During this presentation we are going to build a Java Application for the purpose of detecting cars, pedestrian and traffic lights which are the key components in today's Autonomous Driving. Although for long time Machine Learning has been known as a "Phd field" , actually one may be surprised how shallow the deep learning can be. So at first we are going to explore some of the basics foundations of Computer Vision and Deep Learning, We will walk through the object localization and detection challenges and than gradually present the high level solutions in the new Era of Deep Learning and AI. Additionally will be introduced some state of the art techniques and deep learning neural architectures in order to solve detection object problem in real time even in CPU.