An Adaptive Threshold Segmentation Method in Dynamic Environment

Abstract

The invention discloses an adaptive threshold segmentation method in a dynamic environment. The adaptive threshold segmentation method comprises the steps of acquiring a first image frame of an object as a prior image, extracting the central point of the first image frame and the pre-estimated identification range to a next image frame; performing threshold segmentation on the current image according to the central point and the pre-estimated identification range, computing the central point and the identification range on a segmented pixel, and using the central point and the identification range in object identification of the next image frame; determining the central point and the identification range according to the identification condition of the object by HSV and YCbCr color space, and performing updating or restoring operation on the central point according to a determining result. The adaptive threshold segmentation method can realize highest threshold segmentation result through a smallest threshold segmentation range and can effectively eliminate noise influence, and furthermore adaptive change along with environment can be realized.

Description

technical field [0001] The invention relates to the fields of image processing and pattern recognition, in particular to an adaptive threshold segmentation method in a dynamic environment. Background technique [0002] How to extract the object we are interested in from an image has always been an enduring topic in image processing. The earliest research and the most widely used image segmentation technology is the image segmentation technology, which is A classic problem in the field of image processing and analysis is also one of the difficulties in this field. Image segmentation is actually a division problem. According to specific division criteria, the pixels in the image are filtered and divided. The result of the division is usually to distinguish the background from the extract, or to highlight the extract, or to eliminate noise. Through division, the Images are grouped into meaningful regions, and we can extract our objects of interest. In the field of image segme...

AI Technical Summary

Problems solved by technology

[0003] Classic image segmentation methods such as Otsu (inter-class variance method), maximum entropy, basic global thresholding method, iterative thresholding segmentation method and various adaptive thresholding methods are all single-channel segmentation methods based on grayscale images. The segmentation effect is good when the background difference is large and the noise is low, but if the image contains multiple gray intensities or the threshold points of some areas exceed the segmentation threshold, then these methods will have incomplete segmentation or segmentation confusion.

Images