Pedestrian Detection with Unsupervised Multi-stage Feature Learning

Pedestrian detection is a problem of considerable practical interest. Adding to the list of successful applications of deep learning methods to vision, we report state-of-the-art and competitive results on all major pedestrian datasets with a convolutional network model. The model uses a few new twi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2013 IEEE Conference on Computer Vision and Pattern Recognition S. 3626 - 3633
Hauptverfasser: Sermanet, Pierre, Kavukcuoglu, Koray, Chintala, Soumith, Lecun, Yann
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2013
Schlagworte:
computer vision
convolutional
Convolutional codes
deep learning
detection
Encoding
Equations
Feature extraction
Mathematical model
pedestrian
Training
unsupervised
Unsupervised learning
ISSN:1063-6919, 1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Pedestrian detection is a problem of considerable practical interest. Adding to the list of successful applications of deep learning methods to vision, we report state-of-the-art and competitive results on all major pedestrian datasets with a convolutional network model. The model uses a few new twists, such as multi-stage features, connections that skip layers to integrate global shape information with local distinctive motif information, and an unsupervised method based on convolutional sparse coding to pre-train the filters at each stage.
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2013.465