Research on Target Detection Method Based on Ground Target

Conference: ICMLCA 2021 - 2nd International Conference on Machine Learning and Computer Application
12/17/2021 - 12/19/2021 at Shenyang, China

Proceedings: ICMLCA 2021

Pages: 4Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Authors:
Feng, Yunrui; Zhang, Le; Wang, Yan (Equipment Engineering Department, Shenyang Ligong University, Shenyang, China)

Abstract:
In this paper, the detection and tracking of moving objects are studied in view of the motion position and centroid information acquisition of ground moving objects. Background difference method is the main method of target segmentation. The background modeling optimization algorithm based on the fusion of background difference method and frame difference method is proposed, which solves the problem of incomplete target detection and background illumination change, improves the detection quality, and lays the foundation for subsequent tracking work. Simulation results show that the optimization algorithm can meet the accuracy and real-time requirements of target tracking, and accurately identify the geometric center and contour coordinates of the target.