All Projects → matlab-deep-learning → pose-estimation-3d-with-stereo-camera

matlab-deep-learning / pose-estimation-3d-with-stereo-camera

Licence: other
This demo uses a deep neural network and two generic cameras to perform 3D pose estimation.

Programming Languages

matlab
3953 projects

Projects that are alternatives of or similar to pose-estimation-3d-with-stereo-camera

Sltk
An OpenCV-based structured light processing toolkit.
Stars: ✭ 151 (+277.5%)
Mutual labels:  camera-calibration, 3d-reconstruction
ICON
ICON: Implicit Clothed humans Obtained from Normals (CVPR 2022)
Stars: ✭ 641 (+1502.5%)
Mutual labels:  human-pose-estimation, 3d-reconstruction
transformer-models
Deep Learning Transformer models in MATLAB
Stars: ✭ 90 (+125%)
Mutual labels:  pretrained-models, matlab-deep-learning
Open-Source-Models
Address book for computer vision models.
Stars: ✭ 30 (-25%)
Mutual labels:  pretrained-models, yolov3
Imgclsmob
Sandbox for training deep learning networks
Stars: ✭ 2,405 (+5912.5%)
Mutual labels:  human-pose-estimation, pretrained-models
Yolov3 Object Detection With Opencv
This project implements a real-time image and video object detection classifier using pretrained yolov3 models.
Stars: ✭ 191 (+377.5%)
Mutual labels:  pretrained-models, yolov3
Vgg Multiple View Geometry
A set of MATLAB utilities for multiple view geometry, provided alongside Hartley & Zisserman's "Multiple View Geometry in Computer Vision, Second Edition" (2004). Obtained from http://www.robots.ox.ac.uk/~vgg/hzbook/code/.
Stars: ✭ 62 (+55%)
Mutual labels:  camera-calibration, 3d-reconstruction
Simple Hrnet
Multi-person Human Pose Estimation with HRNet in Pytorch
Stars: ✭ 299 (+647.5%)
Mutual labels:  human-pose-estimation, yolov3
Trt pose
Real-time pose estimation accelerated with NVIDIA TensorRT
Stars: ✭ 525 (+1212.5%)
Mutual labels:  human-pose-estimation, pretrained-models
Pytorch Human Pose Estimation
Implementation of various human pose estimation models in pytorch on multiple datasets (MPII & COCO) along with pretrained models
Stars: ✭ 346 (+765%)
Mutual labels:  human-pose-estimation, pretrained-models
Computer-Vision
Cool Vision projects
Stars: ✭ 51 (+27.5%)
Mutual labels:  camera-calibration, 3d-reconstruction
CalibrationWizard
[ICCV'19] Calibration Wizard: A Guidance System for Camera Calibration Based on Modelling Geometric and Corner Uncertainty
Stars: ✭ 80 (+100%)
Mutual labels:  camera-calibration, 3d-reconstruction
3dv tutorial
An Invitation to 3D Vision: A Tutorial for Everyone
Stars: ✭ 571 (+1327.5%)
Mutual labels:  camera-calibration, 3d-reconstruction
Fspy Blender
Official fSpy importer for Blender
Stars: ✭ 538 (+1245%)
Mutual labels:  camera-calibration
Stag
STag: A Stable Fiducial Marker System
Stars: ✭ 75 (+87.5%)
Mutual labels:  camera-calibration
Advanced lane detection
Advanced lane detection using computer vision
Stars: ✭ 395 (+887.5%)
Mutual labels:  camera-calibration
Stereo Calibration
📷 📷 Stereo camera calibration using OpenCV and C++
Stars: ✭ 376 (+840%)
Mutual labels:  camera-calibration
Ofxmvg
OFX plugins for Multiple View Geometry
Stars: ✭ 64 (+60%)
Mutual labels:  camera-calibration
Handeye calib camodocal
Easy to use and accurate hand eye calibration which has been working reliably for years (2016-present) with kinect, kinectv2, rgbd cameras, optical trackers, and several robots including the ur5 and kuka iiwa.
Stars: ✭ 364 (+810%)
Mutual labels:  camera-calibration
Rawpy
📷 RAW image processing for Python, a wrapper for libraw
Stars: ✭ 256 (+540%)
Mutual labels:  camera-calibration

2台の汎用カメラによる3次元姿勢推定 -Pose Estimation 3D with stereo camera-

About

このデモはディープニューラルネットワークと汎用のカメラ2台を使って3次元の姿勢推定を行うデモです。
This demo uses a deep neural network and two generic cameras to perform 3D pose estimation.

結果 - Result

How to Get Started

  1. プロジェクトファイルPoseEstimation_in_3D.prjを開き、プロジェクトを開始してください。
    Open the project file "PoseEstimation_in_3D.prj" to start this project.
  2. Demosフォルダのmain.mlxを実行するとサンプルデモを開始することができます。
    You can run main.mlx in the Demos folder to start the demo.

Preparations

デモで使った2台のカメラパラメータは事前に単一カメラキャリブレータAppで計算したものです。
The camera intrinsic parameters of the two cameras used in the demo were calculated in advance by the Signle Camera Calibrator App.
https://www.mathworks.com/help/vision/ug/single-camera-calibrator-app.html

デモで使う姿勢推定のネットワークは下のGitHubリポジトリからダウンロードし、使えるようにしておきます。
リポジトリへのパスはプロジェクトファイル実行時に通しますが、本デモのリポジトリとモデルのリポジトリが同じフォルダに存在する前提です。異なる場合はパスを通し直して下さい。
The network for pose estimation used in the demo can be downloaded from the GitHub repository below. You need to set the path for it to work in use. The path to the model will be set automatically when you start the project. But, the default setting assumes that the repository of this demo and the model are located under the identical folder. If this is not the case, please re-set the path.
https://github.com/matlab-deep-learning/Human-Pose-Estimation-with-Deep-Learning

公式のヘルプにも姿勢推定モデルのサンプルがあります。そちらを使っても構いませんが、関係する部分のコードを一部差し替える必要があります。
There is a sample pose estimation model in the official help. You can use that one, but you will need to replace some of the code in the relevant parts.
公式の姿勢推定モデルのサンプル Official sample

Required Products

MATLAB® R2021a
Deep Learning Toolbox™
Computer Vision Toolbox™
Image Processing Toolbox™
Signal Processing Toolbox™

Copyright 2021 The MathWorks, Inc.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].