GAIMS > Introduction

The project GAIMS [1] [2] [3] [4] (this acronym stands for "Gait Analysis Imaging System", "Gait Measuring System", or "Gait Analysis in Multiple Sclerosis"), conducted at the University of Liège in Belgium, started in the beginning of 2011. The collaboration between the engineers of the INTELSIG laboratory and the neurologists of the university hospital aims at developing a new gait (i.e. the way people are walking) analysis system well suited for the clinical routine (see this page and  [2] for more information about the motivations). The initial requirements were that the system should be able to measure the movements of the lower limb extremities (which are named "feet" in this project, even if the extremities can be larger or smaller than the feet), positioning them absolutely in the room in the stance phase as well as in the swing phase, while being non-intrusive. This means that the observed person does not need to carry any sensor or marker, has not to wear special clothes, and is not restricted to walk on a small area such as a treadmill.

Walking [5] is a complex process involving mechanical, muscular, neurological,and psychological aspects, to cite only a few. It is well known that the gait is unique to each person [6]. Moreover, it depends on many factors such as the age, the gender,the weight, the height, or the type of clothing and footwear worn. It can be affected by various diseases (neurological [7], cardiovascular [8], metabolic [9], by the psychological and emotional state, by the simultaneous cognitive load (i.e. dual tasks) [10,11], as well as medication and alcohol consumption. Walking is also altered during pregnancy, and when heavy or bulky objets are transported. For all these reasons,observing, measuring and analyzing the gait is a wonderful mean of inferring a lot of interesting information about people. This process can be used in many kinds of applications, ranging from medical to security and entertainment ones.

In the project GAIMS, we propose to measure the trajectories of the lower limb extremities with range laser scanners, and to derive various gait characteristics from these trajectories. These characteristics can then be further processed in order to determine some information about the observed person, and for example to help diagnosing various diseases and for the longitudinal follow-up of patients with walking impairments. GAIMS comes with a set of tools to help interpreting the measured gait characteristics, some of them being based on statistical analyses, and others on machine learning techniques [12,13].


Figure 2. We measure feet trajectories with range laser scanners covering a common horizontal plane located at the height of the ankles. On this picture, a few laser beams are depicted for three sensors, even if they are invisible in reality.

The following video helps to understand the information GAIMS obtains from the range laser scanners. The measured distance profiles are converted into point clouds, that are merged thanks to the knowledge of the orientations and positions of the sensors. The feet trajectories are computed based on the resulting global point cloud, and the features describing the gait are derived from these two trajectories. We have the walking speed, the inter-feet distance, the deviation from the followed path, the cadence, the stride length, the gait asymmetry, the temporal variability, and the proportion of double limb support time, to cite only a few examples.

Loading the player ...


Figure 3. GAIMS in action! This video shows the dynamic point cloud that is analyzed by our software. A healthy volunteer is walking along a eight-shaped path. On the left hand side, the four sensors are depicted in turquoise, the followed path is drawn in white, the horizontal cross-section of the walking person’s legs (that is the global point cloud, or the “feet”) in yellow. On the right hand side, you can see the synchronized color and range images acquired by a kinect (unused by our software).

Bibliography

  1. S. Piérard, S. Azrour, R. Phan-Ba, and M. Van Droogenbroeck. GAIMS: A reliable non-intrusive gait measuring system. ERCIM News, 95:26-27, October 2013. [ get the document via orbi ]
  2. S. Belachew, S. Piérard, R. Phan-Ba, and M. Van Droogenbroeck. Multimodal evaluation of gait and stride dynamics in relapsing and progressive forms of multiple sclerosis. Proceedings of the Belgian Royal Academies of Medecine, 1:66-69, 2012. [ get the document via orbi ]
  3. S. Piérard, R. Phan-Ba, V. Delvaux, P. Maquet, and M. Van Droogenbroeck. GAIMS: a powerful gait analysis system satisfying the constraints of clinical routine. Multiple Sclerosis Journal, 19(S1):359, October 2013. Proceedings of ECTRIMS/RIMS 2013 (Copenhagen, Denmark), P800. [ get the document via orbi ]
  4. S. Piérard, S. Azrour, and M. Van Droogenbroeck. Design of a reliable processing pipeline for the non-intrusive measurement of feet trajectories with lasers. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 4432-4436, Florence, Italy, May 2014. [ DOI | get the document via orbi | http ]
  5. J. Perry. Gait analysis, normal and pathological function. Slack, first edition, 1992.
  6. N. Boulgouris, D. Hatzinakos, and K. Plataniotis. Gait recognition: a challenging signal processing technology for biometric identification. IEEE Signal Processing Magazine, 22(6):78-90, November 2005.
  7. H.-R. Zheng, M.-J. Yang, H.-Y. Wang, and S. McClean. Machine learning and statistical approaches to support the discrimination of neuro-degenerative diseases based on gait analysis. In S. McClean, P. Millard, E. El-Darzi, and C. Nugent, editors, Intelligent Patient Management, volume 189 of Studies in Computational Intelligence, pages 57-70. Springer, 2009.
  8. B. Bloem, J. Gussekloo, A. Lagaay, E. Remarque, J. Haan, and R. Westendorp. Idiopathic senile gait disorders are signs of subclinical disease. Journal of the American Geriatrics Society, 48(9), September 2000.
  9. J. Petrofsky, S. Lee, and S. Bweir. Gait characteristics in people with type 2 diabetes mellitus. European Journal of Applied Physiology, 93(5):640-647, 2005.
  10. J. Hausdorff, J. Balash, and N. Giladi. Effects of cognitive challenge on gait variability in patients with Parkinson's disease. Journal of Geriatric Psychiatry and Neurology, 16(1):53-58, 2003.
  11. E. Lamberg and L. Muratori. Cell phones change the way we walk. Gait & Posture, 35(4):688-690, April 2012.
  12. C. Bishop. Pattern Recognition and Machine Learning. Information Science and Statistics. Springer, 2006.
  13. T. Hastie, R. Tibshirani, and J. Friedman. The elements of statistical learning: data mining, inference, and prediction. Springer Series in Statistics. Springer, second edition, September 2009.