Main Article Content
Human pose evaluation on multi-person is challenging than human pose evaluation on single-person . Even when the human detectors have given their best results, small errors are available in localization part and recognition. These errors in detection lead to failures in human pose estimation. So, we propose an architecture for human pose evaluation although when the errors are present in the human detection. The model consists of two main steps: first step is to detect the human and next step is to evaluate the human pose for the detected human. The components used primarily for human pose estimation is the STN(Spatial Transformer Network), SPPE(Single Person Pose Estimator) and Pose-NMS(Non-Maximum Suppression). This method is tested on the MPII(multi-person) dataset.