Multiple Objects Identification for Autonomous Car using YOLO and CNN

One of the most anticipated 21$^{st}$-century technologies and one of the subjects of the current study that is gaining significant research attention is autonomous driving. By detecting and responding to the vehicle’s immediate environment, autonomous driving tries to navigate roads without human assistance. It presents significant difficulties for computer vision and machine learning. Processing several candidate object locations, which are frequently referred to as “proposals,” is one difficulty. These choices only offer basic localization, which needs to be refined in order to obtain precise localization. However, solutions to these issues frequently come at the expense of efficiency, precision, or simplicity. R-CNN first introduced in 2013, and their upgraded versions Fast R-CNN and Faster R-CNN are recent examples of cutting-edge deep learning models that tackle the issue of object detection. YOLO, a paradigm for object detection created for speed and real-time use, was released in 2015.