IntelRealSense / librealsense

Intel® RealSense™ SDK
https://www.intelrealsense.com/
Apache License 2.0
7.59k stars 4.82k forks source link

Is the depth data in the D435 accurate enough to be used in facial recognition? #12202

Closed pgswag closed 1 year ago

pgswag commented 1 year ago
Required Info
Camera Model { D435
Firmware Version (Open RealSense Viewer --> Click info)
Operating System & Version {Win 10
Platform PC
SDK Version { legacy / 2.<?>.<?> }
Language {C/C#/labview/nodejs/opencv/pcl/python/unity }
Segment others

Issue Description

Can D435 be used with face recognition applications? Is the depth data accurate enough to capture the features of a human face? If enough, what is the optimal setting of the best parameters for facial recognition。

MartyG-RealSense commented 1 year ago

Hi @pgswag Yes, the D435 camera model can be used with facial recognition to capture the landmarks of a human face. The RealSense SDK provides a couple of example projects.

C++ and Dlib - simple anti-spoofing application https://github.com/IntelRealSense/librealsense/blob/master/wrappers/dlib/face

C++ and OpenVINO https://github.com/IntelRealSense/librealsense/blob/master/wrappers/openvino/face

The default settings of the camera should be sufficient for facial recognition. If high confidence in the depth values is a requirement then the Medium Density camera configuration preset provides a good balance between accuracy and the amount of detail on the depth image.

https://dev.intelrealsense.com/docs/d400-series-visual-presets#preset-table

MartyG-RealSense commented 1 year ago

Hi @pgswag Do you require further assistance with this case, please? Thanks!

MartyG-RealSense commented 1 year ago

Case closed due to no further comments received.