Perform Human Pose Estimation in OpenCV Using OpenPose MobileNet
Perform Human Pose Estimation in OpenCV Using OpenPose MobileNet
python openpose.py
python openpose.py --input image.jpg
--thr
to increase confidence thresholdpython openpose.py --input image.jpg --thr 0.5
Tensorflow MobileNet Model
, which is provided by ildoonet/tf-pose-estimation, instead of Caffe Model
from CMU OpenPose. The original openpose.py
from OpenCV example
only uses Caffe Model
which is more than 200MB while the Mobilenet
is only 7MB.cv.dnn.blobFromImage
and use out = out[:, :19, :, :]
to get only the first 19 rows in the out
variable.