Gait recognition: highly unique dynamic plantar pressure patterns among 104 individuals

Pataky, Todd C.; Mu, Tingting; Bosch, Kerstin; Rosenbaum, Dieter; Goulermas, John Y.

doi:10.1098/rsif.2011.0430

Cited by 95 publications

(58 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The purpose of Pataky et al in their 2012 study [16] was to analyze dynamic foot pressure patterns through plantar pressure imaging using a pedography platform that recorded footprints with 5mm resolution. They recruited 104 individuals and collected 1,040 barefoot steps.…”

Section: Related Workmentioning

confidence: 99%

“…Analyzing the force that a walking individual applies to the ground has also been proposed for identifying people, an approach referred to as footstep recognition [12]. Different gait features can be extracted through force sensors embedded in the floor: the temporal sequence of the ground reaction force (GRF) [13][14][15], the shape of the foot on the ground (footprint) [16], or the trajectory of the center of pressure (COP) [17]. The COP is the point at which the resulting vertical force is applied (i.e., the integrated vectorial pressure field).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Gait Recognition via Deep Learning of the Center-of-Pressure Trajectory

Terrier

2020

Applied Sciences

View full text Add to dashboard Cite

Fig. 6. CAM analysis. Twenty-four segments were randomly selected from the training set containing the gait data of six participants (left columns). These segments were used to fine-tune the last layers of the convolutional neural network (CNN) that was pre-trained on the training set of the 30 other participants. This CNN classified 30 segments drawn randomly from the test set with 100% accuracy (right columns). Class activation mapping (CAM) was performed on each sample of the test set. Color coding shows which parts of the signals are prioritized to be used by the CNN to perform classification. Warm color (red, orange): high focus; cold colors (green, blue): low focus. AbstractThe fact that every human has a distinctive walking style has prompted a proposal to use gait recognition as an identification criterion. Using end-to-end learning, I investigated whether the center-of-pressure trajectory is sufficiently unique to identify a person with a high certainty. Thirty-six adults walked on a treadmill equipped with a force platform that recorded the positions of the center of pressure. The raw two-dimensional signals were sliced into segments of two gait cycles . A set of 20,250 segments from 30 subjects was used to configure and train convolutional neural networks (CNNs). The best CNN classified a separate set containing 2,250 segments with 99.9% overall accuracy. A second set of 4,500 segments from the six remaining subjects was then used for transfer learning. Several small subsamples of this set were selected randomly and used for fine tuning. Training with two segments per subject was sufficient to achieve 100% accuracy. The results suggest that every person produces a unique trajectory of underfoot pressures and that CNNs can learn the distinctive features of these trajectories. Using transfer learning, a few strides could be sufficient to learn and identify new gaits.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Gait Recognition via Deep Learning of the Center-of-Pressure Trajectory

Terrier

2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The same fundamental assumption is implicit in the study of modern forensic footprints [6,7], where threedimensional footprint geometry (or metrics used to describe it) is considered diagnostic of specific individuals. A recent finding that foot pressures on hard or non-compliant surfaces are highly diagnostic of specific individuals [8] suggests that footprints may potentially represent powerful forensic tools, if a strong correlation between habitual motion, pressures and footprint depth can be quantitatively demonstrated.…”

Section: Introductionmentioning

confidence: 99%

Does footprint depth correlate with foot motion and pressure?

Bates

Savage

Pataky

et al. 2013

J. R. Soc. Interface.

View full text Add to dashboard Cite

Footprints are the most direct source of evidence about locomotor biomechanics in extinct vertebrates. One of the principal suppositions underpinning biomechanical inferences is that footprint geometry correlates with dynamic foot pressure, which, in turn, is linked with overall limb motion of the trackmaker. In this study, we perform the first quantitative test of this longstanding assumption, using topological statistical analysis of plantar pressures and experimental and computer-simulated footprints. In computer-simulated footprints, the relative distribution of depth differed from the distribution of both peak and pressure impulse in all simulations. Analysis of footprint samples with common loading inputs and similar depths reveals that only shallow footprints lack significant topological differences between depth and pressure distributions. Topological comparison of plantar pressures and experimental beach footprints demonstrates that geometry is highly dependent on overall print depth; deeper footprints are characterized by greater relative forefoot, and particularly toe, depth than shallow footprints. The highlighted difference between 'shallow' and 'deep' footprints clearly emphasizes the need to understand variation in foot mechanics across different degrees of substrate compliance. Overall, our results indicate that extreme caution is required when applying the 'depth equals pressure' paradigm to hominin footprints, and by extension, those of other extant and extinct tetrapods.

show abstract

“…The unique characteristics of the human walking are enough to identify the persons at a distance may be alone or among a group of people. This may be due to the fact that the individuals move their bodies and limbs in highly unique and repeatable patterns [102]. The first time that forensic gait analysis form evidence became admissible in criminal law occurred in the case of R V Saunders at The Old Bailey Central Court, London, UK, on 12 July 2000.…”

Section: Forensic Gait Analysismentioning

confidence: 99%