Android hand detect and pose estimation by ncnn

Last update: Jan 3, 2023

Overview

ncnn_nanodet_hand
1.hand detect:用nanode-m训练了个hand detect模型,
2.hand pose:用CMU的数据集训练了个ghostnet作为backbone模仿pfld的handpose模型
3.推理:handpose.cpp单独检测pose，nanodet_hand.cpp单独检测手.参照该代码可以无痛集成到ncnn-android-nanodet中哦.
4.在nihui大佬的ncnn-android-nanodet项目基础上,去掉了其他模型只保留了检测手和手势的.
PS:由于数据集质量不理想，且自己水平有限所以实际效果可能较差，自己做着玩的.

Android上的效果可以看一下视频，总之ncnn和nanodet棒极了！
https://www.bilibili.com/video/BV1Uh411Q7Rq
Reference：
https://github.com/nihui/ncnn-android-nanodet(视频中的Android demo是基于该代码的)
https://github.com/Tencent/ncnn
https://github.com/RangiLyu/nanodet

You might also like...

Reviatalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation

Reviatalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation This is the implementation of the approach describ

47 Nov 15, 2022

HybridPose: 6D Object Pose Estimation under Hybrid Representation (CVPR 2020)

HybridPose: 6D Object Pose Estimation under Hybrid Representations This repository contains authors' implementation of HybridPose: 6D Object Pose Esti

358 Nov 22, 2022

Simple inference deep head pose ncnn version

ncnn-deep-head-pose Simple implement inference deep head pose ncnn version with high performance and optimized resource. This project based on deep-he

13 Dec 16, 2022

GFPGAN-ncnn - a naive NCNN implementation of GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration

GFPGAN-ncnn a naive ncnn implementation of GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration model support: 1.GFPGANClean

42 Dec 10, 2022

A lightweight 2D Pose model can be deployed on Linux/Window/Android, supports CPU/GPU inference acceleration, and can be detected in real time on ordinary mobile phones.

58 Jan 3, 2023

pose demo on android mobile based on PaddleDetection

Comments

error on device with single camera

Hi @FeiGeChuanShu ,

Amazing project! It works fine on device with two cameras (front and back) , but fails on device with single camera (only back)

my camera id is '1' , there is only a single camera in my device. so i set private int facing = 1;

but, it is not working on the system because there is check for front camera that is causing an error.

How can I fix this issue? Hope you can suggest a fix.

This is my log output :

2021-06-24 12:41:10.748 28982-28982/com.tencent.nanodetncnn E/NdkImageReader: AImageReader_getWindow 2021-06-24 12:41:11.040 28982-28982/com.tencent.nanodetncnn D/SurfaceView: checkSurfaceViewlLogProperty get invalid command 2021-06-24 12:41:11.054 28982-28982/com.tencent.nanodetncnn D/ncnn: loadModel 0x77c5483700 2021-06-24 12:41:11.057 28982-28982/com.tencent.nanodetncnn W/ncnn: load hand 2021-06-24 12:41:11.585 28982-28982/com.tencent.nanodetncnn D/ncnn: openCamera 1 2021-06-24 12:41:11.585 28982-28982/com.tencent.nanodetncnn W/NdkCamera: open 2021-06-24 12:41:11.588 28982-28982/com.tencent.nanodetncnn W/NdkCamera: open 0 2021-06-24 12:41:11.588 28982-28982/com.tencent.nanodetncnn E/ACameraManager: getCameraCharacteristics: Camera ID does not exist! 2021-06-24 12:41:11.588 28982-28982/com.tencent.nanodetncnn E/ACameraManager: openCamera: cannot get camera characteristics for camera . err -10001 2021-06-24 12:41:11.588 28982-28982/com.tencent.nanodetncnn E/NdkCameraDevice: ACameraDevice_createCaptureRequest: invalid argument! device 0x0 request 0x77bb99d238 2021-06-24 12:41:11.589 28982-28982/com.tencent.nanodetncnn A/libc: Fatal signal 11 (SIGSEGV), code 1, fault addr 0x8 in tid 28982 (ent.nanodetncnn)

opened by GeorvityLabs 1
how to get count of number of fingers open?

@FeiGeChuanShu how do I get the count of the number of fingers open. Hope you could point out the edits needed to be made, to display the number of open fingers.

opened by GeorvityLabs 0