A Pedestrian Detection Method Based on Genetic Algorithm for Optimize XGBoost Training Parameters

Abstract

In this paper, we present a machine learning classifier which is used for pedestrian detection based on XGBoost. Our approach, the Genetic Algorithm is introduced to optimize the parameter tuning process during training an XGBoost model. In order to improve the classification accuracy, HOG and LBP features are used to describe pedestrians in a way of tandem fusion, then input into GA-XGBoost classifier proposed in this paper to form a new static image pedestrian detection algorithm. The pedestrian feature extraction and machine learning are decoupled by storing the extracted pedestrian feature as feature files in the experiment, so that training can be exacuted many times and algorithms can be camparied conveniently. Experimental show that our pedestrian detection algorithm has improved the accuracy of pedestrian detection in the static image. The Area Under the ROC Curve (AUC) value reaches 0.9913.

Keywords

• Pedestrain detection
• histogram of oriented gradient features (HOG)
• local binary patterns (LBP) XGBoost classifier
• genetic algorithm