Face image acquisition method and vehicle

By adjusting the light transmittance of the dimming glass and determining the projection area of ​​the face correction sub-region based on the face image and the reference light intensity, the "half-face" phenomenon in vehicles is solved, and the accuracy and efficiency of face recognition are improved.

CN116311179BActive Publication Date: 2026-06-30SAIC GM WULING AUTOMOBILE CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SAIC GM WULING AUTOMOBILE CO LTD
Filing Date
2023-02-28
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

When performing facial recognition in a vehicle, the "half-lit face" phenomenon caused by light entering from the side windows affects facial data collection. Existing supplementary lighting has limited compensation effect, making it difficult to effectively perform facial recognition.

Method used

The transmittance is adjusted by dimming glass. The projection area of ​​the face correction sub-region is determined based on the face image and the reference light intensity. The transmittance is adjusted to obtain the face image with the best light intensity. The lighting conditions are optimized using human head model and vehicle model.

Benefits of technology

It improves the effectiveness of facial recognition, ensures consistent lighting intensity in facial images, and enhances the accuracy and efficiency of facial recognition.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116311179B_ABST
    Figure CN116311179B_ABST
Patent Text Reader

Abstract

The application relates to a face image acquisition method and a vehicle, and relates to the technical field of vehicles. The method is applied to a vehicle provided with dimming glass, and the method comprises the following steps: acquiring a face image of a driver; determining a face correction sub-region according to the acquired face image and a reference light intensity, and determining the projection region of each face correction sub-region on the dimming glass based on a pre-established human head model and a vehicle model; for each projection region, determining a target light transmittance of the projection region according to the current light transmittance corresponding to the projection region, the regional light intensity of the face correction sub-region and the reference light intensity, and adjusting the light transmittance of the projection region according to the target light transmittance; repeatedly performing the step of acquiring the face image of the driver until there is no face correction sub-region in the acquired face image, and taking the face image as a target face image. The application can improve the face recognition effect.
Need to check novelty before this filing date? Find Prior Art