Comparison of object recognition algorithms

Despite the increasing popularity of process automation, modern video surveillance systems still require constant human involvement to establish the fact of dangerous situations. But at present, systems are becoming more complex, this leads to an increase in threats and it is no longer possible for the operator to keep track of all emerging threats. In addition, in the field of video surveillance, tasks have been added that a person can no longer control just by watching video cameras [1; 2]. In this connection, you need to automate the process. Methods that provide maximum detection stability for small object movements, zoom changes, turning the object at a small angle, and changing lighting are based on describing the image at specific points. A special point is a point that has a number of key features that distinguish it from many other points in the image. Special points are the main characteristics of the object in the video surveillance system. The best object recognition algorithms based on this principle are the SURF and SIFT algorithms. These algorithms search for the direct occurrence of the reference image in relation to the observed one. The article discusses algorithms for detecting objects in an image based on the description of the image by special points. Acomparison of SIFT and SURF algorithms, the analysis highlighted particular points in the recognition of each object, error analysis AI Node in identifying objects in the video stream.