A Comparison on Different 2D Human Pose Estimation Method

Human Pose Estimation is a fast developing field and lately gone forward with the advanced finding of the Kinect system. For 3D pose estimation, this system performs good but the 2D pose estimation has not solved yet. In Computer Vision, articulated body pose estimation, systems detect the pose of a human body, that consists of joints and flexible parts using. Human body pose estimation models are complex therefore it is one of longest-lasting problems in computer vision.There is a need to develop accurate articulated body pose estimation systems to detect the pose of bodies like hands, legs,head etc. Pose estimation has many applications that can benefit such as robotics, human computer interaction, video surveillance, multimedia, augmented reality, video retrieval and biometrics or intelligent surveillance. Images and videos can have many challenges like background clutters, varying lighting conditions, unconstrained clothing of the person, occlusion etc. A comparative study included in this paper mainly focusing on different 2D human pose estimation methods like pictorial structure, silhouette method, skeletonization, model for shape context matching, segmentation, features extraction and recognition tools, research advantages and drawbacks are provided as well.