NEW IMAGE PRE-PROCESSING METHODS FOR TRACKING VARIOUS BIOLOGICAL OBJECTS MOVEMENT

Abstract

The algorithms to tracking of movement dynamics of various biological objects now it is actually to studying. Features and characteristic of objects, conditions of their visualization strongly influence the choice of optimal methods and algorithms for a specific task it they tracking. Therefore, to automate the processes of adaptation of recognition-tracking algorithms, several Labview project trackers are considered in the article. Specificity of these objects, conditions of their visualization and model parameters strongly influence the choice of methods and algorithms, which are optimal for a specific task. Therefore, in this article, in order to automate the processes of adaptation algorithms of recognition - tracking, we suggest several frames pre-processing algorithms using NI Labview tools and Vision Assistant. Preprocessing included equalization of general background luminance of the image, elimination of high-frequency noise and different artifacts (highlighted areas, gaps, fractures, etc.) from the original image, contrasting, thresholding, binarization and other functional transformations. Projects allow changing templates for training and retraining the system quickly. They adapt to the speed of objects and statistical characteristics of noise in images. New pre-processing methods image for algorithms tracking of movement dynamics of various biological objects will be discussed. The experiments carried out to test the trackers on real video files will be presented and analyzed.