A Real-Time Deformable Detector

We propose a new learning strategy for object detection. The proposed scheme forgoes the need to train a collection of detectors dedicated to homogeneous families of poses, and instead learns a single classifier that has the inherent ability to deform based on the signal of interest. We train a dete...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2012-02, Vol.34 (2), p.225-239
Hauptverfasser:	Ali, K., Fleuret, F., Hasler, D., Fua, P.
Format:	Artikel
Sprache:	eng
Schlagworte:	Applied sciences Artificial intelligence Computer science control theory systems Data processing. List processing. Character string processing Deformation Detectors Exact sciences and technology False alarms Feature extraction Formability Image edge detection Image processing Image processing and computer vision Learning Learning systems Machine learning Memory organisation. Data processing Object detection Pattern recognition. Digital image processing. Computational geometry Software Studies Training Training data Trains
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!