| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
Depth-based hand pose estimation: data, methods, and challenges
Abstract : Hand pose estimation has matured rapidly in recent years. The introduction of commodity depth sensors and a multitude of practical applications have spurred new advances. We provide an extensive analysis of the state-of-the-art, focusing on hand pose estimation from a single depth frame. To do so, we have implemented a considerable number of systems, and will release all software and evaluation code. We summarize important conclusions here: (1) Pose estimation appears roughly solved for scenes with isolated hands. However, methods still struggle to analyze cluttered scenes where hands may be interacting with nearby objects and surfaces. To spur further progress we introduce a challenging new dataset with diverse, cluttered scenes. (2) Many methods evaluate themselves with disparate criteria , making comparisons difficult. We define a consistent evaluation criteria, rigorously motivated by human experiments. (3) We introduce a simple nearest-neighbor baseline that outperforms most existing systems. This implies that most systems do not generalize beyond their training sets. This also reinforces the under-appreciated point that training data is as important as the model itself. We conclude with directions for future progress.
Cited literature [37 references]
https://hal.inria.fr/hal-01237023
Contributor : Gregory Rogez <>
Submitted on : Wednesday, December 2, 2015 - 3:29:14 PM
Last modification on : Thursday, November 19, 2020 - 1:00:31 PM
Long-term archiving on: : Saturday, April 29, 2017 - 3:45:06 AM
Contributor : Gregory Rogez <>
Submitted on : Wednesday, December 2, 2015 - 3:29:14 PM
Last modification on : Thursday, November 19, 2020 - 1:00:31 PM
Long-term archiving on: : Saturday, April 29, 2017 - 3:45:06 AM
Files
HandEval.pdf
Files produced by the author(s)