TY - GEN
T1 - Counting pedestrians and bicycles in traffic scenes
AU - Somasundaram, Guruprasad
AU - Morellas, Vassilios
AU - Papanikolopoulos, Nikolaos P
PY - 2009
Y1 - 2009
N2 - Object detection and classification have received increased attention recently from computer vision and image processing researchers. Image processing views this problem at a much lower level as compared to machine learning and linear algebraic analysis which focus on the overall statistics of object classes given sufficient data. A good algorithm uses both these approaches to its advantage. It is important to define and choose the features of an image suitably, so that the classification algorithm can perform at its best in distinguishing object classes. In this paper we investigate the performance of different types of texture-based features when used with a support vector machine. Their performance was evaluated on standardized image datasets and compared. The objective of this study was to come up with a suitable algorithm to distinguish bicycles from pedestrians in locations such as bicycle paths and trails in order to estimate their traffic. The models developed during this study were applied in practice to traffic videos and the results are summarized here. For better application in practice other cues derived from motion were utilized to improve the performance of the classification and hence the accuracy of the counts.
AB - Object detection and classification have received increased attention recently from computer vision and image processing researchers. Image processing views this problem at a much lower level as compared to machine learning and linear algebraic analysis which focus on the overall statistics of object classes given sufficient data. A good algorithm uses both these approaches to its advantage. It is important to define and choose the features of an image suitably, so that the classification algorithm can perform at its best in distinguishing object classes. In this paper we investigate the performance of different types of texture-based features when used with a support vector machine. Their performance was evaluated on standardized image datasets and compared. The objective of this study was to come up with a suitable algorithm to distinguish bicycles from pedestrians in locations such as bicycle paths and trails in order to estimate their traffic. The models developed during this study were applied in practice to traffic videos and the results are summarized here. For better application in practice other cues derived from motion were utilized to improve the performance of the classification and hence the accuracy of the counts.
UR - http://www.scopus.com/inward/record.url?scp=72449130977&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=72449130977&partnerID=8YFLogxK
U2 - 10.1109/ITSC.2009.5309690
DO - 10.1109/ITSC.2009.5309690
M3 - Conference contribution
AN - SCOPUS:72449130977
SN - 9781424455218
T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
SP - 299
EP - 304
BT - 2009 12th International IEEE Conference on Intelligent Transportation Systems, ITSC '09
T2 - 2009 12th International IEEE Conference on Intelligent Transportation Systems, ITSC '09
Y2 - 3 October 2009 through 7 October 2009
ER -