Detecting vehicles using machine learning and computer vision

<p>In order to detect a car on the image, we need to identify&nbsp;<strong>feature(s)</strong>&nbsp;which uniquely represent a car. We could try using simple template matching or relaying on color features but these methods are not robust enough when it comes to changing perspectives and shapes of the object.</p> <p>In order to have a robust feature set and increase our accuracy rate we will be using&nbsp;<a href="https://en.wikipedia.org/wiki/Histogram_of_oriented_gradients" rel="noopener ugc nofollow" target="_blank">Histogram of Oriented Gradients</a>&nbsp;(HOG). This feature descriptor is much more resilient to the dynamics of the traffic. In essence, you should&nbsp;<strong>think of features as thumbprints</strong>&nbsp;of the objects you are interested in.</p> <p><a href="https://towardsdatascience.com/detecting-vehicles-using-machine-learning-and-computer-vision-e319ee149e10"><strong>Read More</strong></a></p>