ROAD DETECTION BY NEURAL AND GENETIC ALGORITHM IN URBAN ENVIRONMENT
In the urban object detection challenge organized by the ISPRS WG III/4 high geometric and radiometric resolution aerial images about Vaihingen/Stuttgart, Germany are distributed. The acquired data set contains optical false color, near infrared images and airborne laserscanning data. The presented...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2012-07-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XXXIX-B3/247/2012/isprsarchives-XXXIX-B3-247-2012.pdf |
| _version_ | 1819064840857059328 |
|---|---|
| author | A. Barsi |
| author_facet | A. Barsi |
| author_sort | A. Barsi |
| collection | DOAJ |
| description | In the urban object detection challenge organized by the ISPRS WG III/4 high geometric and radiometric resolution aerial images about Vaihingen/Stuttgart, Germany are distributed. The acquired data set contains optical false color, near infrared images and airborne laserscanning data. The presented research focused exclusively on the optical image, so the elevation information was ignored. The road detection procedure has been built up of two main phases: a segmentation done by neural networks and a compilation made by genetic algorithms. The applied neural networks were support vector machines with radial basis kernel function and self-organizing maps with hexagonal network topology and Euclidean distance function for neighborhood management. The neural techniques have been compared by hyperbox classifier, known from the statistical image classification practice. The compilation of the segmentation is realized by a novel application of the common genetic algorithm and by differential evolution technique. The genes were implemented to detect the road elements by evaluating a special binary fitness function. The results have proven that the evolutional technique can automatically find major road segments. |
| first_indexed | 2024-12-21T15:36:58Z |
| format | Article |
| id | doaj.art-dfba9e5b0ba24a1db90f71583faebcce |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-12-21T15:36:58Z |
| publishDate | 2012-07-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-dfba9e5b0ba24a1db90f71583faebcce2022-12-21T18:58:37ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342012-07-01XXXIX-B324725210.5194/isprsarchives-XXXIX-B3-247-2012ROAD DETECTION BY NEURAL AND GENETIC ALGORITHM IN URBAN ENVIRONMENTA. Barsi0Dept. of Photogrammetry and Geoinformatics, Budapest University of Technology and Economics, Budapest, HungaryIn the urban object detection challenge organized by the ISPRS WG III/4 high geometric and radiometric resolution aerial images about Vaihingen/Stuttgart, Germany are distributed. The acquired data set contains optical false color, near infrared images and airborne laserscanning data. The presented research focused exclusively on the optical image, so the elevation information was ignored. The road detection procedure has been built up of two main phases: a segmentation done by neural networks and a compilation made by genetic algorithms. The applied neural networks were support vector machines with radial basis kernel function and self-organizing maps with hexagonal network topology and Euclidean distance function for neighborhood management. The neural techniques have been compared by hyperbox classifier, known from the statistical image classification practice. The compilation of the segmentation is realized by a novel application of the common genetic algorithm and by differential evolution technique. The genes were implemented to detect the road elements by evaluating a special binary fitness function. The results have proven that the evolutional technique can automatically find major road segments.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XXXIX-B3/247/2012/isprsarchives-XXXIX-B3-247-2012.pdf |
| spellingShingle | A. Barsi ROAD DETECTION BY NEURAL AND GENETIC ALGORITHM IN URBAN ENVIRONMENT The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | ROAD DETECTION BY NEURAL AND GENETIC ALGORITHM IN URBAN ENVIRONMENT |
| title_full | ROAD DETECTION BY NEURAL AND GENETIC ALGORITHM IN URBAN ENVIRONMENT |
| title_fullStr | ROAD DETECTION BY NEURAL AND GENETIC ALGORITHM IN URBAN ENVIRONMENT |
| title_full_unstemmed | ROAD DETECTION BY NEURAL AND GENETIC ALGORITHM IN URBAN ENVIRONMENT |
| title_short | ROAD DETECTION BY NEURAL AND GENETIC ALGORITHM IN URBAN ENVIRONMENT |
| title_sort | road detection by neural and genetic algorithm in urban environment |
| url | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XXXIX-B3/247/2012/isprsarchives-XXXIX-B3-247-2012.pdf |
| work_keys_str_mv | AT abarsi roaddetectionbyneuralandgeneticalgorithminurbanenvironment |