End-to-End Gaze Estimation Method for Surveillance Camera Images | Zendy

Keiji Uemura | Zendy; Kiyoshi Kiyokawa | Zendy; Nobuchika Sakata | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

End-to-End Gaze Estimation Method for Surveillance Camera Images

Author(s) -

Keiji Uemura,

Kiyoshi Kiyokawa,

Nobuchika Sakata

Publication year - 2025

Publication title -

ieee access

Language(s) - English

Resource type - Magazines

SCImago Journal Rank - 0.587

H-Index - 127

eISSN - 2169-3536

DOI - 10.1109/access.2025.3621428

Subject(s) - aerospace , bioengineering , communication, networking and broadcast technologies , components, circuits, devices and systems , computing and processing , engineered materials, dielectrics and plasmas , engineering profession , fields, waves and electromagnetics , general topics for engineers , geoscience , nuclear engineering , photonics and electrooptics , power, energy and industry applications , robotics and control systems , signal processing and analysis , transportation

Gaze estimation technology has been widely used in the field of computer vision in recent years. It has been utilized in various fields, such as automotive systems, human-computer interaction and augmented reality (AR) / virtual reality (VR). In these applications, the target of gaze estimation is apparent, and sensors and cameras are placed at close distances to ensure precise gaze estimation. Conversely, applications such as measuring attention in advertisements have emerged, by utilizing gaze direction obtained from the increasing number of surveillance cameras in urban areas and public spaces. These surveillance cameras are not primarily intended for capturing individuals’ faces for gaze detection. Furthermore, potential obstructions, which may obscure individuals, create challenges that differ from the typical environments considered for gaze estimation. In this paper, we propose a method to estimate the gaze direction of a person with high accuracy, even in images taken by such surveillance cameras. We also compare and evaluate the proposed method using an existing dataset of surveillance camera images.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research