Method for enhancing object contour of image in real-time video

A method for enhancing a contour of an object in a real-time video image, comprising the following steps:

• S1 :
• acquiring a captured video, and dividing a next frame of image in the video into a plurality of image blocks;
• S2:
• subjecting each pixel in each of the plurality of image blocks to contour enhancement based on a gradient algorithm;
• S3:
• subjecting the plurality of contour-enhanced image blocks as a whole to noise filtering by using a Gaussian filtering method to obtain an entire noise-filtered image;
• and
• S4:
• subjecting the entire noise-filtered image to contrast processing based on a gamma transformation to obtain a final enhanced image;
• wherein step S2 comprises:
• S2.1:
• performing gradient calculation on a brightness component of each pixel of each of the plurality of image blocks based on an improved gradient calculation formula to obtain a gradient value of each pixel;
• and
• S2.2:
• determining whether each gradient value is greater than a set threshold;
• if yes, determining that the pixel is at an edge, and determining whether to set the pixel at a white edge or a black edge according to a negative of the gradient value;
• and if not, not processing;
• wherein in step S2.1, the improved gradient calculation formula is:
• I=ΣiΣj((Y1−Y2)/(Y1+Y2))
• wherein, Y1 and Y2 are brightness of two adjacent pixels;
• i and j are an abscissa and an ordinate of a pixel, respectively;
• and I is a calculated gradient value.