Pothole and Object Detection for an Autonomous Vehicle Using YOLO

Object Detection is an key software and a fundamental task for an autonomous driving system that provides remarkable change in computer vision. İn recent years, company's are planning to launch autonomous vehicle in an full swing that's the most important ascpets for object detection and one of most challenging task for locating specific object from from multiple objects in a specific scenario. The computer vision and machine learning algorithm is the important tool for detecting objects in and around the environment. In this paper, which consists of two parts The first part is implemented on object detection in the surrounding with Yolo (You Only Look Once)Algorithm provides exact classification and position which is configured on newly created datasets for classes of object: a car, a person, a truck, a bus, traffic light, motorcycle, pothole, wetland uses the Convolutional Neural Network and max-polling layer for prediction that improves detecting of small target and these deep learning technique provides a high accuracy for detecting real world. Detecting potholes in Indian road help the autonomous vehicle to move smoothly without getting struck in the potholes. In part two of the proposed method is implemented on Raspberry pi4 a popular embedded computer board explores suitability for the running objects. That solves the real world problems and improves the impact on detecting objects. Knowing pothole and wetland detection for self-driving vehicle is needed badly to solve the road lay problems like: accident, slowing down the transport system these are solved by deep learning.