牡丹江师范学院学报（自然科学版）Issue(2)：57-63,7.
基于逆光图像校正的竞技体操连接加分动作分割方法
A Segmentation Method for Combined Bonus Actions in Competitive Gymnastics based on Backlit Image Correction
摘要
Abstract
A competitive gymnastics connection bonus action segmentation method based on backlight image cor-rection(Backlight Image Correction Method)is proposed to compensate for local overexposure and underexposure caused by backlight,thereby improving the accuracy of action segmentation.This method corrects the dark and bright areas of backlight images and utilizes a multi-scale fusion pyramid to fuse these bright and dark regions.It employs Gaussian Mixture Model(GMM)background modeling to process the corrected images,obtaining a back-ground model,and combines it with an improved ViBe algorithm for action segmentation.Experimental results dem-onstrate that this method can enhance the image information entropy and average gradient,effectively segment con-nection bonus actions,and achieve high boundary smoothness in action segmentation under different light intensi-ties,providing theoretical support for the automation and scientific assessment of competitive gymnastics scoring.关键词
逆光图像校正/竞技体操/加分动作/分割方法/二次光照/ViBe算法Key words
backlight image correction/competitive gymnastics/bonus action/segmentation method/secondary il-lumination/ViBe Algorithm分类
信息技术与安全科学引用本文复制引用
郑忠文,徐志洋..基于逆光图像校正的竞技体操连接加分动作分割方法[J].牡丹江师范学院学报（自然科学版）,2026,(2):57-63,7.基金项目
2020年度安徽省哲学社会科学规划一般项目(AHSKY2020D79) （AHSKY2020D79）
2021年度阜阳市人文社会科学研究专项项目(FYSK2021LH07) （FYSK2021LH07）
