Title :
People detection in cluttered scenes
Author :
Öztürk, Serdar ; Sankur, Bülent ; Akgül, Ceyhun B.
Abstract :
In this paper, we present a people finding algorithm in cluttered scenes using Histogram of Oriented Gradients (HOG) approach. The people search operation in an image is performed by sliding a detection window and converting the content of each window to a HOG feature vector. HOG feature vectors are obtained from windows with humans and not containing any human (negative samples), and used to train a linear SVM classifier. The performance of the algorithm is measured using different parameters and configurations, and the results are presented with Precision-Recall plots.
Keywords :
clutter; image classification; object detection; support vector machines; cluttered scenes; detection window; feature vector; histogram of oriented gradients; linear SVM classifier; people detection; people finding algorithm; people search operation; precision recall plots; sliding window; Conferences; Feature extraction; Histograms; Humans; IEEE Computer Society; Pattern recognition; Vectors;
Conference_Titel :
Signal Processing and Communications Applications Conference (SIU), 2010 IEEE 18th
Conference_Location :
Diyarbakir
Print_ISBN :
978-1-4244-9672-3
DOI :
10.1109/SIU.2010.5652714
