Intelligent Object Recognition System for Autonomous and Semi-Autonomous Vehicles

Abstract

Road accidents have long been a significant issue involving loss of life and property. So recent years have seen rapid developments in autonomous and semi-autonomous vehicles. Autonomous vehicles are a comprehensive solution built for safety and comfort on the roads. This solution has many challenges. One of these challenges is to spot and recognize obstacles. As humans do, the only way to discover and recognize these obstacles is to see them. Therefore, vision systems are an essential part of this type of vehicle. This paper proposed a vision-based approach for autonomous vehicles to recognize objects and traffic lights on the road. The proposed system contains three phases: image pre-processing, feature extraction, and classification. In the first phase, some image pre-processing techniques are applied, which consists of three stages: Convert Color images to Grayscale, Histogram Equalization, and Resize Image. The second phase is the extraction of features from images using Principal Component Analysis (PCA). In the third phase, the features that are extracted are used as input to machine learning (ML) classifiers for object recognition. ML algorithms used in this proposed system are Random Forest (RF), Random Tree (RT), and Naive Bayes (NB). The results show that the RF algorithm has the highest classification precision rate, 75%, compared to the NB algorithm 63% and the RT algorithm 53%.