Estimating the distance to an object from static color stereo images using convolutional neural networks

In issues such as autonomy of movement, the vital information is the vehicle's distance from the obstacle. The research presented is devoted to the phenomenon of disparity in color stereo images. Their goal was to estimate the distance to the obstacle. A convolutional neural network regression model was used as a research method. The data set is a proprietary set of color stereo static images. Testing the learned CNN model gave excellent results. The analysis of the obtained results showed that the developed solution could be used in engineering solutions such as supporting vehicle control.