Comparison of Multi-shot Models for Short-term Re-identification of People using RGB-D Sensors

Andreas Møgelmose, Chris Bahnsen, Thomas B. Moeslund

2015

Abstract

This work explores different types of multi-shot descriptors for re-identification in an on-the-fly enrolled environment using RGB-D sensors. We present a full re-identification pipeline complete with detection, segmentation, feature extraction, and re-identification, which expands on previous work by using multi-shot descriptors modeling people over a full camera pass instead of single frames with no temporal linking. We compare two different multi-shot models; mean histogram and histogram series, and test them each in 3 different color spaces. Both histogram descriptors are assisted by a depth-based pruning step where unlikely candidates are filtered away. Tests are run on 3 sequences captured in different circumstances and lighting situations to ensure proper generalization and lighting/environment invariance.

References

  1. Bak, S., Charpiat, G., Corvée, E., Brémond, F., and Thonnat, M. (2012). Learning to Match Appearances by Correlations in a Covariance Metric Space. In ECCV (3), volume 7574 of LNCS, pages 806-820. Springer.
  2. Barbosa, I. B., Cristani, M., Bue, A. D., Bazzani, L., and Murino, V. (2012). Re-identification with RGB-D Sensors. In ECCV Workshops (1), volume 7583 of LNCS, pages 433-442. Springer.
  3. Bradski, G. and Kaehler, A. (2008). Learning OpenCV, chapter 7, pages 201-202. O'Reilly.
  4. Dalal, N. and Triggs, B. (2005). Histograms of Oriented Gradients for Human Detection. In CVPR.
  5. Demirkus, M., Garg, K., and Guler, S. (2010). Automated person categorization for video surveillance using soft biometrics. pages 76670P-76670P-12.
  6. Doretto, G., Sebastian, T., Tu, P. H., and Rittscher, J. (2011). Appearance-based person reidentification in camera networks: problem overview and current approaches. J. Ambient Intelligence and Humanized Computing, 2(2):127-151.
  7. Jüngling, K. and Arens, M. (2010). Local Feature Based Person Reidentification in Infrared Image Sequences. In AVSS, pages 448-455. IEEE Computer Society.
  8. Møgelmose, A., Clapés, A., Bahnsen, C., Moeslund, T. B., and Escalera, S. (2013a). Tri-modal Person Reidentification with RGB, Depth and Thermal Features. In 9th IEEE Workshop on Perception Beyond the Visible Spectrum. IEEE.
  9. Møgelmose, A., Moeslund, T. B., and Nasrollahi, K. (2013b). Multimodal Person Re-Identification using RGB-D Sensors and a Transient Identification Database. In International Workshop on Biometrics and Forensics.
  10. Velardo, C. and Dugelay, J. (2012). Improving Identification by Pruning: A Case Study on Face Recognition and Body Soft Biometric. In WIAMIS, pages 1-4. IEEE.
  11. Zhao, R., Ouyang, W., and Wang, X. (2013). Unsupervised Salience Learning for Person Re-identification. CVPR.
  12. Zheng, W., Gong, S., and Xiang, T. (2011). Person reidentification by probabilistic relative distance comparison. In CVPR, pages 649-656. IEEE.
Download


Paper Citation


in Harvard Style

Møgelmose A., Bahnsen C. and Moeslund T. (2015). Comparison of Multi-shot Models for Short-term Re-identification of People using RGB-D Sensors . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-090-1, pages 244-251. DOI: 10.5220/0005266402440251


in Bibtex Style

@conference{visapp15,
author={Andreas Møgelmose and Chris Bahnsen and Thomas B. Moeslund},
title={Comparison of Multi-shot Models for Short-term Re-identification of People using RGB-D Sensors},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={244-251},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005266402440251},
isbn={978-989-758-090-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)
TI - Comparison of Multi-shot Models for Short-term Re-identification of People using RGB-D Sensors
SN - 978-989-758-090-1
AU - Møgelmose A.
AU - Bahnsen C.
AU - Moeslund T.
PY - 2015
SP - 244
EP - 251
DO - 10.5220/0005266402440251