Long Short-Term Memory Kalman Filters: Recurrent Neural Estimators for Pose Regularization
Authors:
- Huseyin CoskunHCHuseyin Coskun
- Felix AchillesFAFelix Achilles
- Robert DiPietroRDRobert DiPietro
- Nassir NavabNNNassir Navab
- Federico TombariFTFederico Tombari
- 1 October 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5525-5533
Abstract
One-shot pose estimation for tasks such as body joint localization, camera pose estimation, and object tracking are generally noisy, and temporal filters have been extensively used for regularization. One of the most widely-used methods is the Kalman filter, which is both extremely simple and general. However, Kalman filters require a motion model and measurement model to be specified a priori, which burdens the modeler and simultaneously demands that we use explicit models that are often only crude approximations of reality. For example, in the pose-estimation tasks mentioned above, it is common to use motion models that assume constant velocity or constant acceleration, and we believe that these simplified representations are severely inhibitive. In this work, we propose to instead learn rich, dynamic representations of the motion and noise models. In particular, we propose learning these models from data using long shortterm memory, which allows representations that depend on all previous observations and all previous states. We evaluate our method using three of the most popular pose estimation tasks in computer vision, and in all cases we obtain state-of-the-art performance.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Marker-Less 3D Human Motion Capture with Monocular Image Sequence and Height-Maps2016
- Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video2016
- PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization2015
- Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural EnvironmentsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- RGB-D object tracking: A particle filter approach on GPU2013
- Learning to Forget: Continual Prediction with LSTMNeural Computation, 2000
- Long Short-Term MemoryNeural Computation, 1997
- Learning long-term dependencies with gradient descent is difficultIEEE Transactions on Neural Networks, 1994
- Backpropagation through time: what it does and how to do itProceedings of the IEEE, 1990
- A New Approach to Linear Filtering and Prediction ProblemsJournal of Basic Engineering, 1960