Pose estimates from online videos show that side-by-side walkers synchronize movement under naturalistic conditions

Chambers, Claire; Kong, Gaiqing; Wei, Kunlin; Kording, Konrad

doi:10.1371/journal.pone.0217861

Cited by 30 publications

(35 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another "in the wild example" is given by a recent study by Chambers et al (86), who revisited the classic question of how people synchronize their walking, but with a modern twist by using videos from YouTube and analysis with OpenPose (19). Consistent with studies performed in the laboratory, they found a tendency for pairs of people to either walk in or exactly out of phase (86).…”

Section: Natural Behaviors and Ethologically Relevant Featuresmentioning

confidence: 74%

Deep learning tools for the measurement of animal behavior in neuroscience

Mathis

2020

Current Opinion in Neurobiology

340

237

View full text Add to dashboard Cite

Recent advances in computer vision have made accurate, fast and robust measurement of animal behavior a reality. In the past years powerful tools specifically designed to aid the measurement of behavior have come to fruition. Here we discuss how capturing the postures of animals -pose estimation -has been rapidly advancing with new deep learning methods. While challenges still remain, we envision that the fast-paced development of new deep learning tools will rapidly change the landscape of realizable real-world neuroscience. Highlights:1. Deep neural networks are shattering performance benchmarks in computer vision for various tasks.2. Using modern deep learning approaches (DNNs) in the lab is a fruitful approach for robust, fast, and efficient measurement of animal behavior.3. New DNN-based tools allow for customized tracking approaches, which opens new avenues for more flexible and ethologically relevant real-world neuroscience.

show abstract

Section: Natural Behaviors and Ethologically Relevant Featuresmentioning

confidence: 74%

Deep learning tools for the measurement of animal behavior in neuroscience

Mathis

2020

Current Opinion in Neurobiology

340

237

View full text Add to dashboard Cite

show abstract

“…Some prior studies have used OpenPose to investigate particular features of walking or other human movement patterns (Chambers et al, 2019;Sato et al, 2019;Viswakumar et al, 2019;Nakano et al, 2020;Ota et al, 2020;Zago et al, 2020). Our findings align with these reports in that we found OpenPose to be capable of reasonably accurate tracking of human movement (in our case, walking).…”

Section: Discussionmentioning

confidence: 99%

“…OpenPose is a freely available human pose estimation algorithm that uses Part Affinity Fields to detect up to 135 keypoints in images of humans (Martinez et al, 2017;Cao et al, 2019). Several prior studies have used OpenPose to study certain features of human walking (Chambers et al, 2019;Sato et al, 2019;Viswakumar et al, 2019;Zago et al, 2020), but there remain important needs for robust validation of a comprehensive set of gait parameters against motion capture measurements and a shareable workflow. First, we used OpenPose to detect keypoints on videos of healthy adults walking overground.…”

Section: Introductionmentioning

confidence: 99%

Two-dimensional video-based analysis of human gait using pose estimation

Stenum

Rossi

Roemmich

2020

Preprint

View full text Add to dashboard Cite

Walking is the primary mode of human locomotion. Accordingly, people have been interested in studying human gait since at least the fourth century BC. Human gait analysis is now common in many fields of clinical and basic research, but gold standard approaches – e.g., three-dimensional motion capture, instrumented mats or footwear, and wearables – are often expensive, immobile, data-limited, and/or require specialized equipment or expertise for operation. Recent advances in video-based pose estimation have suggested exciting potential for analyzing human gait using only two-dimensional video inputs collected from readily accessible devices (e.g., smartphones, tablets). However, we currently lack: 1) data about the accuracy of video-based pose estimation approaches for human gait analysis relative to gold standard measurement techniques and 2) an available workflow for performing human gait analysis via video-based pose estimation. In this study, we compared a large set of spatiotemporal and sagittal kinematic gait parameters as measured by OpenPose (a freely available algorithm for video-based human pose estimation) and three-dimensional motion capture from trials where healthy adults walked overground. We found that OpenPose performed well in estimating many gait parameters (e.g., step time, step length, sagittal hip and knee angles) while some (e.g., double support time, sagittal ankle angles) were less accurate. We observed that mean values for individual participants – as are often of primary interest in clinical settings – were more accurate than individual step-by-step measurements. We also provide a workflow for users to perform their own gait analyses and offer suggestions and considerations for future approaches.

show abstract

“…By creating such a 'normative' database, we can then estimate the probability that the movements of a new infant belong to the normative distribution, thereby assessing the probability that the infant is healthy. In previous work, we have shown that online video databases are a useful source of human movement data [27]. In the present study, we built a normative database of infant movements based on video data of infants from YouTube, assuming that found videos represented healthy infant movement.…”

Section: A Youtube Datamentioning

confidence: 99%

Computer Vision to Automatically Assess Infant Neuromotor Risk

Chambers

Seethapathi

Saluja

et al. 2020

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

An infant's risk of developing neuromotor impairment is primarily assessed through visual examination by specialized clinicians. Therefore, many infants at risk for impairment go undetected, particularly in under-resourced environments. There is thus a need to develop automated, clinical assessments based on quantitative measures from widely-available sources, such as videos recorded on a mobile device. Here, we automatically extract body poses and movement kinematics from the videos of at-risk infants (N=19). For each infant, we calculate how much they deviate from a group of healthy infants (N=85 online videos) using a Naïve Gaussian Bayesian Surprise metric. After pre-registering our Bayesian Surprise calculations, we find that infants who are at high risk for impairments deviate considerably from the healthy group. Our simple method, provided as an open-source toolkit, thus shows promise as the basis for an automated and low-cost assessment of risk based on video recordings.

show abstract

Pose estimates from online videos show that side-by-side walkers synchronize movement under naturalistic conditions

Cited by 30 publications

References 39 publications

Deep learning tools for the measurement of animal behavior in neuroscience

Deep learning tools for the measurement of animal behavior in neuroscience

Two-dimensional video-based analysis of human gait using pose estimation

Computer Vision to Automatically Assess Infant Neuromotor Risk

Contact Info

Product

Resources

About