http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-102609938-B
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_d6a6f422b091ba12ea61d4adbf1b0e8e |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00 |
filingDate | 2012-01-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2014-04-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9121ff166df3b268aac743588e29ee02 |
publicationDate | 2014-04-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-102609938-B |
titleOfInvention | Method for detecting vanishing points of road based on single image |
abstract | The invention discloses a method for detecting vanishing points of a road based on a single image. According to the characteristics that the gradient directions of pixels on a marking line or a vehicle trajectory of road in a road image are consistent and pixels on the surface of the road must have similar texture and color features, the vanishing points of the road in the image are detected by using a line segment based method. According to the invention, the advantages of an image edge based method and an image texture based method are integrated, a plurality of straight lines which exist in general road images and are uncorrelated with roads are removed by using a direction consistency concept in the image texture based method, and by using the characteristic that pixels on the surface of a road have similar texture and color features and the like, the detection accuracy of vanishing points of the road can be improved, and the computing complexity is low; therefore, the method can be applied to computer vision systems for real-time road monitoring, intelligent walking robots or automatic driving automobiles and the like. |
priorityDate | 2012-01-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Predicate | Subject |
---|---|
isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID4781 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419554059 |
Total number of triples: 13.