Out of the Box: A combined approach for handling occlusion in Human Pose Estimation
This work addresses occlusion in human pose estimation, which is critical for applications like surveillance and motion capture, but appears incremental as it builds on existing algorithms.
The paper tackles the problem of occlusion in human pose estimation, a fundamental challenge in both 2D and 3D contexts, by formulating a combined approach to address this issue, though no specific results or numbers are provided.
Human Pose estimation is a challenging problem, especially in the case of 3D pose estimation from 2D images due to many different factors like occlusion, depth ambiguities, intertwining of people, and in general crowds. 2D multi-person human pose estimation in the wild also suffers from the same problems - occlusion, ambiguities, and disentanglement of people's body parts. Being a fundamental problem with loads of applications, including but not limited to surveillance, economical motion capture for video games and movies, and physiotherapy, this is an interesting problem to be solved both from a practical perspective and from an intellectual perspective as well. Although there are cases where no pose estimation can ever predict with 100% accuracy (cases where even humans would fail), there are several algorithms that have brought new state-of-the-art performance in human pose estimation in the wild. We look at a few algorithms with different approaches and also formulate our own approach to tackle a consistently bugging problem, i.e. occlusions.