3D reconstruction of freely moving persons for re-identification with a depth sensor
- 1 May 2014
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4512-4519
- https://doi.org/10.1109/icra.2014.6907518
Abstract
In this work, we describe a novel method for creating 3D models of persons freely moving in front of a consumer depth sensor and we show how they can be used for long-term person re-identification. For overcoming the problem of the different poses a person can assume, we exploit the information provided by skeletal tracking algorithms for warping every point cloud frame to a standard pose in real time. Then, the warped point clouds are merged together to compose the model. Re-identification is performed by matching body shapes in terms of whole point clouds warped to a standard pose with the described method. We compare this technique with a classification method based on a descriptor of skeleton features and with a mixed approach which exploits both skeleton and shape features. We report experiments on two datasets we acquired for RGB-D re-identification which use different skeletal tracking algorithms and which are made publicly available to foster research in this new research branch.Keywords
This publication has 17 references indexed in Scilit:
- Scalable real-time volumetric surface reconstructionACM Transactions on Graphics, 2013
- Mining actionlet ensemble for action recognition with depth camerasPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Improving identification by pruning: A case study on face recognition and body soft biometricPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Home 3D body scans from noisy image and range dataPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- KinectFusionPublished by Association for Computing Machinery (ACM) ,2011
- 4-dimensional local spatio-temporal features for human activity recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Kinect Identity: Technology and ExperienceComputer, 2011
- Action recognition based on a bag of 3D pointsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Three-Dimensional Face RecognitionInternational Journal of Computer Vision, 2005
- A method for registration of 3-D shapesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992