The method is generic and can be applied to detect road-markings in any orthogonal view produced from optical sensors or laser scanners from aerial or terrestrial platforms. We show the results an ortho-image computed from ground-based laser scanning.http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/II-3-W4/47/2015/isprsannals-II-3-W4-47-2015.pdf |
| spellingShingle | A. Hervieu B. Soheilian M. Brédif ROAD MARKING EXTRACTION USING A MODEL&DATA-DRIVEN RJ-MCMC ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | ROAD MARKING EXTRACTION USING A MODEL&DATA-DRIVEN RJ-MCMC |
| title_full | ROAD MARKING EXTRACTION USING A MODEL&DATA-DRIVEN RJ-MCMC |
| title_fullStr | ROAD MARKING EXTRACTION USING A MODEL&DATA-DRIVEN RJ-MCMC |
| title_full_unstemmed | ROAD MARKING EXTRACTION USING A MODEL&DATA-DRIVEN RJ-MCMC |
| title_short | ROAD MARKING EXTRACTION USING A MODEL&DATA-DRIVEN RJ-MCMC |
| title_sort | road marking extraction using a model data driven rj mcmc |
| url | http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/II-3-W4/47/2015/isprsannals-II-3-W4-47-2015.pdf |
| work_keys_str_mv | AT ahervieu roadmarkingextractionusingamodeldatadrivenrjmcmc AT bsoheilian roadmarkingextractionusingamodeldatadrivenrjmcmc AT mbredif roadmarkingextractionusingamodeldatadrivenrjmcmc |