demonkenny/MAXINE-AR-SDK
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add images to README

Browse Source
This commit is contained in:
jdsouza90
2020-10-04 13:14:31 -07:00
committed by GitHub
parent ea3b5faaa3
commit d565a97779
1 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.MD
View File

@@ -6,9 +6,17 @@ NVIDIA AR SDK enables real-time modeling and tracking of human faces from video.
NVIDIA AR SDK has the following features:
- **Face detection and tracking**, which detects, localizes, and tracks human faces in images or videos by using bounding boxes.
![Face detection and tracking](https://developer.nvidia.com/sites/default/files/akamai/gameworks/nv_broadcast/arsdk_001.png)
- **Facial landmark detection and tracking**, which predicts and tracks the pixel locations of human facial landmark points and head poses in images or videos. It can predict 68 and 126 landmark points. The 68 detected facial landmarks follow the _Multi-PIE 68 point mark-ups_ information in [facial point annotations](https://ibug.doc.ic.ac.uk/resources/facial-point-annotations/). The 126 landmark points detector can predict more points on the cheeks, the eyes, and on laugh lines.
![Facial landmark detection and tracking](https://developer.nvidia.com/sites/default/files/akamai/gameworks/nv_broadcast/arsdk_002.png)
- **Face 3D mesh and tracking**, which reconstructs and tracks a 3D human face and its head pose from the provided facial landmarks.
![Face 3D mesh and tracking](https://developer.nvidia.com/sites/default/files/akamai/gameworks/nv_broadcast/arsdk_003.png)
NVIDIA AR SDK provides a sample application that demonstrates the features listed above in real time by using a webcam or offline videos.
NVIDIA AR SDK is distributed in the following parts: