Abstract
Vehicle detection is an important issue in driver assistance systems and self-guided vehicles that includes two stages of hypothesis generation and verification. In the first stage, potential vehicles are hypothesized and in the second stage, all hypothesis are verified. The focus of this work is to classify vehicle candidate images into vehicle and non-vehicle classes. We extract Pyramid Histograms of Oriented Gradients (PHOG) features from a traffic image as candidates of feature vectors to detect vehicles. Principle Component Analysis (PCA) is applied to these PHOG feature vectors as a dimension reduction tool to obtain the PHOG- PCA vectors. Then we employ real coded chromosome Genetic Algorithm (GA) and linear Support Vector Machine (SVM) to classify the PHOG-PCA features as well as to improve their performance and generalization. Our tests show good classification accuracy of more than 96% correct classification on realistic on-road vehicle images.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have