Pose Estimation

Capability Introduction

Key skeletal features of a human body, precise detection

This API detects 14 key features of human bodies in images, and feeds back coordinate information of such features, including information of key skeletal features such as head, neck, left and right shoulders, as well as left and right elbows.

Behavior recognition, posture capture

This API can be used to accurately detect key skeletal features of a human body and is applicable to scenarios based on human posture capture, such as behavior recognition and human tracking.

Exercise and fitness

Provides exercise guidances by comparing the the estimated motions based on skeletal feature detection with standard exercise motion.

Intelligent security

Determines whether a person in the surveillance area has any abnormal behavior based on skeletal feature detection, so as to issue warnings and take security measures promptly.



VisionImage image = VisionImage.fromBitmap(dstbmp);
ArrayList<BodySkeletons> mBodySkeletons = new ArrayList<>();
int resultCode = mDetector.detect(image, mBodySkeletons, null);



Start development here with Huawei

Service introduction

Service overview, application scenarios, and functions
Learn more

Access preparation

Preparation for access, such as registration, authentication, and agreement signing
Learn more

Sample code

Demonstration of sample code
Learn more

API description

Interface parameter definition, description, restrictions, and constraints
Learn more
1Can I call the faceCompare() method without calling the prepare() method of the API?

Yes, you can. The engine is started by default in the faceCompare() method. If the engine has already been started, it will not restart.

2Which mobile phone models does this API support?

Currently, the API only supports mobile phones equipped with Kirin 970/980 chips.

3Does this API compute on-device or in-cloud?

The API computes on-device, and can be used normally without network connection.