Academic Journals Database
Disseminating quality controlled scientific knowledge

Front and Rear Vehicle Detection Using Hypothesis Generation and Verification

Author(s): Nima Khairdoost | S. Amirhassan Monadjemi | Kamal Jamshidi

Journal: Signal & Image Processing
ISSN 2229-3922

Volume: 4;
Issue: 4;
Start page: 31;
Date: 2013;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Vehicle Detection | Hypothesis Generation | Hypothesis Verification | PHOG | PCA | GA | Linear SVM | Feature Weighting

Vehicle detection in traffic scenes is an important issue in driver assistance systems and self-guidedvehicles that includes two stages of Hypothesis Generation (HG) and Hypothesis Verification (HV). Theboth stages are important and challenging. In the first stage, potential vehicles are hypothesized and in thesecond stage, all hypotheses are verified and classified into vehicle and non-vehicle classes. In this paper,we present a method for detecting front and rear on-road vehicles without lane information and priorknowledge about the position of the road. In the HG stage, a three-step method including shadow, textureand symmetry clues is applied. In the HV stage, we extract Pyramid Histograms of Oriented Gradients(PHOG) features from a traffic image as basic features to detect vehicles. Principle Component Analysis(PCA) is applied to these PHOG feature vectors as a dimension reduction tool to obtain the PHOG-PCAvectors. Then, we use Genetic Algorithm (GA) and linear Support Vector Machine (SVM) to improve theperformance and generalization of the PHOG-PCA features. Experimental results of the proposed HVstage showed good classification accuracy of more than 97% correct classification on realistic on-roadvehicle dataset images and also it has better classification accuracy in comparison with other approaches.

Tango Rapperswil
Tango Rapperswil

RPA Switzerland

RPA Switzerland

Robotic process automation