Abstract | ||
---|---|---|
Research on pedestrian detection system still presents a lot of space for improvements, both on speed and detection accuracy. This paper presents a full implementation of a pedestrian detection system, using a part-based classification for the candidates identification and a feature based tracking for increasing the result robustness. The novelty of this approach relies on the use of part-based approach with a combination of Haar-cascade and HOG-SVM. Tests have been conducted using standard datasets showing results aligned with those of the other state-of-the-art systems available in literature. Real world tests also show high speed performance. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/IVS.2013.6629662 | Intelligent Vehicles Symposium |
Keywords | Field | DocType |
Haar transforms,feature extraction,image classification,pedestrians,support vector machines,HOG-SVM,Haar-cascade,candidates identification,feature based tracking,high performance pedestrian detection design,high performance pedestrian detection implementation,histogram of oriented gradients,part-based classification,pedestrian detection system,support vector machines | Computer vision,Pattern recognition,Feature (computer vision),Support vector machine,Feature extraction,Robustness (computer science),Artificial intelligence,Engineering,Novelty,Feature based,Contextual image classification,Pedestrian detection | Conference |
ISSN | ISBN | Citations |
1931-0587 | 978-1-4673-2754-1 | 2 |
PageRank | References | Authors |
0.37 | 15 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
antonio prioletti | 1 | 34 | 2.55 |
Paolo Grisleri | 2 | 214 | 17.99 |
Mohan M. Trivedi | 3 | 6564 | 475.50 |
Alberto Broggi | 4 | 1527 | 178.28 |