Human Pose Estimation Using Convolutional Neural Networks

Abstract

Human pose estimation has always been a challenging problem that holds great attention, it has the widespread and extensive variety of uses from the classification of images to activity acknowledgment, main challenge is the detection and localization of the key points in the variation of several body poses. To resolve this issue, substantial research work have been done in this area. This paper discusses the issues in human pose estimation and gives the overview of considerable research work in pose estimation, including deep learning approach and customary image-based techniques. After analyzing several results and detecting the restrictions, the author has reconstructed a simple model using convolutional neural network that estimates the poses and demonstrates the potential of CNN's. The author concludes with a few promising bearings and directions that have to be explored for future research.