CN106175778A - A kind of method setting up gait data collection and gait analysis method - Google Patents
A kind of method setting up gait data collection and gait analysis method Download PDFInfo
- Publication number
- CN106175778A CN106175778A CN201610517381.XA CN201610517381A CN106175778A CN 106175778 A CN106175778 A CN 106175778A CN 201610517381 A CN201610517381 A CN 201610517381A CN 106175778 A CN106175778 A CN 106175778A
- Authority
- CN
- China
- Prior art keywords
- gait
- data
- parameter
- data collection
- collection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/112—Gait analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
- A61B5/6804—Garments; Clothes
- A61B5/6807—Footwear
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6813—Specially adapted to be attached to a specific body part
- A61B5/6829—Foot or ankle
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physiology (AREA)
- Dentistry (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention provides a kind of method setting up gait data collection, including: 1) allow test person straight line moving in test zone, the sensing data gait data as this sample of current walking process sample is gathered with the wearable sensors being fixed on test person left foot and right crus of diaphragm；Described wearable sensors includes inertial sensor and sonic transducer；2) footprint stayed in video camera preset in described test zone and/or described test zone is utilized to draw the gait parameter of current walking process sample；3) by step 2) gait data of gait parameter labelling correspondence sample that drawn, thus obtain the gait data collection after labelling.Present invention also offers corresponding gait analysis method based on labeled data collection.The present invention is favorably improved the accuracy realizing accurate gait analysis based on wearable sensors；Having merged multi-modal data, the data set data volume obtained is big, classification is clear, convenient analysis and research.
Description
Technical field
The present invention relates to gait research and analysis technical field, specifically, the present invention relates to gait data acquisition and survey
Amount technical field.
Background technology
The analysis of gait and research are the comprehensive studies to human motion function, including to the measurement of human motion feature,
Describe and the assessment of quantity.By to the analysis of gait and research, gait cycle can be identified, calculate gait kinematics and
Kinetic parameter etc..In recent years, the research of gait all rises at aspects such as training, medical diagnosis on disease, rehabilitation medical, identifications
Very important effect and application are arrived.Such as, in some trainings, gait analysis can be applied to analyze athlete
Some problems occurred in the training process, then help them to deduct a percentage achievement；In medical diagnosis on disease, application gait analysis is sentenced
More disconnected orthopaedics or nervous system disease, such as apoplexy etc.；In rehabilitation medical, gait analysis can be applied to guard controlling of patient
More process；In biologic medical engineering, gait analysis has become as a kind of basic householder method to identify the motion feature of people；
In identification, different people is used as biometric identifier in the minor variations of gait style and identifies the people of individuality.
In sum, owing to gait analysis has a wide range of applications with research, researcher to be analyzed and to study,
It is accomplished by substantial amounts of gait data.The gait feature great majority of the disclosedest available gait data collection are all based on
Image.But, in dynamic environment, the image of shooting is blocked etc. many by illumination variation, the shadow of moving target, clothes
The impact of factor, brings bigger difficulty can to Method of Gait Feature Extraction based on image.
On the other hand, M.Hofmann et al. was published in the name of J.Vis.Commun.Imag e.Represent in 2014
For " The TUM gait from audio, image and depth (GAID) database:Multimodal
Recognition of subjects and traits " article in, disclose by Microsoft's Kinect instrument, it gathers people
The video of body gait, depth image and footsteps are as feature, and the method setting up data set.This scheme can pass through sound
Signal assists Method of Gait Feature Extraction based on image, but, it still cannot break away from illumination variation, the shadow of moving target, clothing
Clothes such as block at the restriction of the image to dynamic environment shooting.Further, in this scheme, sound signal collecting is also required to installation sound in advance
Sound pick device also debugs voice pickup environment.Therefore, the gait data collection obtained by this method is difficult to apply to people's
In gait data acquisition in daily life and analysis.
M.U.B.Altaf et al. was published in the entitled " Acoustic of IEEE Trans.Biomed.Eng in 2015
Gaits:Gait Analysis with Footstep Sounds " article in, disclose by preset 16 in room
Microphone array gathers footsteps and is acquired gait data as feature.The process employs sound as gait feature,
Need not gather the view data of gait, but for realize this gait data acquisition based on sound, need installation sound in advance
Sound pick device also debugs voice pickup environment.But, the environment residing for the daily behavior of people is difficult to such pacify in advance
Dress and debugging, this means that the gait data collection obtained by this method is difficult to apply to the gait data to people's daily life
In gathering and analyzing.
In sum, currently can support the gait data acquisition in the daily life of people and analysis in the urgent need to a kind of
Gait data collection build solution.
Summary of the invention
Therefore, it is an object of the invention to overcome the defect of above-mentioned prior art, it is provided that a kind of can support the day to people
Often the gait data collection of the gait data acquisition in life and analysis builds solution.
The invention provides a kind of method setting up gait data collection, comprise the following steps:
1) test person straight line moving in test zone, use is allowed to be fixed on the wearable sensors of test person left foot and right crus of diaphragm
Gather the sensing data gait data as this sample of current walking process sample；Described wearable sensors includes that inertia passes
Sensor and sonic transducer；
2) utilize the footprint stayed in video camera preset in described test zone and/or described test zone to draw to work as
The gait parameter of front walking process sample；Described gait parameter includes: gait distance parameter and time parameter, described gait distance
Parameter at least includes that step width and step-length, described time parameter include: the walking time, gait cycle, the support phase, shaking peroid, cadence,
Leg speed and step number；
3) by step 2) gait data of gait parameter labelling correspondence sample that drawn, thus obtain the gait after labelling
Data set.
Wherein, described step 1) in, described inertial sensor includes in accelerograph, gyroscope, geomagnetic sensor
Item or multinomial；Described sonic transducer includes mike or sonac.
Wherein, described step 1) in, described wearable sensors is fixed on the outside of the upper of a shoe of tested person, front side or rear side
Or the sole of tested person.
Wherein, described gait parameter also includes: step pitch, stride, single step time, support initial stage, support mid-term and support end
Phase.
Wherein, described step 2) in, the video camera preset in described test zone of described utilization draws gait parameter
Method includes: utilize the video camera being previously placed in described test zone shooting can follow the trail of regarding of tested person's walking process
Frequently, then by analyzing every two field picture, determine the initial time of various gait behavior, so obtain in described gait parameter time
Between parameter, described time parameter includes: single step time, gait cycle, support initial stage, supports mid-term, support in latter stage, shaking peroid
One or more.
Wherein, described step 2) in, the video camera preset in described test zone of described utilization draws gait parameter
Method also includes: lay readily identified coordinate (such as net in advance in the ground rectangular region being positioned on track route
The readily identified coordinate of trellis), in test person walking process, shoot with horizontal and vertical video camera simultaneously and walked
Journey, the described readily identified coordinate being then based in captured picture, identifies each step in walking process on the ground
Coordinate position, and then obtain the distance parameter in gait parameter.
Wherein, described step 2) in, described footprint includes the electronics footprint utilizing stress test plate to measure.
Wherein, described step 2) in, described utilize described test zone in the footprint that the stays method that draws gait parameter
Including: on test zone ground, spread one layer of thin powder in advance, or smear in advance at tested person's sole and easily leave obvious footprint
Pigment so that tested person walking after leave footprints on test zone ground, the most again by measure footprint draw step pitch, step
Width, step-length, stride and step number.
Wherein, described step 1) also include: the affiliated classification information of record tested person's walking process, described classification information
Including to the classification gathering main body: name, sex, height, body weight, age, normal person, abnormal gait people；To acquisition time
Classification: season, date, time；Classification to collecting location: indoor, outdoor；Classification to gathering main body wear shoes: move in the soft end
Footwear, hard-caked sediment sport shoes, leather shoes；Classification to gathering ground: wood floor, rock land face, hair/cotton carpet ground, face, soil.
The invention provides a kind of gait analysis method based on labeled data collection, including:
Step 100: obtaining the labeled data collection of body gait data, wherein, described gait data is integrally fixed at tested person
Sensing data in the walking process that the wearable sensors of foot is gathered, described labeled data is concentrated and is included multiple walking
The gait data of journey sample and the gait parameter corresponding to each walking process sample, described wearable sensors includes that inertia passes
Sensor and sonic transducer；
Step 200: setting up the mapping model from gait data to gait parameter, this reflects with described labeled data collection training
Penetrate model；
Step 300: utilize inertial sensor and the sonic transducer Real-time Collection tested person being fixed on current tested person foot
Gait data, be then based on surveyed gait data, based on training after mapping model draw the step that current tested person is current
State parameter.
Wherein, in described step 100, the previously described method setting up gait data collection is utilized to obtain body gait data
Labeled data collection.
Compared with prior art, it is an advantage of the current invention that:
1, the present invention can carry out dataset acquisition by wearable equipment, it is not necessary to pacifies in test environment in advance
Dress collecting device；
2, the present invention can use multiple mask method to mark wearable gait data accurately, thus obtains
Obtaining the data set precisely marked, this is favorably improved the accuracy realizing accurate gait analysis based on wearable sensors；
3, the present invention uses acoustical signal and inertial sensor to gather gait data, has merged multi-modal data, has been obtained
Data set data volume big, classification is clear, convenient analyze and research.
Accompanying drawing explanation
Embodiments of the present invention is further illustrated referring to the drawings, wherein:
Fig. 1 is the schematic diagram setting up gait data diversity method according to an embodiment of the invention；
Fig. 2 is that gait distance parameter according to an embodiment of the invention illustrates schematic diagram；
Fig. 3 is bowing of the high-definition camera photographed scene for carrying out time-labeling according to an embodiment of the invention
Depending on schematic diagram；
Fig. 4 is the schematic diagram being contained in advance on footwear by gait harvester according to an embodiment of the invention；With left foot
As a example by footwear, from left to right, before the position of gait harvester lays respectively at the outside of footwear, front side, rear side, bottom, in bottom, the end
Behind portion；
Fig. 5 is according to an embodiment of the invention gait harvester to be worn on the schematic diagram at ankle；With the right side
As a example by foot, from left to right, gait harvester is worn on the outside of ankle, rear side, front side respectively；
Fig. 6 shows the scene schematic diagram measuring gait parameter in one embodiment of the invention.
Detailed description of the invention
As it was noted above, in existing gait analysis technology, collecting device generally requires in default (typically room, region
In) install and debug, this causes the collection of gait data also can only complete in this specific region, therefore, it is difficult to daily to people
Gait in life is analyzed.Inventor overcomes drawbacks described above, by wearable inertial sensor and sonic transducer (such as wheat
Gram wind or sonac) combination introduce in gait analysis technology, thus realize the analysis to the gait in people's daily life.
With detailed description of the invention, the present invention is elaborated below in conjunction with the accompanying drawings.
According to one embodiment of present invention, it is provided that a kind of based on wearable sonic transducer with the step of inertial sensor
The construction method of state data set.Data set constructed by the method has merged multi-modal data, the number in the data set obtained
, classification big according to amount clearly, is conveniently analyzed and research.Meanwhile, wearable of sonic transducer, inertial sensor etc. is also overcomed
Some inherent shortcomings of body, so that being analyzed being possibly realized to the gait in people's daily life.
Currently, inertial sensor is widely used in counting in step technology, but, gait analysis needs the gait ginseng obtained
Number requires higher precision, and owing to the cumulative errors problem that inertial sensor is intrinsic cannot inherently eliminate, therefore, existing
Technology also directly cannot calculate accurate gait parameter by inertial sensor data.In the present embodiment, introduce mike and carry out
The collection of voice data, mike is small and exquisite, cheap, is especially suitable for coordinating wearable relevant smart machine to use.Exist at both feet
During walking, footsteps ratio is more visible and reliable, by the detection to footsteps, can accurately judge some times that gait is walked
Parameter (such as single step cycle, walking period, swing initial stage, zero-speed detection etc.).So, by combining the step sound number of mike
According to analysis, can largely eliminate and improve conventional inertia sensor and carry out the cumulative errors of introducing during gait analysis.
Fig. 1 shows the schematic diagram of the construction method of the gait data collection of the present embodiment, the structure side of this gait data collection
Method comprises the following steps:
Step 101: allow test person straight line moving in test zone, utilizes wearable sensors and traditional gait collection
Device, synchronous acquisition wearable sensors data and tradition gait information.In this step, wearable sensors include mike and
Inertial sensor, wherein inertial sensor includes accelerograph, gyroscope, geomagnetic sensor etc..
In one embodiment, according to concrete collection situation, the sample gathered can be classified.Such as, main to gathering
Body is classified: name, sex, height, body weight, age, normal person, abnormal gait people；To acquisition time classify: season, the date, time
Between；Collecting location is classified: indoor, outdoor；To gathering the classification of main body wear shoes: sport shoes (the soft end), sport shoes (hard-caked sediment), skin
Footwear；To gathering ground classification: wood floor, rock land face, hair/cotton carpet ground, face, soil.Can be by all or part of
State classification information flag on the sample of the wearable sensors gait data gathered, thus be that follow-up gait analysis works
There is provided and preferably support.
In one example, the harvester being used for gathering gait data at least includes: mike and inertial sensor (example
As, accelerograph, gyroscope, geomagnetic sensor etc.).Wherein, harvester wearing mode can be that left and right both feet are worn simultaneously.
By using two gait data acquisition device nodes on biped simultaneously, it is analyzed the data of left and right foot merging, permissible
Obtain than monopodia metering system information more accurately.Concrete, the diverse location that can be contained in footwear by harvester is (with reference to figure
Shown in 4, typically it is contained in shoe lining in advance when producing footwear) or be worn at both feet ankle (with reference to shown in Fig. 5).In the present embodiment,
Harvester is worn in the symmetric position of left and right foot.
As shown in Figure 4 and Figure 5, when carrying out gait data acquisition, acquisition node (device) can be worn on two respectively
On foot or left and right foot is worn by the shoes of pre-implantation acquisition node respectively.
In Fig. 4 and Fig. 5, a represents gait harvester, and b represents elastic bandage, is used for fixing harvester, the most favourable
In the comfort level that user dresses.For wearing mode as shown in Figure 4, after both feet are worn by, can as required shoes be worn
Tightly, shoes are made not to be moved on foot.During owing to gait harvester is worn on inside ankle, may be to normal walking
Bring impact, and then affect gait and the gait parameter collected, therefore gait harvester can be worn on outside ankle,
Rear side and front side.
For wearing mode as shown in Figure 5, after both feet are worn by, elastic bandage can be adjusted as required so that it is tight
Fasten at foot, be not moved.When gait harvester is contained in footwear in advance, before harvester may be located at upper of a shoe
Side, outside, rear side and sole.
Before the experiment gathering body gait data starts, can optionally carry out following preparation:
S1-0a: the personal information of record subjects, can such as include: name, sex, height, body weight, age, whether
It is diagnosed as abnormal gait people by regular medical institutions.
S1-0b: record collecting location: indoor, outdoor.Owing to the present invention uses the multisensor of fusion acoustical signal
Gather gait data method, so in order to reduce the interference to the data gathered, when choosing testing location, should try one's best
Avoid the place that environment is noisy.
S1-0c: record acquisition time: season, date, time (specific to when).Should be understood that in different seasons
Joint, owing to human body dress is different, dress up difference, health bears a heavy burden equal factor, more or less can affect body gait.Other one
Periods different in it, food and drink, daily life etc. are also possible to affect body gait.
S1-0e: record collection main body wear shoes: sport shoes (the soft end), sport shoes (hard-caked sediment), leather shoes.
S1-0f: record collection ground: wood floor, rock land face, hair/cotton carpet ground, face, soil.
Step 102: utilize the high-definition camera being previously placed in described test zone shooting can follow the trail of tested People's Bank of China
Walk the video of process or utilize tested person to walk left footprint, by manually distinguishing or passing through Computer Automatic Recognition
Technology draws the gait parameter of tested person's walking process sample from this video and footprint.In the present embodiment, gait parameter is permissible
Including with one or more in Types Below: when step pitch, step width, step-length, stride, step number, cadence, leg speed, walking distance, walking
Between, the single step time, gait cycle, the support initial stage (including the support initial stage of left and right foot), support mid-term (include left and right foot
Support mid-term), support latter stage (including the support latter stage of left and right foot), shaking peroid (including the shaking peroid of left and right foot).Fig. 2 shows
The schematic diagram of the gait distance parameter in the present embodiment.Wherein, gait distance parameter includes: step pitch, step width, step-length, stride etc..
For distance parameter and step number, can be measured by tested person's left footprint of walking.Can be in advance on test zone ground
On spread one layer of thin powder (such as flour or pulverized limestone), or smear the face easily leaving obvious footprint in advance at tested person's sole
Material so that test zone leaves footprints on ground, draws step pitch, step width, step-length, stride and step by measurement footprint the most again
Number.Certainly, the method for above-mentioned measurement distance parameter is not unique, in another embodiment, it is also possible to use specialty pressure
Test board measures distance parameter.And for time parameter, such as cadence, leg speed, walking distance, the walking time, the single step time,
Gait cycle, support initial stage (including the support initial stage of left and right foot), support mid-term (including the support mid-term of left and right foot), support
Latter stage (including the support latter stage of left and right foot), shaking peroid (including the shaking peroid of left and right foot) etc., it is possible to use high-definition camera
Shooting, by analyzing every two field picture, and then determines the initial time of gait behavior, and then obtains above-mentioned time parameter.At another
In individual embodiment, the support initial stage in above-mentioned time parameter can be replaced with the support phase, support mid-term and support latter stage.Support
Phase is to the integrated support period supporting finish time in latter stage from the start time at the initial stage of support.
In described test zone, can arrange that horizontal and vertical high-definition camera (sometimes referred to simply as video camera) arrives in advance
Precalculated position so that below double-legged ankle complete in gait processes and ankle can be photographed at high-definition camera whole.Fig. 3
Show the schematic top plan view of the high-definition camera photographed scene for carrying out time-labeling in the present embodiment.As it is shown on figure 3,
Wherein: v represents the vertical dimension of longitudinal video camera distance walking walking line (i.e. Walking Route)；When l represents collection gait parameter
Walking distance.The distance of v and l, should make in the case of high-definition camera does not moves and rotates, it is possible to photograph step
Double-legged ankle complete during row and ankle are with lower part.Lateral camera is the static shooting along the shooting of walking direction
Machine, as shown in Figure 3.
When it may be noted that if tested person's walking process is beyond the scope of the l shown in Fig. 3, longitudinal video camera is it is possible to difficulty
Walking information with accurate recording people.Therefore, in order to increase the scope shot of longitudinal video camera, in another embodiment
In, longitudinal video camera can be arranged on the track parallel with walking direction so that longitudinal video camera can with tested person
Walking speed same speed is followed this tested person and is moved, so that this longitudinal direction video camera can photograph walking all the time
During complete double-legged ankle and ankle with lower part.Further, for the ease of computer identification, involved by walking circuit
Horizontal and vertical line (or coordinate) is drawn in advance on the ground in region, when drawing horizontal and vertical line (or coordinate), adjacent two
Distance between bar line is unsuitable excessive, in order to avoid causing later stage mark to introduce more multiple error.So, in tested person's gait processes,
Gather image by horizontal and vertical high-definition camera, then mark in the moment corresponding to each two field picture and identify this frame
Position in left and right foot coordinate-system on the ground in image, and then draw gait parameter accurately.Fig. 6 shows based on this reality
Executing the scene schematic diagram measuring gait parameter of example, with reference to Fig. 6, gait parameter concrete in this embodiment measures process
As follows: one, the ground in being positioned at track route rectangular region draw grid (in Fig. 6, the long 5.0m of rectangular region, wide
0.8 meter.Having demarcated coordinate system on the ground, with horizontal and vertical high-definition camera shooting, the two high-definition camera can be used for marking
Note gait time parameter and gait distance parameter), this Rectangular grid is many by the straight cuts in length and breadth of different colours
Individual little square (square of such as 5cm × 5cm), is thus equivalent to having drawn on the ground one the biggest readily identified
Coordinate, so that the maximum error of measured estimation gait distance parameter controls within 2-3cm.People is at this rectangle net
On lattice in the walking process of normal walking, use the high-definition camera of vertical and horizontal to shoot simultaneously, described grid can be relied on
Auxiliary, from captured image, obtain the distance parameter as labeled data easily.Specifically, one can be determined on the ground
Zero, can be clearly seen that each step of walking on the ground from the image (one by one) of high-definition camera shooting
Coordinate position, and then distance parameter can be marked out.
Further, table 1 gives the definition of various gait parameter, and some methods obtaining gait parameter.
Table 1
In sum, in above-described embodiment, stayed by the video capture device arranged in advance and being prone to of arranging in advance
The collection measure of footprint, obtains and can follow the trail of the footprint that stays after the video of tested person's walking process and test, by manually
Measure or Computer Automatic Recognition technology, draw the gait parameter that gathered gait data sample is corresponding.It is prone to leave foot
The collection measure of print can be interpreted broadly, such as, the stress test plate of specialty can be used to obtain the electronics in tested person's walking process
Footprint information, draws the gait parameter of correspondence the most again based on this electronic foot official seal breath.
In step 102, the gait parameter drawn can be considered result measured directly, and accuracy is high, therefore can be used for marking
Noting described gait data (sensing data based on wearable sensors of step 101 gained), therefore these gait parameters also may be used
It is referred to as labeled data.
Step 103: after drawing the gait parameter that gathered sample data is corresponding is right with the gait parameter mark drawn
The wearable sensors gait data answered, thus the sample data (being referred to as in FIG storing data) after being marked.
Repeat above-mentioned steps 101～103, the labeled data of sample based on wearable sensors data can be obtained
Collection, the sample data gathered including wearable sensors and the mark to this sample data, this mark includes a series of table
Levy the gait parameter of gait information.In one example, these sample datas and the gait feature being made up of gait parameter are vectorial
(can be described as the gait feature vector of sample data) one_to_one corresponding, thus convenient inquiry.
In above-described embodiment, labeled data collection uses acoustical signal and inertial sensor to be acquired gait data, merges
Multi-modal data, data volume in the data set obtained is big, classification is clear, convenient analyze and research；Meanwhile, use multiple
Gait data is marked by mask method accurately, can obtain and mark accurately for data set.
Further, according to another embodiment of the present invention, a kind of gait based on above-mentioned labeled data collection is additionally provided
Analysis method, including:
Step 100: set up the labeled data collection of the body gait data gathered based on multiple wearable sensors, these data
Collection at least includes sample data that wearable sensors gathers and the mark to this sample data, and this mark includes a series of sign
The gait parameter of gait information.In the present embodiment, described multiple wearable sensors includes inertial sensor and sonic transducer,
When gathering gait data, they are all deployed in the foot of tested person.
Step 200: setting up the mapping model from gait data to gait parameter, this reflects with described labeled data collection training
Penetrate model.Mapping model in this step is a kind of plan merged based on multisensor (including inertial sensor and sonic transducer)
Mapping model slightly.Specifically, it is simply that the gait data as this mapping model input data includes inertial sensor gait
Data harmony sensing data.Inventor studies discovery, if relying on simple inertial sensor data to detect gait parameter
Time, more missing inspection can be caused due to walking habits such as the weight speeds of the step of wearer；And simple dependence sonic transducer
When data detect gait parameter, more false retrieval can be caused due to the body weight dressed, speed etc. of walking.Therefore the present embodiment
In, when setting up the mapping model from labeled data to gait parameter, when training this model, have employed fusion both sensings
The strategy of device data, such inertial sensor gait data harmony sensing data can supply a gap mutually.
Mapping model in this step can be BP neural network model or SVM supporting vector machine model.BP nerve net
Network refers to document: Learning internal representations by back-propagating errors, DE
Rumelhart, GE Hinton, RJ Williams-" Nature " 1986；SVM support vector machine refers to document:
P.H.Chen,C.J.Lin,and B.A tutorial onν-support vector machines,
Appl.Stoch.Models.Bus.Ind.2005,21,111-136.。
Step 300: utilize inertial sensor and the step of sonic transducer Real-time Collection tested person being deployed in tested person foot
State data, are then based on surveyed gait data, draw, based on the mapping model after training, the gait parameter that tested person is current.
Above-mentioned gait analysis scheme can carry out gait data acquisition by wearable equipment, it is not necessary to is surveying in advance
Test ring border is installed collecting device, thus has widened the application of gait analysis, make the gait in people's daily life is carried out
Gather and analysis is possibly realized.Further, preliminary test shows, mapping model based on convergence strategy compare single type sensing
The mapping model of device has higher accurate rate and recall rate.Wherein, accurate rate can improve about 10%, and recall rate can improve about
10%.
It should be noted last that, above example is only in order to illustrate technical scheme and unrestricted.On although
The present invention has been described in detail by literary composition with reference to embodiment, it will be understood by those within the art that, the skill to the present invention
Art scheme is modified or equivalent, and without departure from the spirit and scope of technical solution of the present invention, it all should be contained at this
In the middle of the right of invention.
Claims (10)
1. the method setting up gait data collection, comprises the following steps:
1) test person straight line moving in test zone, use is allowed to be fixed on the wearable sensors collection of test person left foot and right crus of diaphragm
The sensing data of current walking process sample is as the gait data of this sample；Described wearable sensors includes inertial sensor
And sonic transducer；
2) footprint stayed in video camera preset in described test zone and/or described test zone is utilized to draw current line
Walk the gait parameter of process sample；Described gait parameter includes: gait distance parameter and time parameter, described gait distance parameter
At least include that step width and step-length, described time parameter include: walking time, gait cycle, support phase, shaking peroid, cadence, leg speed
And step number；
3) by step 2) gait data of gait parameter labelling correspondence sample that drawn, thus obtain the gait data after labelling
Collection.
The method setting up gait data collection the most according to claim 1, it is characterised in that described step 1) in, described used
It is one or more that property sensor includes in accelerograph, gyroscope, geomagnetic sensor；Described sonic transducer include mike or
Sonac.
The method setting up gait data collection the most according to claim 2, it is characterised in that described step 1) in, described can
Dress sensor and be fixed on the outside of upper of a shoe, front side or rear side or the sole of tested person of tested person.
The method setting up gait data collection the most according to claim 1, it is characterised in that described gait parameter also includes:
Step pitch, stride, the single step time, support the initial stage, support mid-term and support latter stage.
The method setting up gait data collection the most according to claim 4, it is characterised in that described step 2) in, described profit
Video camera preset in being used in described test zone show that the method for gait parameter includes: utilizes and is previously placed at described test section
Video camera shooting in territory can follow the trail of the video of tested person's walking process, then by analyzing every two field picture, determines various step
The initial time of state behavior, and then obtain the time parameter in described gait parameter, described time parameter includes: the single step time,
Gait cycle, support the initial stage, support mid-term, support in latter stage, shaking peroid one or more.
The method setting up gait data collection the most according to claim 5, it is characterised in that described step 2) in, described profit
Video camera preset in being used in described test zone show that the method for gait parameter also includes: on the ground being positioned on track route
On rectangular region lay readily identified coordinate in advance, in test person walking process, with horizontal and vertical video camera
Shoot walking process simultaneously, the described readily identified coordinate being then based in captured picture, identifies in walking process
Each step coordinate position on the ground, and then obtain the distance parameter in gait parameter.
The method setting up gait data collection the most according to claim 4, it is characterised in that described step 2) in, described profit
Show that the method for gait parameter includes with the footprint stayed in described test zone: utilize stress test plate to measure electronics footprint,
Step pitch, step width, step-length, stride and step number is drawn the most again by measurement footprint；Or on test zone ground, spread one in advance
The thin powder of layer, or the pigment easily leaving obvious footprint is smeared in advance at tested person's sole so that in test after tested person's walking
Leave footprints on localized ground, draw step pitch, step width, step-length, stride and step number by measurement footprint the most again.
The method setting up gait data collection the most according to claim 4, it is characterised in that described step 1) also include: note
Record tested person's walking process affiliated classification information, described classification information include to gather main body classification: name, sex,
Height, body weight, age, normal person, abnormal gait people；Classification to acquisition time: season, date, time；To collecting location
Classification: indoor, outdoor；Classification to gathering main body wear shoes: the sport shoes of the soft end, hard-caked sediment sport shoes, leather shoes；Divide gathering ground
Class: wood floor, rock land face, hair/cotton carpet ground, face, soil.
9. a gait analysis method based on labeled data collection, including:
Step 100: obtaining the labeled data collection of body gait data, wherein, described gait data is integrally fixed at tested person foot
The walking process that gathered of wearable sensors in sensing data, described labeled data is concentrated and is included multiple walking process sample
Gait data originally and the gait parameter corresponding to each walking process sample, described wearable sensors includes inertial sensor
And sonic transducer；
Step 200: set up the mapping model from gait data to gait parameter, with described this mapping mould of labeled data collection training
Type；
Step 300: utilize inertial sensor and the step of sonic transducer Real-time Collection tested person being fixed on current tested person foot
State data, are then based on surveyed gait data, draw, based on the mapping model after training, the gait ginseng that current tested person is current
Number.
Gait analysis method based on labeled data collection the most according to claim 9, it is characterised in that described step 100
In, utilize the method setting up gait data collection according to any one of claim 1～8 to obtain the mark number of body gait data
According to collection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610517381.XA CN106175778B (en) | 2016-07-04 | 2016-07-04 | A kind of method that establishing gait data collection and gait analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610517381.XA CN106175778B (en) | 2016-07-04 | 2016-07-04 | A kind of method that establishing gait data collection and gait analysis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106175778A true CN106175778A (en) | 2016-12-07 |
| CN106175778B CN106175778B (en) | 2019-02-01 |
Family
ID=57465776
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610517381.XA Active CN106175778B (en) | 2016-07-04 | 2016-07-04 | A kind of method that establishing gait data collection and gait analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106175778B (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016346A (en) * | 2017-03-09 | 2017-08-04 | 中国科学院计算技术研究所 | gait identification method and system |
| CN107170466A (en) * | 2017-04-14 | 2017-09-15 | 中国科学院计算技术研究所 | The sound detection method that mops floor based on audio |
| CN107403143A (en) * | 2017-07-06 | 2017-11-28 | 广东小天才科技有限公司 | Gait recognition method and electronic equipment |
| CN107696921A (en) * | 2017-08-30 | 2018-02-16 | 重庆延锋安道拓汽车部件***有限公司 | Automotive seat regulating system and its control method |
| CN108030497A (en) * | 2018-01-16 | 2018-05-15 | 大连乾函科技有限公司 | A kind of gait analysis devices and methods therefor based on IMU inertial sensors |
| CN109009148A (en) * | 2018-08-24 | 2018-12-18 | 广东工业大学 | A kind of gait function appraisal procedure |
| CN109452728A (en) * | 2017-04-12 | 2019-03-12 | 佛山市丈量科技有限公司 | A kind of Intelligent insole and its step size computation method based on step size computation |
| CN109528212A (en) * | 2018-12-29 | 2019-03-29 | 大连乾函科技有限公司 | A kind of abnormal gait identification device and method |
| CN109646011A (en) * | 2018-10-15 | 2019-04-19 | 王长贵 | A kind of voltage inductance answers compound tile |
| CN109745055A (en) * | 2018-08-10 | 2019-05-14 | 柳州泽屹科技有限公司 | The terraced detection system of intelligent rehabilitation training and detection method |
| CN110123330A (en) * | 2019-05-20 | 2019-08-16 | 浙江大学 | Foot type parameter measurement and pressure cloud atlas generation method based on plantar pressure data |
| CN110210392A (en) * | 2019-05-31 | 2019-09-06 | 吉林化工学院 | A kind of Gait Recognition device based on probability theory |
| CN110236550A (en) * | 2019-05-30 | 2019-09-17 | 清华大学 | A kind of body gait prediction meanss based on multi-modal deep learning |
| CN110916970A (en) * | 2019-11-18 | 2020-03-27 | 南京伟思医疗科技股份有限公司 | Device and method for realizing cooperative motion of weight-reducing vehicle and lower limb robot through communication |
| CN111028374A (en) * | 2019-10-30 | 2020-04-17 | 中国科学院自动化研究所南京人工智能芯片创新研究院 | Attendance machine and attendance system based on gait recognition |
| CN111079651A (en) * | 2019-12-17 | 2020-04-28 | 河南水滴智能技术有限公司 | Re-optimization of gait classification method |
| CN111178338A (en) * | 2020-03-18 | 2020-05-19 | 福建中医药大学 | Method for establishing database and standardized model in gait analysis system |
| CN112472531A (en) * | 2020-12-17 | 2021-03-12 | 大连理工大学 | Gait smoothing algorithm of lower limb exoskeleton robot for medical rehabilitation and assisted walking |
| TWI737237B (en) * | 2020-03-25 | 2021-08-21 | 國泰醫療財團法人國泰綜合醫院 | Measuring system for measuring foot's inertial information |
| CN114052724A (en) * | 2022-01-13 | 2022-02-18 | 西安交通大学医学院第一附属医院 | Orthopedics traction abnormity detection system based on artificial intelligence |
| CN114267088A (en) * | 2022-03-02 | 2022-04-01 | 北京中科睿医信息科技有限公司 | Gait information processing method and device and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6836744B1 (en) * | 2000-08-18 | 2004-12-28 | Fareid A. Asphahani | Portable system for analyzing human gait |
| CN102243687A (en) * | 2011-04-22 | 2011-11-16 | 安徽寰智信息科技股份有限公司 | Physical education teaching auxiliary system based on motion identification technology and implementation method of physical education teaching auxiliary system |
| CN104729507A (en) * | 2015-04-13 | 2015-06-24 | 大连理工大学 | Gait recognition method based on inertial sensor |
| US20150257679A1 (en) * | 2011-03-24 | 2015-09-17 | MedHab, LLC | System and method for monitoring a runner's gait |
-
2016
- 2016-07-04 CN CN201610517381.XA patent/CN106175778B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6836744B1 (en) * | 2000-08-18 | 2004-12-28 | Fareid A. Asphahani | Portable system for analyzing human gait |
| US20150257679A1 (en) * | 2011-03-24 | 2015-09-17 | MedHab, LLC | System and method for monitoring a runner's gait |
| CN102243687A (en) * | 2011-04-22 | 2011-11-16 | 安徽寰智信息科技股份有限公司 | Physical education teaching auxiliary system based on motion identification technology and implementation method of physical education teaching auxiliary system |
| CN104729507A (en) * | 2015-04-13 | 2015-06-24 | 大连理工大学 | Gait recognition method based on inertial sensor |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016346A (en) * | 2017-03-09 | 2017-08-04 | 中国科学院计算技术研究所 | gait identification method and system |
| CN109452728A (en) * | 2017-04-12 | 2019-03-12 | 佛山市丈量科技有限公司 | A kind of Intelligent insole and its step size computation method based on step size computation |
| CN107170466A (en) * | 2017-04-14 | 2017-09-15 | 中国科学院计算技术研究所 | The sound detection method that mops floor based on audio |
| CN107170466B (en) * | 2017-04-14 | 2020-12-29 | 中国科学院计算技术研究所 | Mopping sound detection method based on audio |
| CN107403143A (en) * | 2017-07-06 | 2017-11-28 | 广东小天才科技有限公司 | Gait recognition method and electronic equipment |
| CN107696921A (en) * | 2017-08-30 | 2018-02-16 | 重庆延锋安道拓汽车部件***有限公司 | Automotive seat regulating system and its control method |
| CN107696921B (en) * | 2017-08-30 | 2020-06-12 | 重庆延锋安道拓汽车部件***有限公司 | Automobile seat adjusting system and control method thereof |
| CN108030497B (en) * | 2018-01-16 | 2023-12-19 | 大连乾函科技有限公司 | Gait analysis device and method based on IMU inertial sensor |
| CN108030497A (en) * | 2018-01-16 | 2018-05-15 | 大连乾函科技有限公司 | A kind of gait analysis devices and methods therefor based on IMU inertial sensors |
| CN109745055A (en) * | 2018-08-10 | 2019-05-14 | 柳州泽屹科技有限公司 | The terraced detection system of intelligent rehabilitation training and detection method |
| CN109009148A (en) * | 2018-08-24 | 2018-12-18 | 广东工业大学 | A kind of gait function appraisal procedure |
| CN109646011A (en) * | 2018-10-15 | 2019-04-19 | 王长贵 | A kind of voltage inductance answers compound tile |
| CN109528212B (en) * | 2018-12-29 | 2023-09-19 | 大连乾函科技有限公司 | Abnormal gait recognition equipment and method |
| CN109528212A (en) * | 2018-12-29 | 2019-03-29 | 大连乾函科技有限公司 | A kind of abnormal gait identification device and method |
| CN110123330A (en) * | 2019-05-20 | 2019-08-16 | 浙江大学 | Foot type parameter measurement and pressure cloud atlas generation method based on plantar pressure data |
| CN110236550A (en) * | 2019-05-30 | 2019-09-17 | 清华大学 | A kind of body gait prediction meanss based on multi-modal deep learning |
| CN110210392A (en) * | 2019-05-31 | 2019-09-06 | 吉林化工学院 | A kind of Gait Recognition device based on probability theory |
| CN110210392B (en) * | 2019-05-31 | 2022-12-09 | 吉林化工学院 | Gait recognition device based on probability theory |
| CN111028374A (en) * | 2019-10-30 | 2020-04-17 | 中国科学院自动化研究所南京人工智能芯片创新研究院 | Attendance machine and attendance system based on gait recognition |
| CN111028374B (en) * | 2019-10-30 | 2021-09-21 | 中科南京人工智能创新研究院 | Attendance machine and attendance system based on gait recognition |
| CN110916970A (en) * | 2019-11-18 | 2020-03-27 | 南京伟思医疗科技股份有限公司 | Device and method for realizing cooperative motion of weight-reducing vehicle and lower limb robot through communication |
| CN111079651A (en) * | 2019-12-17 | 2020-04-28 | 河南水滴智能技术有限公司 | Re-optimization of gait classification method |
| CN111178338A (en) * | 2020-03-18 | 2020-05-19 | 福建中医药大学 | Method for establishing database and standardized model in gait analysis system |
| TWI737237B (en) * | 2020-03-25 | 2021-08-21 | 國泰醫療財團法人國泰綜合醫院 | Measuring system for measuring foot's inertial information |
| CN112472531A (en) * | 2020-12-17 | 2021-03-12 | 大连理工大学 | Gait smoothing algorithm of lower limb exoskeleton robot for medical rehabilitation and assisted walking |
| CN114052724A (en) * | 2022-01-13 | 2022-02-18 | 西安交通大学医学院第一附属医院 | Orthopedics traction abnormity detection system based on artificial intelligence |
| CN114052724B (en) * | 2022-01-13 | 2022-09-09 | 西安交通大学医学院第一附属医院 | Orthopedics traction abnormity detection system based on artificial intelligence |
| CN114267088A (en) * | 2022-03-02 | 2022-04-01 | 北京中科睿医信息科技有限公司 | Gait information processing method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106175778B (en) | 2019-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106175778B (en) | A kind of method that establishing gait data collection and gait analysis method | |
| US10314520B2 (en) | System and method for characterizing biomechanical activity | |
| CN107174255B (en) | Three-dimensional gait information acquisition and analysis method based on Kinect somatosensory technology | |
| US9700241B2 (en) | Gait analysis system and method | |
| CN104126185A (en) | Fatigue indices and uses thereof | |
| JP6444813B2 (en) | Analysis system and analysis method | |
| CN106667493A (en) | Human body balance assessment system and assessment method | |
| US11559261B2 (en) | Gait motion display system and program | |
| JP6505614B2 (en) | Training classification system, training classification method and training classification server | |
| CN109171734A (en) | Human body behavioural analysis cloud management system based on Fusion | |
| CN105125216A (en) | Gait detection system based on sole pressure | |
| CN107644229A (en) | Indoor anomaly detection method based on multi-sensor information fusion | |
| JP6127873B2 (en) | Analysis method of walking characteristics | |
| CN108814617A (en) | Freezing of gait recognition methods and device and gait detector | |
| WO2016149832A1 (en) | Systems, methods and devices for exercise and activity metric computation | |
| CN106073793A (en) | Attitude Tracking based on micro-inertia sensor and recognition methods | |
| Cai et al. | Single-camera-based method for step length symmetry measurement in unconstrained elderly home monitoring | |
| CN113768471B (en) | Parkinson disease auxiliary diagnosis system based on gait analysis | |
| CN107692984A (en) | A kind of fatigue detection method and device | |
| Nouredanesh et al. | Chasing feet in the wild: a proposed egocentric motion-aware gait assessment tool | |
| WO2013084031A1 (en) | System for motion tracking and comparison | |
| US20230316620A1 (en) | System and method for generating a virtual avatar | |
| McCalmont et al. | eZiGait: toward an AI gait analysis and sssistant system | |
| Abhayasinghe et al. | A novel approach for indoor localization using human gait analysis with gyroscopic data | |
| Meigal et al. | Analysis of human gait based on smartphone inertial measurement unit: a feasibility study |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20161207 Assignee: Beijing Zhongke Huicheng Technology Co., Ltd. Assignor: Institute of Computing Technology, Chinese Academy of Sciences Contract record no.: 2018110000005 Denomination of invention: Method for establishing gait data set and gait analysis method License type: Common License Record date: 20180222 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EC01 | Cancellation of recordation of patent licensing contract |
Assignee: Beijing Zhongke Huicheng Technology Co., Ltd. Assignor: Institute of Computing Technology, Chinese Academy of Sciences Contract record no.: 2018110000005 Date of cancellation: 20180309 |
|
| EC01 | Cancellation of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20161207 Assignee: Luoyang Zhongke Huicheng Technology Co., Ltd. Assignor: Institute of Computing Technology, Chinese Academy of Sciences Contract record no.: 2018110000009 Denomination of invention: Method for establishing gait data set and gait analysis method License type: Common License Record date: 20180319 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |