Personnel trajectory tracking method

The invention relates to a personnel trajectory tracking method. The method comprises the following steps: S1, performing histogram equalization on each frame of a video of a water pump room worker; s2, inputting the image processed in the step S1 into a Yolov5 model for detection to obtain a target...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: SHANG YUHAO, XU XIN, SUN HAILONG, ZHANG LIANYUAN, ZHANG YUECHAO, XIE HAIFENG, WANG YUXUAN, PEI WENLIANG, ZHANG XUHUA, ZHENG ZIDONG, MA XINGANG, GUO YONGTAO, LI JUNWEI
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention relates to a personnel trajectory tracking method. The method comprises the following steps: S1, performing histogram equalization on each frame of a video of a water pump room worker; s2, inputting the image processed in the step S1 into a Yolov5 model for detection to obtain a target frame; s3, obtaining a motion track of the worker through a track identification model; and S4, judging whether the central point of the target frame in each frame falls in a preset key area of the water pump house or not, and recording. According to the method, image preprocessing and deep learning algorithms are adopted, the accuracy is high, the application scene is wide, and the incompleteness caused by only manual feature design is reduced; the method is not interfered by complex backgrounds, and is high in robustness and portability. 本发明涉及一种人员轨迹追踪方法,包括如下步骤S1将水泵房工作人员的视频每一帧进行直方图均衡化;S2将经过步骤S1处理后的图像输入Yolov5模型进行检测,获得目标框;S3通过轨迹识别模型中得到工作人员的运动轨迹;S4判断每一帧中目标框的中心点是否落在预先设定好的水泵房关键区域并记录。本发明采用图像预处理,深度学习算法,精确度高,适用场景广,减少了仅仅人