Research on Edge Curve Processing for Human Upper Limb Motion Image

Konferenz: ICMLCA 2021 - 2nd International Conference on Machine Learning and Computer Application
17.12.2021 - 19.12.2021 in Shenyang, China

Tagungsband: ICMLCA 2021

Seiten: 5Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Autoren:
Qin, Lijuan; Ma, Zeqi (School of Information Science and Engineering, Shenyang Ligong University, Shenyang, China)

Inhalt:
Video-based human upper limb motion image analysis technology has extremely broad application prospects in many fields. To realize the analysis and recognition of human motion, it is necessary to calculate the edge curve of moving limbs. This paper summarizes a set of methods for organizing edge points, and expounds the process of filling edge curve fault zone by curve connection method. Finally, combining the edge point organization with fault zone filling, an edge point integration algorithm is proposed to complete the edge point processing. It can be seen from the experimental results that the background noise is filtered out, the pseudo edges of clothes folds are reduced, and the breakpoints of limb edges are filled. After processing the outer edge map of the human arm, a connected outer contour curve is obtained, which can provide a good basis for the later recognition and analysis of motion.