Title :
Traffic sign classification using K-d trees and Random Forests
Author :
Zaklouta, Fatin ; Stanciulescu, Bogdan ; Hamdoun, Omar
Author_Institution :
Robot. Center, Mines ParisTech, Paris, France
fDate :
July 31 2011-Aug. 5 2011
Abstract :
In this paper, we evaluate the performance of K-d trees and Random Forests for traffic sign classification using different size Histogram of Oriented Gradients (HOG) descriptors and Distance Transforms. We use the German Traffic Sign Benchmark data set [1] containing 43 classes and more than 50,000 images. The K-d tree is fast to build and search in. We combine the tree classifiers with the HOG descriptors as well as the Distance Transforms and achieve classification rates of up to 97% and 81.8% respectively.
Keywords :
gradient methods; pattern classification; random processes; traffic engineering computing; transforms; tree data structures; German traffic sign benchmark; HOG descriptor; K-d tree; classification rate; distance transform; histogram of oriented gradients; random forest; traffic sign classification; tree classifier; Histograms; Image color analysis; Image edge detection; Support vector machines; Training; Transforms; Vegetation;
Conference_Titel :
Neural Networks (IJCNN), The 2011 International Joint Conference on
Conference_Location :
San Jose, CA
Print_ISBN :
978-1-4244-9635-8
DOI :
10.1109/IJCNN.2011.6033494
