Human pose detection
YOLO
Pytorch model see Running pre-trained YOLO model in OpenCV
OpenPose
State of the art approach for real-time human pose estimation - Github
- Complete OpenPose guide [Updated Mar 2024]
- Deep Learning based Human Pose Estimation using OpenCV - code example
Running from OpenCV DNN)
It’s already part of opencv//samples/dnn/
see
Installation
Not successfull.
git clone https://github.com/CMU-Perceptual-Computing-Lab/openpose
cd openpose/
git submodule update --init --recursive --remote
--
cd {OpenPose_folder}
mkdir build/
cd build/
-- Ubuntu Prerequisites -
sudo apt install protobuf-compiler -- Protobuf
sudo apt install libopencv-dev
sudo apt-get install libatlas-base-dev.
--
cmake-gui ..
-- then configure
-- then build
make -j 4
-- issue
CMake Error at /usr/share/cmake-3.29/Modules/FindPackageHandleStandardArgs.cmake:230 (message):
Could NOT find Atlas (missing: Atlas_CLAPACK_INCLUDE_DIR
Atlas_CBLAS_LIBRARY Atlas_BLAS_LIBRARY)
Call Stack (most recent call first):
/usr/share/cmake-3.29/Modules/FindPackageHandleStandardArgs.cmake:600 (_FPHSA_FAILURE_MESSAGE)
cmake/Modules/FindAtlas.cmake:43 (find_package_handle_standard_args)
cmake/Dependencies.cmake:121 (find_package)
CMakeLists.txt:49 (include)
see also
- Coral PoseNet
- Using OpenPose with Stable Diffusion
- Using MPFB to Pose for Stable Diffusion
- ControlNet: A Complete Guide - a neural network that controls image generation in Stable Diffusion by adding extra conditions.
- How to Use Open Pose & ControlNet in Stable Diffusion
Written on February 6, 2018, Last update on June 8, 2024
computer-vision
human
pose-estimation
stable-diffusion
blender