A Novel Approach for Classification and Recognition of Object Detection Methods for Autonomous Vehicles

Autonomous vehicles have been observed as a huge market prospect nowadays, especially with the emergence of cutting-edge technologies like edge computing, 5G communication, Blockchain, and deep learning. Despite rapid growth, this technology faces particular challenges in a few areas, Object detection plays a pivotal role in ensuring safety and fluid vehicular operation in the escalating field of autonomous driving. This paper presents a novel approach for classifying and recognizing diverse object detection methodologies in autonomous vehicles. In contrast to existing classification schemes based on traditional metrics and attributes, our proposed framework integrates machine learning techniques with a unique set of characteristics to categorize and recognize different object detection methods accurately and dynamically. In this paper, a hybrid approach of YoLo with Deep Learning algorithm has been adopted. In this paper, a methodology has been proposed to detect the object along with classification based on pattern of the object and the single class and multiclass objects were detected, and the experiment has been performed using the KITTI benchmark dataset with single object detection and Multiclass object detection, the accuracy is 80% for both single class and multi class object detection.