Object Classification Using A rtificial I ntelligence Technique s i n Autonomous Vehicles

Abstract

Autonomous or self-driving vehicles are self- decision systems that must choose their next course of action when an object or other vehicle is spotted on the road. Smooth driving is crucial for self-driving cars to avoid causing other road users to become stranded in a traffic jam. For autonomous vehicles, understanding traffic objects is crucial. The self-driving automobile can perform the required action after identifying an object’s precise class. Self-driving cars should be extra cautious when passing big vehicles like buses or trucks if they are identified. Consequently, one of the key capabilities of self-driving automobiles is object identification. Computer vision tasks like object classification can be useful for object recognition. Deep learning is a key subfield of machine learning and crucial for a number of computer vision applications such object detection, localization, and classification. In this paper, we present a model for real-time object classification using the Convolutional Neural Network (CNN) of AI approach. It includes a thorough discussion of various deep learning techniques for classifying objects in RGB pictures and LiDAR point clouds.