Re-identification of people in a video stream based on a Kalman filter

2024

Full text Open access: Green Metadata (CSL-JSON)
DOI 10.1117/12.3058549
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

This article illustrates the application of the Kalman filter in real-time human re-identification tasks to improve accuracy, reliability, and reduce computational costs while determining a person's position and orientation. The use of the Kalman filter addresses noise filtering and prediction issues in human re-identification tasks.