Prediction Performance of Support Vector Machines with Fused Data in Road Scene Analysis

Automatic video-based vehicle detection is one of the main research topics in Intelligent Transportation Systems (ITS) and is a key element for automatic traffic surveillance systems. Support Vector Machines (SVMs) have been increasingly applied to an automatic video-based vehicle detection and a road scene analysis because of their remarkable performance in prediction accuracy. The property of input data for learning on SVMs determines the predictive performance. It is important task to choose the best input vectors in order to improve the predictive performance. It is normal to use a single property of input vectors in the application of learning models. However, the composition of different input vectors may affect predictive performance and a new input vector will be created by combining two raw data. In this paper, two information sources of edge information and pixel gray value have been combined to detect vehicle in road scene images and see how the fused data affect the predictive performance in SVMs. The experimental results of this study show that the fused data may provide better performance in predictive accuracy than a raw input data. Moreover, the results show that SVMs could provide much better performance than the Backpropagation model which is the best known neural network.

[1]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[2]  Tipu Z. Aziz,et al.  Parkinson's Disease tremor classification - A comparison between Support Vector Machines and neural networks , 2012, Expert Syst. Appl..

[3]  Yuanyuan Zhang,et al.  Structural damage detection based on semi-supervised fuzzy C-means clustering , 2014, 2014 9th International Conference on Computer Science & Education.

[4]  Seung-Jae Lee,et al.  Input Vector Normalization Methods in Support Vector Machines for Automatic Incident Detection , 2007 .

[5]  John D. Leonard,et al.  Vehicle Detection Using Video Image Processing System: Evaluation of PEEK VideoTrak , 2003 .

[6]  Majid Mirmehdi,et al.  Real-Time Detection and Recognition of Road Traffic Signs , 2012, IEEE Transactions on Intelligent Transportation Systems.

[7]  Daehyon Kim,et al.  Prediction performance of support vector machines on input vector normalization methods , 2004, Int. J. Comput. Math..

[8]  Bernhard Schölkopf,et al.  Incorporating Invariances in Support Vector Learning Machines , 1996, ICANN.

[9]  Lawrence A. Klein,et al.  Sensor and Data Fusion: A Tool for Information Assessment and Decision Making , 2004 .

[10]  Kazuhiro Hotta.  Robust face recognition under partial occlusion based on support vector machine with local Gaussian summation kernel , 2008, Image Vis. Comput..

[11]  Hong Qiao,et al.  A Low-Cost Pedestrian Detection System with a Single Optical Camera , 2006, 2006 6th World Congress on Intelligent Control and Automation.

[12]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[13]  Louis Vuurpijl,et al.  Support vector machines for the classification of western handwritten capitals , 2004 .

[14]  Federico Castanedo,et al.  A Review of Data Fusion Techniques , 2013, TheScientificWorldJournal.

[15]  Chia-Feng Juang,et al.  Object detection by color histogram-based fuzzy classifier with support vector learning , 2009, Neurocomputing.

[16]  Kyung-Joong Kim,et al.  Design of a visual perception model with edge-adaptive Gabor filter and support vector machine for traffic sign detection , 2013, Expert Syst. Appl..

[17]  Dino Isa,et al.  A hybrid text classification approach with low dependency on parameter by integrating K-nearest neighbor and support vector machine , 2012, Expert Syst. Appl..

[18]  Kannan Balakrishnan,et al.  Unconstrained Handwritten Malayalam Character Recognition using Wavelet Transform and Support vector Machine Classifier , 2012 .

[19]  Daehyon Kim,et al.  Pre-processing of inputs to a neural network model for better performance in traffic scene analysis , 2010 .

[20]  Jian-xiong Dong,et al.  An improved handwritten Chinese character recognition system using support vector machine , 2005, Pattern Recognit. Lett..

[21]  Bernhard Schölkopf,et al.  Extracting Support Data for a Given Task , 1995, KDD.

[22]  Kuo-Chin Fan,et al.  Vehicle Detection Using Normalized Color and Edge Map , 2007, IEEE Transactions on Image Processing.

[23]  Edward Jones,et al.  Vision-based detection and tracking of vehicles to the rear with perspective correction in low-light conditions , 2011 .