Deep-Learning-based-OpenPose-Estimation

Deep learning based OpenPose estimation.

Dataset

1. VGG Pose Dataset (https://www.robots.ox.ac.uk/~vgg/data/pose/)
2. COCO Keypoints challenge. (http://cocodataset.org/#home)

References:-

1. LearnOpenCV's Blog on Open Pose, Author: Vikas Gupta: https://www.learnopencv.com/deep-learning-based-human-pose-estimation-using-opencv-cpp-python/
2. https://arxiv.org/pdf/1611.08050.pdf
3. https://medium.com/neuromation-blog/neuronuggets-understanding-human-poses-in-real-time-b73cb74b3818

Important terms used in the reference paper

1. Confidence Maps.
   • Resource: mohitzsh/Adversarial-Semisupervised-Semantic-Segmentation#4
2. L2 Loss.
   • http://rishy.github.io/ml/2015/07/28/l1-vs-l2-loss/
3. Affinity fields.

Testing

The code has been tested using:

1. Caffe Version 1.0.
2. Python 3.6
3. OpenCV 3.4.x

Language Used

1. Python
2. C++