Approach to Detecting Pedestrian Movement Using the Method of Histograms of Oriented Gradients

An approach to automatically recognizing the movement of people at a pedestrian crossing is presented in this article. This approach includes two main procedures, for each of which commands are given in the C# programming language using the EMGU computer vision library. In the first procedure, pedestrian detection is performed using the combination of a directional gradient histogram and support vector methods. The second procedure allows you to read frames from a video sequence and process them. This approach allows for the detection of the movements of people at a pedestrian crossing without using specialized neural networks. At the same time, the method proposed in this article had sufficient reliability in terms of human movement recognition, which indicates its applicability to real conditions.