ResearchSpace

Comparison of canny and V1 neural network based edge detectors applied to road extraction

Show simple item record

dc.contributor.author Hauptfleisch, AC
dc.contributor.author Van Den Bergh, F
dc.contributor.author Bachoo, AK
dc.contributor.author Engelbrecht, AP
dc.date.accessioned 2007-07-27T10:57:00Z
dc.date.available 2007-07-27T10:57:00Z
dc.date.issued 2006-11
dc.identifier.citation Hauptfleisch, AC et al. 2006. Comparison of canny and V1 neural network based edge detectors applied to road extraction. 17th Annual Symposium of the Pattern Recognition Association of South Africa, Parys, South Africa, 29 Nov - 1 Dec 2006, pp 6 en
dc.identifier.isbn 9780620373845
dc.identifier.isbn 0620373849
dc.identifier.uri http://hdl.handle.net/10204/1047
dc.description.abstract The Anti-parallel edge Centerline Extractor (ACE) algorithm is designed to extract road networks from high resolution satellite images. The primary mechanism used by the algorithm to detect the presence of roads is a filter that detects parallel edges with a specified distance between them. The success of the ACE algorithm thus depends critically on the quality of the edges that are extracted early on in the algorithm, typically using Canny’s edge detector. This paper investigates the viability of an ACE variant that uses a different edge detector, modelled on the primary visual cortex (V1). Considering the experimental evidence, it seems unlikely that the V1-based algorithm is able to produce better results than the original Canny-based algorithm en
dc.language.iso en en
dc.subject Anti-parallel edge centerline extractor en
dc.subject Visual cortex en
dc.subject Edge detector en
dc.subject ZASAT-002 en
dc.subject Self-organizing road map en
dc.title Comparison of canny and V1 neural network based edge detectors applied to road extraction en
dc.type Conference Presentation en
dc.identifier.apacitation Hauptfleisch, A., Van Den Bergh, F., Bachoo, A., & Engelbrecht, A. (2006). Comparison of canny and V1 neural network based edge detectors applied to road extraction. http://hdl.handle.net/10204/1047 en_ZA
dc.identifier.chicagocitation Hauptfleisch, AC, F Van Den Bergh, AK Bachoo, and AP Engelbrecht. "Comparison of canny and V1 neural network based edge detectors applied to road extraction." (2006): http://hdl.handle.net/10204/1047 en_ZA
dc.identifier.vancouvercitation Hauptfleisch A, Van Den Bergh F, Bachoo A, Engelbrecht A, Comparison of canny and V1 neural network based edge detectors applied to road extraction; 2006. http://hdl.handle.net/10204/1047 . en_ZA
dc.identifier.ris TY - Conference Presentation AU - Hauptfleisch, AC AU - Van Den Bergh, F AU - Bachoo, AK AU - Engelbrecht, AP AB - The Anti-parallel edge Centerline Extractor (ACE) algorithm is designed to extract road networks from high resolution satellite images. The primary mechanism used by the algorithm to detect the presence of roads is a filter that detects parallel edges with a specified distance between them. The success of the ACE algorithm thus depends critically on the quality of the edges that are extracted early on in the algorithm, typically using Canny’s edge detector. This paper investigates the viability of an ACE variant that uses a different edge detector, modelled on the primary visual cortex (V1). Considering the experimental evidence, it seems unlikely that the V1-based algorithm is able to produce better results than the original Canny-based algorithm DA - 2006-11 DB - ResearchSpace DP - CSIR KW - Anti-parallel edge centerline extractor KW - Visual cortex KW - Edge detector KW - ZASAT-002 KW - Self-organizing road map LK - https://researchspace.csir.co.za PY - 2006 SM - 9780620373845 SM - 0620373849 T1 - Comparison of canny and V1 neural network based edge detectors applied to road extraction TI - Comparison of canny and V1 neural network based edge detectors applied to road extraction UR - http://hdl.handle.net/10204/1047 ER - en_ZA


Files in this item

Thumbnail
Name: Hauptfleisch_2006.pdf
Size: 470.0Kb
Format: PDF
View/Open

This item appears in the following Collection(s)

Show simple item record