Fast embedded feet pose estimation based on a depth camera for smart walker

Page, Solenne; Martins, Maria; Saint-Bauzel, Ludovic; Santos, Cristina P.; Pasqui, Viviane

doi:10.1109/icra.2015.7139781

Cited by 19 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The position of the foot was determined to be its centroid, whereas the orientation was found using Principal Component Analysis (PCA). The position error along the anterior-posterior direction and the orientation error with respect to the vertical axis were less than 31 mm and 22 Root Mean Square Deviation %, respectively for healthy subjects [20] and 40.1 mm for the position error along the forward for older adults [21].…”

Section: Introductionmentioning

confidence: 81%

“…The authors then used the Markov Chain model and Support Vector Machine (SVM) to identify walking patterns. Without the use of modeling, the feet can still be directly extracted from the depth image [20,21]. The position of the foot was determined to be its centroid, whereas the orientation was found using Principal Component Analysis (PCA).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time Foot Tracking and Gait Evaluation with Geometric Modeling

Foo¹,

Chang²,

Ang

2022

Sensors

View full text Add to dashboard Cite

Gait evaluation is important in gait rehabilitation and assistance to monitor patient’s balance status and assess recovery performance. Recent technologies leverage on vision-based systems with high portability and low operational complexity. In this paper, we propose a new vision-based foot tracking algorithm specially catering to overground gait assistive devices, which often have limited view of the users. The algorithm models the foot and the shank of the user using simple geometry. Through cost optimization, it then aligns the models to the point cloud, showing the back view of the user’s lower limbs. The system outputs the poses of the feet, which are used to compute the spatial-temporal gait parameters. Seven healthy young subjects are recruited to perform overground and treadmill walking trials. The results of the algorithm are compared with the motion capture system and a third-party gait analysis software. The algorithm has a fitting rotational and translational errors of less than 20 degrees and 33 mm, respectively, for 0.4 m/s walking speed. The gait detection F1 score achieves more than 96.8%. The step length and step width errors are around 35 mm, while the cycle time error is less than 38 ms. The proposed algorithm provides a fast, contactless, portable, and cost-effective gait evaluation method without requiring the user to wear any customized footwear.

show abstract

Section: Introductionmentioning

confidence: 81%

Section: Introductionmentioning

confidence: 99%

Real-Time Foot Tracking and Gait Evaluation with Geometric Modeling

Foo¹,

Chang²,

Ang

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Given that a joint angle difference of more than 5 • is considered a clinically significant difference for gait analysis [55], we claim the accuracy of our CoLiTrack approach to be sufficient. In comparison, results from instrumented crutches [56] as well as from a smart walker (rollator + depth camera) [57] using principal component analysis to estimate the shank angle showed deviations of up to 10 • . Moreover, our real-world experiment demonstrated that neither ground reflectance nor clutter has an influence on CoLiTrack performance.…”

Section: Advantages Of the Proposed Methodsmentioning

confidence: 97%

Real-time limb tracking in single depth images based on circle matching and line fitting

et al. 2021

View full text Add to dashboard Cite

Modern lower limb prostheses neither measure nor incorporate healthy residual leg information for intent recognition or device control. In order to increase robustness and reduce misclassification of devices like these, we propose a vision-based solution for real-time 3D human contralateral limb tracking (CoLiTrack). An inertial measurement unit and a depth camera are placed on the side of the prosthesis. The system is capable of estimating the shank axis of the healthy leg. Initially, the 3D input is transformed into a stabilized coordinate system. By splitting the subsequent shank estimation problem into two less computationally intensive steps, the computation time is significantly reduced: First, an iterative closest point algorithm is applied to fit circular models against 2D projections. Second, the random sample consensus method is used to determine the final shank axis. In our study, three experiments were conducted to validate the static, the dynamic and the real-world performance of our CoLiTrack approach. The shank angle can be tracked at 20 Hz for one sixth of the entire human gait cycle with an angle estimation error below $$2.8\pm 2.1^{\circ }$$ 2.8 ± 2 . 1 ∘ . Our promising results demonstrate the robustness of the novel CoLiTrack approach to make “next-generation prostheses” more user-friendly, functional and safe.

show abstract

“…LIDAR sensors combined with wearable ones (Weon and Lee, 2018) have been used to analyse the kinematics of lower limbs and measure feet orientation. Page et al (2015) also resorted to a depth camera for feet position and orientation detection. Lv et al (2020) used multi-channel proximity sensors to determine each leg's distance and velocity.…”

Section: Human Motion Decoding In Smart Walkersmentioning

confidence: 99%

Deep learning-based approaches for human motion decoding in smart walkers for rehabilitation

Gonçalves¹,

Lopes²,

Moccia³

et al. 2023

Preprint

View full text Add to dashboard Cite

Gait disabilities are among the most frequent impairments worldwide. Their treatment increasingly relies on rehabilitation therapies, in which smart walkers are being introduced to empower the user's recovery state and autonomy, while reducing the clinicians effort. For that, these should be able to decode human motion and needs, as early as possible. Current walkers decode motion intention using information gathered from wearable or embedded sensors, namely inertial units, force sensors, hall sensors, and lasers, whose main limitations imply an expensive solution or hinder the perception of human movement. Smart walkers commonly lack an advanced and seamless human-robot interaction, which intuitively and promptly understands human motions. A contactless approach is proposed in this work, addressing human motion decoding as an early action recognition/detection problematic, using RGB-D cameras. We studied different deep learning-based algorithms, organised in three different approaches, to process lower body RGB-D video sequences, recorded from an embedded camera of a smart walker, and classify them into 4 classes (stop, walk, turn right/left). A custom dataset involving 15 healthy participants walking with the walker device was acquired and prepared, resulting in 28800 balanced RGB-D frames, to train and evaluate the deep learning networks. The best results were attained by a convolutional neural network with a channel-wise attention mechanism, reaching accuracy values of 99.61% and above 93%, for offline early detection/recognition and trial simulations, respectively. Following the hypothesis that human lower body features encode prominent information, fostering a more robust prediction towards real-time applications, the algorithm focus was also quantitatively evaluated using Dice metric, leading to values slightly higher than 30%. Promising results were attained for early action detection as a human motion decoding strategy, with enhancements in the focus of the proposed architectures.

show abstract

Fast embedded feet pose estimation based on a depth camera for smart walker

Cited by 19 publications

References 13 publications

Real-Time Foot Tracking and Gait Evaluation with Geometric Modeling

Real-Time Foot Tracking and Gait Evaluation with Geometric Modeling

Real-time limb tracking in single depth images based on circle matching and line fitting

Deep learning-based approaches for human motion decoding in smart walkers for rehabilitation

Contact Info

Product

Resources

About