Pedestrian detection from still images

Pedestrian detection from still images

In this work, a pedestrian detection method based on adaptive boosting is proposed. The proposed method works on still images. The features utilized in the work are derived from Haar-like templates. An Adaboost classifier is utilized for both feature selection and classification. To show the effecti...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tetik, Y. E., Bolat, B.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Adaboost
Classification algorithms
Computer vision
Conferences
Feature extraction
Haar-like features
Leg
pedestrian detection
Pixel
rectangular features
Training
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this work, a pedestrian detection method based on adaptive boosting is proposed. The proposed method works on still images. The features utilized in the work are derived from Haar-like templates. An Adaboost classifier is utilized for both feature selection and classification. To show the effectiveness of the proposed algorithm, the system is trained by using Nicta Pedestrian Dataset and tested by using Penn Fudan Pedestrian Dataset. The experimental result shows the proposed method's effectiveness.
DOI:10.1109/INISTA.2011.5946164