When subject vehicle look at the images or videos, it can easily identify and locate the objects of its interest within moments, thereby helping the subject vehicle make decisions and travel behavior on the road. We just focus on the YOLOv5 algorithm, which is a single deep Convolution Neural Networks for detecting, identifying, classifying the object. YOLO is made from combination between convolutional layers and connected layers. YOLO can split the input image into a set of grid cells, unlike image classification or face detection, grid cell in YOLO algorithm will have an associated vector in the output that tells us if an object exists in that grid cell, the class of that object, the predicted bounding box for that object. Video test results show the effectiveness of using the proposed algorithm.