Try to take a look at 'CGA Normative Gait Database'. You could also consider using some of OpemSim (SimTK) free material on gait analysis in different speeds. The latter you can find in a OpenSim project attached.
In 2011 we have published on Gait&Posture Journal reference kinematic, kinetic and EMG data of healthjy subjects during walking at self-selected, very slow, slow, medium and fast speed, as well as during toe walking, heel walking, step ascending and step descending. We have collected data separately for young and adult subjects. Here attached you can find the published paper and its electronic addendum, including the database in excel format.
We published data sets from our studies at http://www.activitynet.org/ among others you can find reference data for gait phase detection and spatio-temporal gait parameters.
There is also the CASIA Gait Database from Center of Biometric and Security Research, which was gait surveillance in diverse conditions and many published papers based on it. You can access it via the following link: http://www.cbsr.ia.ac.cn/english/Gait%20Databases.asp
Gait MoCap database extracted from CMU data (50+ identities, 4000+ gait cycles) is freely available together with the software framework for evaluation at our web page http://gait.fi.muni.cz . For details have a look at listed publication, or ask.
And what features are lacking datasets preprocessed and posted on https://gait.fi.muni.cz ? They could be straightforwardly used for comparison with other ML methods.
We published datasets from our studies on Mendeley Data:
Horst, F., Lapuschkin, S., Samek, W., Müller, K.-R., & Schöllhorn, W. I. (2019). A public dataset of overground walking kinetics and full-body kinematics in healthy individuals. Mendeley Data, v2. http://dx.doi.org/10.17632/svx74xcrjr.2
Horst, F., Kramer, F., Schäfer, B., Eekhoff, A., Hegen, P., Nigg, B. M., & Schöllhorn, W. I. (2019). A public dataset of overground walking kinetics and lower-body kinematics in healthy adult individuals on different days. Mendeley Data, v1. http://dx.doi.org/10.17632/8kyv4jm759.1
Horst, F., Eekhoff, A., Newell, K. M., & Schöllhorn, W. I. (2019). A public dataset of overground walking kinetics and lower-body kinematics in healthy adult individuals on different sessions within one day. Mendeley Data, v1. http://dx.doi.org/10.17632/b48n46bfry.1
Horst, F., Mildner, M. & Schöllhorn, W. I. (2018). A public dataset of overground walking kinetics in healthy individuals. Mendeley Data, v1. http://dx.doi.org/10.17632/yrpbd8fhc4.1
We have started a normative collection project at Penn State Brandywine (PSB) and at Penn State Harrisburg (PSH) this last month. We will be publishing our updated tracked marker coordinates monthly at https://github.com/timniiler/gaitdata . There is nothing there now, but there should be by the end of June 2019. The data from PSB will, for the time being, include only 3D marker data from an 8 camera Motion Analysis Corporation system filming at 100 Hz, while the data from PSH will include data from an 8 camera Qualisys system, also set at 100 Hz and also forces. A total of 40 markers are used in an augmented Cleveland Clinic marker set. This is planned to be an on-going collection that will be renewed yearly. The age-group is to range from 18 to 65 and include both male and female subjects.
I need xy data of ankle,knee,hip in sagittal plane of walking on a treadmill,can any one send me excel file of data or introducing a link to download these data.
in attachment you can find an excel file with the data acquired (sampling frequency 60 Hz) from a healthy subject walking on a treadmill at 4.4 km/h.
Please, if you will use it, cite the following papers:
Rabuffetti M, Marzegan A, Crippa A, Carpinella I, Lencioni T, Castagna A, Ferrarin M. The LAMB gait analysis protocol: Definition and experimental assessment of operator-related variability. Proc Inst Mech Eng H. 2019 Mar;233(3):342-353.
Carpinella I, Crenna P, Rabuffetti M, Ferrarin M. Coordination between upper- and lower-limb movements is different during overground and treadmill walking. Eur J Appl Physiol. 2010 Jan;108(1):71-82.
We have recently published the following database of gait data: "Human kinematic, kinetic and EMG data during different walking and stair ascending and descending tasks". The data descriptor and associated dataset is freely available on Scientific Data Journal at the following link: https://www.nature.com/articles/s41597-019-0323-z
Have a look at this paper that presents a human gait data collection for analysis and activity recognition consisting of continues recordings of combined activities, such as walking, running, taking stairs up and down, sitting down, and so on; and the data recorded are segmented and annotated. Data were collected from a body sensor network consisting of six wearable inertial sensors (accelerometer and gyroscope) located on the right and left thighs, shins, and feet. Additionally, two electromyography sensors were used on the quadriceps (front thigh) to measure muscle activity.
Article HuGaDB: Human Gait Database for Activity Recognition from We...
In addition to Fabians post, we published a new gait dataset on Mendeley data:
Burdack, J., Horst, F., Giesselbach, S., Hassan, I., Daffner, S., & Schöllhorn, W. I. (2020). A public dataset of overground walking kinetics in healthy adult individuals on different sessions within one day. Mendeley Data, v2. http://dx.doi.org/10.17632/y55wfcsrhz.2
Article Systematic Comparison of the Influence of Different Data Pre...
Data A public dataset of overground walking kinetics in healthy a...
We published a dataset containg ground reaction force data of walking from 2084 patients with various musculoskeletal impairments and 211 healthy controls:
Horsak, B., Slijepcevic, D., Raberger, A. et al. GaitRec, a large-scale ground reaction force dataset of healthy and impaired gait. Sci Data 7, 143 (2020). https://doi.org/10.1038/s41597-020-0481-z
We published a database containg ground reaction force (GRF) and center of pressure (COP) data of two consecutive steps measured - by two force plates embedded in the ground - during level overground walking at self-selected walking speed. The "Gutenberg Gait Database" comprises data of 350 healthy individuals recorded in our laboratory over the past seven years:
Horst, F., Slijepcevic, D., Simak, M. et al. Gutenberg Gait Database, a ground reaction force database of level overground walking in healthy individuals. Sci Data 8, 232 (2021). https://doi.org/10.1038/s41597-021-01014-6
Additionally, the "Gutenberg Gait Database" [Article Gutenberg Gait Database, a ground reaction force database of...
] (see last post) can be used in conjunction with the "GaitRec Dataset" [
Article GaiTRec, a large-scale ground reaction force dataset of heal...
] (see the third last post). The pre-processing process as well as the data preparation and publishing format are identical. Merging the two datasets not only allows experiments and analyses on 2.645 subjects (2084 patients and 561 healthy subjects), but also leads to a balance of the data (since Gaitrec contains mainly pathological gait patterns and Gutenberg only data from healthy subjects).