CN104713568A - Gait recognition method and corresponding pedometer - Google Patents
Gait recognition method and corresponding pedometer Download PDFInfo
- Publication number
- CN104713568A CN104713568A CN201510153005.2A CN201510153005A CN104713568A CN 104713568 A CN104713568 A CN 104713568A CN 201510153005 A CN201510153005 A CN 201510153005A CN 104713568 A CN104713568 A CN 104713568A
- Authority
- CN
- China
- Prior art keywords
- gait
- signal
- current
- sensitive axes
- value
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C22/00—Measuring distance traversed on the ground by vehicles, persons, animals or other moving solid bodies, e.g. using odometers, using pedometers
- G01C22/006—Pedometers
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The embodiment of the invention discloses a gait recognition method and a corresponding pedometer. The gait recognition method comprises the following steps: acquiring acceleration signals during wrist movement, wherein the acceleration signals comprise a first sensitive shaft signal and a second sensitive shaft signal; selecting one of the first sensitive shaft signal and the second sensitive shaft signal as the current gait recognition signal according to the moving state of the previous gait; determining whether the current gait is complete or not by judging the conversion between a wave peak section and a wave trough section of the current gait recognition signal based on the dynamic threshold value preset for the previous gait. The gait recognition method is capable of effectively recognizing running and other walking modes, thus improving the step-counting accuracy.
Description
Technical field
Each embodiment of the present disclosure relates to passometer field, relates more specifically to a kind of gait recognition method and corresponding passometer.
Background technology
Along with the reinforcement of health of people consciousness, people focus on the amount of exercise in daily routines more.Passometer, as a kind of small-sized exercise equipment, can help people to record amount of exercise and the energy ezpenditure of every day, for people assess amount of exercise whether up to standard and help people formulate more reasonably fitness program.
The pattern of walking generally comprises five kinds of motions: static, walking, upstairs, downstairs, running.When counting step process, if can effectively distinguish difference to walk line state, the degree of accuracy of meter step must be improved.In general, run to walk line state with other all there is significant difference in cadence and energy ezpenditure.Identifying rapidly and accurately runs walks line state with other, can improve accuracy when gait counting and the calculating of motion consumed energy.
In prior art, publication number is propose in the patent of CN101881625A to judge to walk or run by the amplitude range of resultant acceleration, there is such problem in the method: when people walks fast, swing arm frequency also synchronously improves, arm increases at the changing value of the acceleration of motion of fore-and-aft direction and vertical direction, this has an impact to the amplitude of resultant acceleration, causes hurrying up being identified as running.Publication number is propose in the patent of US20140074431 to judge to walk or run according to the frequency range of resultant acceleration signal, still there is the problem be easily erroneously identified of jogging and hurry up in the method.
And be in the patent of CN104075730A at publication number, propose the acceleration change amount according to maximum variable quantity acceleration axle and vertically over glaze, judge motion state and Gait Recognition.Axially judge whether with the difference of another axial acceleration changing value to need to change meter step scheme by peak acceleration change, the method Problems existing is: its each striding carries out a moving state identification, and the motion process of people has continuation, moving state identification easily produces error too frequently, and this invention is not analyzed issuable meter step error, and and then meter step compensation scheme is proposed.
Summary of the invention
For the deficiencies in the prior art, one of object of the present disclosure is to provide a kind of gait recognition method of improvement and corresponding passometer.
By the gait recognition method that the disclosure is improved, may be used for effectively identifying and run and other patterns of walking, and be applied to Gait Recognition and meter step, wherein Gait Recognition process at least can comprise the identification of judgement, the effectively gait of complete gait, and walks based on the meter that effective gait is carried out and the compensation of meter step.
Wherein, the inventive concept of gait recognition method of the present disclosure is mainly according to motion continuation principle, the motion Gait Recognition of a time period (such as latter one second) after the motion state that previous time period (such as last second) identifies being applied to; According to motion state, corresponding dynamic threshold is set for identifying gait parameter; And when identifying motion state and occurring to change, optionally need carry out meter step and compensate.Due under correct motion state, the dynamic threshold setting in Gait Recognition process will be more accurate, and meter step result is also more accurate.
Therefore, according to first aspect of the present disclosure, provide a kind of gait recognition method, comprise the following steps: gather acceleration signal during wrist motion, described acceleration signal comprises the first sensitive axes signal and the second sensitive axes signal; According to the motion state of gait before, select one of described first sensitive axes signal and second sensitive axes signal as the identification signal of current gait; And based on the dynamic threshold that gait before presets, by judging that changing between the crest section of the identification signal of described current gait and trough section determines whether current gait is complete gait.
According to further embodiment of the present disclosure, can judge whether current gait is effective gait according to the time span of current gait and peak-to-peak value, and correspondingly count step.
According to further embodiment of the present disclosure, also comprise: if the time span of not carrying out the described acceleration signal of motion state judgement current met for first schedule time, then judge the motion state in described first schedule time in conjunction with described first sensitive axes signal and the second sensitive axes signal.
According to further embodiment of the present disclosure, also comprise: if the time span of current gait reaches the second predetermined time value, then give up the gait parameter of current gait, gait parameter described in initialization, start the identification of next gait.
According to further embodiment of the present disclosure, the judgement of the motion state in wherein said first schedule time comprises following three judgements: first judges: judge whether the maximum variable quantity of described second sensitive axes signal is greater than first threshold; Second judges: judge described first sensitive axes signal, whether the maximum variable quantity sum of the second sensitive axes signal be greater than Second Threshold; 3rd judges: judge whether the absolute value of the described maximal value of the second sensitive axes signal and the average of minimum value is greater than the 3rd threshold value; Wherein, if above-mentioned 3 results judged are all that the former is greater than the latter, then judge that the motion state in described first schedule time is running state, otherwise walk line state for other.
According to further embodiment of the present disclosure, the described judgement of the motion state in described first schedule time also comprises: judge by described first and described second judgement, to be careful with hurry up, state area of running separates, and judge further by the described 3rd, to hurry up and to distinguish with running state, thus the differentiation of the state three that realizes being careful, hurrying up and running.
According to further embodiment of the present disclosure, wherein said dynamic threshold determines according to the gait parameter of described gait before.
According to further embodiment of the present disclosure, if the motion state of its current gait is running state, then keep current dynamic threshold constant, and as the dynamic threshold of next gait; Dynamic threshold under described running state sets based on the value of the second sensitive axes signal of described acceleration transducer.
According to further embodiment of the present disclosure, if wherein the motion state of current gait is that other except running state walk line state, then dynamic threshold sets based on the value of the first sensitive axes signal of described acceleration transducer.
According to further embodiment of the present disclosure, if wherein the motion state of current gait is that other except running state walk line state, also set the dynamic threshold of next gait according to following steps: if current gait is invalid gait, then the dynamic threshold of next gait is the current maximal value of the first sensitive axes signal that identifies and the average of minimum value; If current gait is effective gait, but last gait is invalid gait, then the dynamic threshold of next gait is the crest value of current gait and the average of trough value; If current gait and last gait are effective gait, the then dynamic threshold dyn_thre=(thre2+thre3 × 3)/4 of next gait, wherein thre2 is the crest value of current gait and the average of trough value, and thre3 is the crest value of last effective gait and the average of trough value.
According to further embodiment of the present disclosure, if the difference of the dynamic threshold preset wherein and current selected acceleration signal is excessive, then the described dynamic threshold preset is revised.
According to further embodiment of the present disclosure, also comprise, judge whether that needs carry out meter step and compensate according to the parameter information of effective gait.
According to further embodiment of the present disclosure, if wherein the time span of current gait meets the time span of two continuous gaits, and the T.T. of current gait is only than the time of a half-wave duration gait mostly, then compensate meter step number.
According to further embodiment of the present disclosure, if wherein half-wave duration meets the time span of half gait, and be about 3 to 4 times of half-wave duration the T.T. of current gait, then meter step number compensated.
According to further embodiment of the present disclosure, if wherein identify gait to become running modes from the pattern of walking, then meter step number is compensated.
According to further embodiment of the present disclosure, if wherein identify gait to become other patterns of walking from running modes, then meter step number is compensated.
According to further embodiment of the present disclosure, be also included in after having gathered described acceleration signal, filtering is carried out to described acceleration signal.
According to further embodiment of the present disclosure, wherein said gait parameter comprises crest value, trough value, the relative point in time of crest value in gait, the relative point in time of trough value in gait and the T.T. length of gait.
According to second aspect of the present disclosure, provide a kind of passometer, it applies the gait recognition method described by above first aspect, and particularly, it can comprise:
Data acquisition module, acceleration signal during its collection wrist motion, described acceleration signal comprises the first sensitive axes signal and the second sensitive axes signal;
Data processing module, it is configured to perform following steps: according to the motion state of gait before, select one of described first sensitive axes signal and second sensitive axes signal as the identification signal of current gait; And based on the dynamic threshold that gait before presets, by judging that changing between the crest section of the identification signal of described current gait and trough section determines whether current gait is complete gait; And
Data memory module, it stores the data result of described data acquisition module and described data processing module.
According to further embodiment of the present disclosure, also comprise display module, be configured to the information showing described data processing module and/or data memory module output.
According to further embodiment of the present disclosure, wherein said data processing module is also configured to, and judges that whether current gait is effective, and correspondingly count step according to the time span of current gait and peak-to-peak value.
According to further embodiment of the present disclosure, also comprise: external interface module, it comprises button selection, transmission line interface and/or wireless transmission interface.
According to further embodiment of the present disclosure, wherein said data memory module is storing history data also.
According to the third aspect of the present disclosure, additionally provide a kind of Gait Recognition device, comprising:
Harvester, acceleration signal during its collection wrist motion, described acceleration signal comprises the first sensitive axes signal and the second sensitive axes signal;
Selecting arrangement, it, according to the motion state of gait before, selects one of described first sensitive axes signal and second sensitive axes signal as the identification signal of current gait; And
Judgment means, its dynamic threshold preset based on gait before, by judging that changing between the crest section of the identification signal of described current gait and trough section determines whether current gait is complete gait.
According to further embodiment of the present disclosure, wherein, described judgment means is also configured to, and judges that whether current gait is effective, and correspondingly count step according to the time span of current gait and peak-to-peak value.
The technique effect of the technical scheme that above-mentioned various aspects of the present disclosure provide is relative to prior art, without the need to calculating, resultant acceleration, step are simple, in calculating process, take storage space little and adopt meter step compensation scheme, make meter walk result more accurate.
Accompanying drawing explanation
In the accompanying drawings, similar/identical Reference numeral usually runs through different views and refers to similar/identical part.Accompanying drawing also need not be drawn in proportion, but usually emphasizes the diagram to principle of the present disclosure.In the accompanying drawings:
Fig. 1 shows people and wears kinematic sketch when wrist passometer is walked;
Fig. 2 show people wear wrist passometer run time kinematic sketch;
Fig. 3 shows the system flowchart of a kind of gait recognition method according to preferred embodiment of the present disclosure;
Fig. 4 shows the first sensitive axes acceleration signal schematic diagram when people walks in wrist equipment;
Fig. 5 shows the particular flow sheet of the identification gait parameter according to preferred embodiment of the present disclosure;
Fig. 6 shows the particular flow sheet according to the effective gait of the judgement of preferred embodiment of the present disclosure; And
Fig. 7 shows the structured flowchart of a kind of passometer according to preferred embodiment of the present disclosure.
Embodiment
Process flow diagram in accompanying drawing and block diagram, illustrate the architectural framework in the cards of the method and apparatus according to each embodiment of the disclosure, function and operation.In this, each square frame in process flow diagram or block diagram can represent a part for module, program segment or a code, and a part for described module, program segment or code comprises one or more executable instruction for realizing the logic function specified.Also it should be noted that at some as in the realization of replacing, the function marked in square frame also can be different from occurring in sequence of marking in accompanying drawing.Such as, in fact the square frame that two adjoining lands represent can perform substantially concurrently, and they also can perform by contrary order sometimes, and this determines according to involved function.Also it should be noted that, the combination of the square frame in each square frame in block diagram and/or process flow diagram and block diagram and/or process flow diagram, can realize by the special hardware based system of the function put rules into practice or operation, or can realize with the combination of specialized hardware and computer instruction.
Below with reference to accompanying drawing, passometer of the present disclosure and gait recognition method thereof are described in detail.
Fig. 1 and Fig. 2 respectively illustrate people wear wrist passometer walk and run time kinematic sketch.As depicted in figs. 1 and 2, wrist passometer is worn on the wrist of user's hand.Can be designed to include the first sensitive axes and the second sensitive axes according to wrist passometer of the present disclosure, wherein the first sensitive axes is perpendicular to the second sensitive axes.Although it should be noted that in Fig. 1 and Fig. 2 the direction that the first sensitive axes and the second sensitive axes have been shown, this direction is only example, and in other embodiments, the direction of the first sensitive axes and the second sensitive axes can be different.
Well-known, daily when running on foot, in order to keep the steadily of centre of gravity of health, the both hands of people can coordinate both feet to show the synperiodic coordinated movement of various economic factors.When human body with a stable state in walking or stair activity time, both arms naturally droop swing, and the entirety of people is with uniform motion in the horizontal direction.
Acceleration along forearm direction when the first sensitive axes record walking of acceleration transducer or stair activity in wrist equipment as shown in Figure 1, the first sensitive axes acceleration direction and vertical direction close, the second sensitive axes acceleration direction and fore-and-aft direction close.Walk or stair activity time, often step a step, centre of body weight once rises and falls, and the first sensitive axes acceleration direction and vertical ground direction are close, can record paces on foot.
When human body with a stable state when running, about at an angle of 90, to take on as axle carries out front and back swing arm, it all produces larger accekeration in vertical, level and side direction, and arms swing amplitude is larger for the large arm of health and forearm.In wrist equipment as shown in Figure 2, the first sensitive axes record of acceleration transducer is along the acceleration in forearm direction, and the second sensitive axes acceleration direction is vertical with forearm, and this direction and vertical ground direction close.During running, often step a step, centre of body weight all produces and once rises and fall, compared to the first sensitive axes, the second sensitive axes acceleration direction and vertical ground direction close, the paces of running can be reflected.
Inventive concept of the present disclosure is to realize running by means of the acceleration signal of the first sensitive axes and the second sensitive axes to walk the differentiation of line state with other, and is applied to the identification of follow-up gait and meter walks; Wherein based on the continuation of people's motion process, can on the basis of the motion state of known current gait, the motion state of current gait is used for the motion Gait Recognition in next stage, and on the basis of known motion state, can rational dynamic threshold be set thus effective identification motion gait information.Further, in the process of gait counting, additionally use meter step compensation scheme, to make up the step error because dynamic threshold and actual signal differ greatly and produce.It is that the gait information inference that basis has identified goes out the unrecognized gait of current existence one that meter step compensates, and then compensates (such as adding 1) meter step number.
Exemplarily, Fig. 3 shows the system flowchart of a kind of gait recognition method of preferred embodiment of the present disclosure.Should be appreciated that Fig. 3 only exemplarily provides, it should not form any restriction of implementation of the present disclosure.
As shown in Figure 3, first, step S201, gather acceleration signal during wrist motion, this acceleration signal comprises the first sensitive axes signal and the second sensitive axes signal.The realization of this step S201 such as can be carried out sampling by acceleration transducer described above according to the sample frequency of setting and realize.According to the sample frequency of disclosure setting, this sample frequency can be such as 50Hz.Because being embodied as of this step is known in the art, therefore elaboration detailed is not further done to this step.
Then, in step S202, filtering is carried out to gathered acceleration signal.The object of this step removes the high frequency noise in motor message, the interference brought to avoid noise.It will be appreciated by those skilled in the art that, when gathered acceleration signal does not have noise, although or there is noise, when there is not materially affect to Gait Recognition later, the step of this filtering is likely optional in certain embodiments.
Particularly, can carry out moving average filter to gathered acceleration signal, this moving average filter carries out running mean window filtering to the first sensitive axes progressively collected, the second sensitive axes signal.Running mean window filtering removes the high frequency noise in motor message.The limit of people is motion 5 step per second, therefore set the window of moving average filter long time, at least need to ensure that the signal of below 5Hz can effectively retain.Such as, when sample frequency is 50Hz, can set wave filter window length is 8.After acceleration information filtering, effective gait signal can be retained, can high frequency noise be removed again.
In step S203, the maximal value of (filtered) acceleration signal within first schedule time such as 1 second and minimum value can be calculated respectively.The object of this step is for this first schedule time, for the motion state (discussing in detail further below) in this schedule time of follow-up judgement.
To describe the implementation procedure asking for the schedule time such as interior maximal value per second and minimum value in step S203 in detail for the first sensitive axes signal below, the processing procedure of the second sensitive axes data is with the first sensitive axes.The implementation procedure of this step S203 can comprise:
Initial parameter is arranged: the data in the first sensitive axes maximum value register are set to the minimum value of short, and the numerical value of minimum value register is set to the maximal value of short, and dot counters is 0.Above-mentioned 3 kinds of parameters need the above-mentioned schedule time such as per secondly to reset once.
When there being filtered new data to arrive, dot counters is from adding 1, if the data that new data is greater than the data in maximum value register or is less than in minimum value register, be current new data by the data in maximum value register or the Data Update in minimum value register.Whether the data in judging point counter equal the sampling number (the such as above-mentioned schedule time is 1 second, sample frequency 50Hz, then corresponding sampling number is 50) in the above-mentioned schedule time; If equal, then the data in current maximum and minimum value register are respectively maximal value and the minimum value of signal in such as 1 second this schedule time.
Step S204, identifies gait parameter and judges whether current demand signal exists the conversion of crest section and trough section.Attention: this identification and judgement can be carried out simultaneously, also can successively carry out.As previously mentioned, will produce acceleration signal during people's wrist motion, this acceleration signal is a kind of periodically signal.Namely design of the present disclosure is to identify trough and crest by the dynamic threshold of setting, and corresponding gait parameter can be identified simultaneously, this gait parameter such as can comprise the T.T. length etc. of relative point in time in this gait of trough value, the relative point in time of trough value in this gait, crest value, crest value and this gait.
Fig. 4 shows the complete gait schematic diagram be made up of a trough section and a crest section of the present disclosure.Based on the schematic diagram of this complete gait, it will be understood by those skilled in the art that the acceleration signal axle selected for Gait Recognition, first identify trough section, identify crest section again, then once monitor the conversion between crest section to trough section again, the identification of complete gait can be realized.Attention: first identify trough section, then identify that crest section is not required, also can first identify crest section in other embodiments, then identify trough section.
The implementation procedure of step S204 such as can be as shown in Figure 5.Similarly, should be understood that the steps flow chart of Fig. 5 is only example, it does not form any restriction to specific implementation of the present disclosure.
The principle of attention: Fig. 5 is the conversion by the crest section and trough section judging signal, realizes the whether complete identification of gait and carries out the identification of gait parameter simultaneously.In addition, if the dynamic threshold of setting and actual walking pattern deviation of signal cause more greatly such as only identifying crest section, the identification whether this gait is complete still terminates.
Step in Fig. 5 is described in detail as follows: based on motion continuation principle, step S301 according to before the motion state (such as the motion state of last gait) of gait, judge the acceleration signal that current Gait Recognition adopts, if the motion state of last gait is running state, then the second sensitive axes signal is adopted to carry out follow-up Gait Recognition in step S302; If the motion state of last gait is other patterns (static, walking, downstairs) of walking, then the first sensitive axes signal is adopted to carry out follow-up Gait Recognition in step S303 upstairs.The comparison of the dynamic threshold dyn_thre subsequently under step S304 judges current demand signal pedo_signal and this motion state.Then, can judge that signal is in crest section, trough section, is entered crest section by trough section, enters trough section by crest section by the change of flag value corresponding to pedo_signal, and in this identifying marking wave peak value and relative point in time, trough value and relative point in time thereof, gait T.T. the parameter information such as length.
Particularly, in step S304, if current demand signal pedo_signal is greater than dynamic threshold dyn_thre, then judge that current demand signal point is in crest section, such as, and arrange flag value corresponding to this signaling point in step S307 and S308, this flag value can be one of bi-values, is 1.The flag value of hypothesis set by step S307 and S308 is 1 by conveniently follow-up discussion below.Simultaneously, whether the flag value detecting the signaling point of previous collection corresponding in step S305 is 1, if so, is then compared with crest section maximal value pedo_max by pedo_signal in step S307, and upgrade pedo_max, and upgrade the pedo_max_point that relatively counts residing for pedo_max.Then, next signaling point of pedo_signal is re-started to the judgement of step S304.If detecting flag value corresponding to previous signaling point in step S305 is not 1 (namely no), then only marking flag value corresponding to current demand signal point in step S308 is the 1 pedo_signal value current with storage.Then, similarly next signaling point of pedo_signal is re-started to the judgement of step S304.Attention: the flag value that the preceding signal point detected from step 305 is corresponding to be flag value that 0 to step S308 current demand signal point is corresponding be 1 change may be used for representing that pedo_signal is from trough section to the leap of crest section.
In step S304, if current demand signal pedo_signal is less than dynamic threshold dyn_thre, then judge that current demand signal point is in trough section, and in step S309 and S310, arrange flag value corresponding to this current demand signal point be 0.Similarly, the flag value of hypothesis set by step S309 and S310 is 0 by conveniently follow-up discussion below.Simultaneously, whether be 0, if so, then compared with trough section minimum value pedo_min by pedo_signal in step S309 if detecting flag value corresponding to previous signaling point in step S306, and upgrade pedo_min, and upgrade the pedo_min_point that relatively counts residing for pedo_min; Then, next signaling point of pedo_signal is re-started to the judgement of step S304; If detect that the flag value that previous signaling point is corresponding is not 0 (namely no) in step S306, then only exporting flag value corresponding to current demand signal point in step S310 is the 0 pedo_signal value current with storage.Attention: the flag value that the preceding signal point detected from step 306 is corresponding to be flag value that 1 to step S310 current demand signal point is corresponding be 0 change may be used for representing that pedo_signal is from crest section to the leap of trough section.
Once identify pedo_signal from crest section across to trough section in step S204, then show that the identification of a complete gait terminates.
To be understood by above description, in certain embodiments, for the identification of complete gait, step S202 and S203 may be not required.
Subsequently, in step S205, carry out the judgement of effective gait according to the gait parameter identified and count the operations such as step.The thinking of effective Gait Recognition process of the present disclosure is: an effective gait at least needs satisfied two conditions: peak-to-peak value meets acceleration amplitude change during motion, and time span meets the time span of transporting and moving a step.Utilize peak-to-peak value can reject the doubtful gait that signal produces under stationary state.Utilize time span can reject the doubtful gait of high frequency noise generation.Therefore, according to embodiment of the present disclosure, Effective judgement can be carried out according to the time span of gait and peak-to-peak value to gait.
In addition, in the process of step S205, can further include and judge whether to need meter step to compensate, and set the dynamic threshold of next gait, to carry out follow-up Gait Recognition and analysis.
The detailed process of step S205 as shown in Figure 6, first, in step S401 according to the gait parameter identified, can ask for peak-to-peak value peak_to_peak and half-wave duration half_wavelength.Wherein, peak_to_peak=pedo_max-pedo_min; Half-wave duration half_wavelength refers to the mistiming of crest value and trough value, has half_wavelength=(pedo_max_point-pedo_min_point)/sample frequency.
Then, in step S402, judge whether peak-to-peak value peak_to_peak meets the acceleration amplitude variation range of an effective gait.Such as, can judge peak-to-peak value peak_to_peak whether be greater than setting walk time acceleration minimum change value.
In step S402, if peak-to-peak value peak_to_peak does not meet the rangeability of effective gait, then judge that whether half-wave duration half_wavelength is too small in step S403, such as whether be less than 0.1 second, as too small, then show signal may be affected by noise suddenly by crest section across to trough section, think that the identification of this gait does not complete, continue to identify; Otherwise judge that the gait identified is doubtful gait or the imperfect gait (such as may only have crest section) of spacing wave generation in step S404, they are all judged as invalid gait, disregard step.
In step S402, if peak-to-peak value meets acceleration change amplitude when people walks or runs, then step S405 according to gait T.T. length and half-wave duration judge this gait whether effectively gait, such as judge gait T.T. length whether in schedule time scope (such as at 0.2 second to 2 seconds) and half-wave duration whether be greater than scheduled duration (such as 0.1 second).
If judge it is effective gait in step S407, then count step number and add 1, thus realize judgement and the meter step of effective gait.
Then continue to judge whether to need meter step to compensate based on the parameter of above-mentioned effective gait in step S408.
Wherein, judge whether that the content needing meter step to compensate can be as follows according to the parameter information of effective gait in step S408:
Because dynamic threshold dyn_thre of the present disclosure is that the effective gait parameter gone out according to default threshold or proximity detection sets, if gait signal thereafter because of amplitude of variation less, amplitude is always on or below dynamic threshold, without crossing over threshold value behavior, then gait (last gait) signal larger with contiguous amplitude of variation is combined and is identified as an effective gait by this gait.If analyzed the time span in this gait parameter, this time span meets the time span of two continuous gaits, then compensate meter step data.
According to example of the present disclosure, the particular type carrying out counting step compensation is needed at least to comprise following two kinds:
If a) half-wave duration is larger, and the T.T. of this gait is only than the time of a half-wave duration gait mostly, then think to there is the less complete gait of a changes in amplitude between the trough of this gait and crest, this gait fails to be effectively recognized, then compensate meter step number, such as order meter step number compensates and adds 1; And
If b) half-wave duration meets the time span of half gait, and the T.T. length of current effective gait is larger, be about 3 to 4 times of half-wave duration, then think also there is a Unidentified gait before the trough of this gait or after crest, then compensate meter step number, such as order meter step number compensates and adds 1.
In addition, the disclosure also according to the dynamic threshold dyn_thre of next gait of gait information setting before, to carry out identification and the analysis of next gait.The setting of the dynamic threshold of this next gait can comprise following operation:
If a) motion state of current gait is running state (i.e. step S409 be judged to be), then making its dynamic threshold constant, is the default threshold set under this state, the dyn_thre namely under step S416 arranges running modes.Wherein, dynamic threshold under running state is positive negative sense according to the maximal value of the second sensitive axes acceleration information and the average of minimum value (note: what this positive negative sense depended on wrist passometer of the present disclosure wears direction), chooses a rational dynamic threshold.
If b) motion state of current gait walks line state (namely step S409 is judged to be no) for other, then the establishing method of the dynamic threshold of next gait has:
B1) if current gait is invalid gait, the dynamic threshold of next gait is the average of the data in the current maximum value register identified and the data in minimum value register;
B2) if current gait is effective gait, but previous gait is invalid gait, the dynamic threshold dyn_thre of next gait is the crest value pedo_max of current gait and the average thre2 (namely from step S410 to step S413) of trough value pedo_max.
B3) if current gait and previous gait are effective gait, then the dynamic threshold of next gait is set as dyn_thre=(thre2+thre3 × 3)/4 (namely from step S411 to step S412), wherein thre2 is the crest value of current gait and the average of trough value, and thre3 is the crest value of previous effective gait and the average of trough value.As can be seen from computing formula, the dynamic threshold of next gait and the average correlativity of previous gait trough crest value larger.A lot of sporter, it is when normally walking, and its first sensitive axes signal presents rule as shown in Figure 4, together with one " larger gait " periodically overlaps on one " less gait ", this and people are in normal motion, and it is relevant for periodically stepping left and right pin.The setting of this dynamic threshold considers the similarity that same pin steps paces.
After other dynamic threshold walked under line state above-mentioned has set (step S410-step S413), in theory, next dynamic threshold should with current signal value close to the trough that can better identify in gait signal and crest, if and the difference of the dynamic threshold dyn_thre of new settings and current demand signal pedo_signal is excessive, then can revise dynamic threshold in step S414, make the two close.Such as, can set correction algorithm is: dyn_thre=(dyn_thre+pedo_signal)/2, effectively can reduce the difference of next step dynamic threshold and current demand signal, thus ensures that the dynamic threshold of next gait is more reasonable.Meanwhile, in step S415, the thre3 in register is updated to thre2, for use in the setting of the dynamic threshold of follow-up next gait again.
Referring back to Fig. 3, then, can step S206 be performed, if the time span of current frame data (such as the current acceleration signal not judging motion state) meets first schedule time (such as one second), then judge the motion state in this first schedule time.The judged result of this motion state may be used for selecting the first sensitive axes in step S204 before and the second sensitive axes signal, thus for Gait Recognition.
Step S206 judges that the specific implementation of motion state can comprise the following steps:
According to maximal value and the minimum value of the first sensitive axes, the second sensitive axes acceleration signal, calculate the first sensitive axes, the maximum variable quantity of the second sensitive axes acceleration within first schedule time such as 1 second respectively;
Calculate the maximum variable quantity sum of acceleration of the first sensitive axes, the second sensitive axes; And
Calculate the average of the second sensitive axes acceleration signal maximal value and minimum value.
According to above calculating, the motion state in above-mentioned first schedule time can be judged by following Rule of judgment:
Whether the maximum variable quantity of Rule of judgment 1: the second sensitive axes is greater than first threshold;
Whether the maximum variable quantity sum of acceleration of Rule of judgment 2: the first sensitive axes, the second sensitive axes is greater than Second Threshold;
Whether the maximal value of Rule of judgment 3: the second sensitive axes acceleration and the absolute value of minimum value average are greater than the 3rd threshold value;
If the result of above-mentioned three kinds of comparisons is all for the former be greater than the latter, then judges that the motion state in this first schedule time is running state, otherwise walk line state for other.
Wherein, first threshold and Second Threshold are and obtain human body movement data analysis.Acceleration change value when being careful is less, and hurry up and acceleration change value under running state all larger.In conjunction with Rule of judgment 1 and Rule of judgment 2, can distinguish is careful runs with hurrying up.Under the prerequisite of Rule of judgment 1 and Rule of judgment 2, for Rule of judgment 3, because of the peak valley change that the second sensitive axes acceleration in human motion process periodically presents, the maximal value of its second sensitive axes acceleration and the average of minimum value, be similar to the mean value of this axle acceleration signal.When walking fast, the acceleration of fore-and-aft direction during the second sensitive axes records of acceleration arms swing fore backward, the second sensitive axes data are not now containing acceleration of gravity signal, and near 0g, periodic peak valley changes; And when running, the second sensitive axes acceleration direction and vertical direction close, this axle acceleration has merged acceleration of gravity, and the absolute value of its mean value is near 1g.Therefore, if the maximal value of the second sensitive axes acceleration signal and the mean value of minimum value are near 0g, illustrate that current motion state is for the state of hurrying up, if the absolute value of mean value is near 1g, illustrate that current motion state is running state, thus effectively differentiation is hurried up and running.To sum up know, the 3rd threshold value is the numerical value between 0g and 1g.Wherein, in above-mentioned 0g or 1g, g represents acceleration of gravity.
The method can effectively be distinguished normally to walk, these three kinds of states of hurrying up and run.The correct judgement of motion state, sets dynamic threshold when contributing to Gait Recognition, thus improves meter step accuracy rate.
Then, perform step S207, judge whether the time span (that is, failing to identify the time of complete gait) of the current gait identified reaches second schedule time (such as 2 seconds).If reach this second schedule time, then give up the gait parameter that this gait is corresponding, the identification of a new gait from next signal point.
The reason that step S207 gives up gait parameter corresponding to this gait is that people makes a move on foot for the most such as 2 seconds, identifies a complete gait if also fail in Gait Recognition process 2 seconds, then there are two kinds of possibilities: one: signal is spacing wave; Two: dynamic threshold and actual walking pattern deviation of signal large.
Test example, as changes in amplitude value in 2 seconds signals, if changes in amplitude value is less, thinks that current motion state is static; If amplitude of variation is comparatively large, then think that the reason of this gait recognition result is above-mentioned the second possibility, namely dynamic threshold and actual walking pattern deviation of signal are comparatively large, and this at least exists an effective gait in 2 seconds in signal.
Below the judgement of gait recognition method of the present disclosure and motion state has been described in detail, by this description, those skilled in the art can understand and realize the recognition methods of motion state of the present disclosure judgement, complete gait, effectively gait fully, and corresponding meter walks and compensates, and various possible distortion, amendment or replacement can be realized on the basis of described embodiment of the present disclosure.
Such as, meter step of the present disclosure compensation method also may be present in following situation:
When motion state becomes running modes from the pattern of walking, because the dynamic threshold under two kinds of patterns may be different, probably error is produced when Gait Recognition, and generally, the frequency of running signal is larger than the frequency of signal of walking, and compensates (such as adding 1) the meter step number that may produce error.
After moving state identification, when finding that motion state becomes running modes from the pattern of walking, and the first sensitive axes signal floats near 0g in above-mentioned first schedule time (such as 1 second), and the absolute value of the first sensitive axes acceleration signal when normal gait or stair activity floats near 1g, then from the first sensitive axes signal, do not identify effective gait in above-mentioned first schedule time, again compensate meter step number, such as count step number and add 1, wherein g represents acceleration of gravity.
Identifying after motion state to become other pattern of walking from running, infer the change that likely there occurs motion state within the previous schedule time (such as last second), because at least there is a running signal in the previous schedule time, be therefore identified as running state.Because dynamic threshold reason causes may existing in the previous schedule time on foot, gait is unrecognized, compensates, such as, count step number and add 1 this issuable meter step error.
Identifying after motion state to become other pattern of walking from running, because being that employing second sensitive axes signal carries out Gait Recognition in above-mentioned first schedule time (such as 1 second), the gait produced when possibility " omission " falls walking in identifying, this kind of situation easily produces meter step error.Now, judge the amplitude of variation of the first sensitive axes signal in this first schedule time, if amplitude of variation is larger, think at least to exist in this first schedule time a walking or upper downstairs time gait signal, meter step number is compensated (such as adding 1), if amplitude of variation is less, thinking current is stationary state.
In step S207, fail to identify signal in second schedule time (such as 2 seconds) and become trough section from crest section, to this, if there is crest value and trough value in the signal having identified this second schedule time, if peak-to-peak value is larger, think at least there is an effective gait in this second schedule time, (such as adding 1) is compensated to meter step number.
Be described above a kind of gait recognition method, the disclosure additionally provides a kind of passometer of this gait recognition method of application, and its structured flowchart can be as shown in Figure 7.Each comprising modules can be respectively: data acquisition module, data memory module, data processing module, display module and external interface module.
Wherein, data acquisition module is for gathering the acceleration information etc. of wrist motion.
Data memory module can store the signal that data collecting module collected arrives, meanwhile, can also storing history data, as the motion step number, consumed energy, motion mileage etc. of every day in nearest one week or January recently.
Data processing module is used for carrying out moving state identification and Gait Recognition to the acceleration information collected, and meter step, and the data processed result of this module is stored into data memory module by timing.
Display module may be used for display information basic time, current motion information and historical movement information etc., facilitates man-machine interaction.
External interface module can comprise button selection, transmission line interface, wireless transmission interface etc., thus is convenient for people to do further statistical study to exercise data, to formulate rational exercise program etc.
As the example according to passometer of the present disclosure corresponding to above-mentioned gait recognition method, it can comprise:
Data acquisition module, acceleration signal during its collection wrist motion, described acceleration signal comprises the first sensitive axes signal and the second sensitive axes signal;
Data processing module, it is configured to perform following steps: according to the motion state of gait before, select one of described first sensitive axes signal and second sensitive axes signal as the identification signal of current gait; And based on the dynamic threshold that gait before presets, by judging that changing between the crest section of the identification signal of described current gait and trough section determines whether current gait is complete gait; And
Data memory module, it stores the data result of described data acquisition module and described data processing module.
According to the example of this passometer, this data processing module is also configured to, and judges that whether current gait is effective, and correspondingly count step according to the time span of current gait and peak-to-peak value.
According to the example of this passometer, can further include: display module, be configured to the information showing described data processing module and/or data memory module output.
According to the example of this passometer, can further include: external interface module, it comprises button selection, transmission line interface and/or wireless transmission interface.
According to the example of this passometer, can further include: described data memory module is storing history data also.
Those skilled in the art also will understand, and the every other technical characteristic in above-mentioned gait recognition method all can be realized by the corresponding module in passometer, therefore no longer repeats the 26S Proteasome Structure and Function of this passometer.
In addition, the disclosure also relates to a kind of Gait Recognition device corresponding to above-mentioned gait recognition method, and it can directly be realized by corresponding functional device, such as, can comprise:
Harvester, acceleration signal during its collection wrist motion, described acceleration signal comprises the first sensitive axes signal and the second sensitive axes signal;
Selecting arrangement, it, according to the motion state of gait before, selects one of described first sensitive axes signal and second sensitive axes signal as the identification signal of current gait; And
Judgment means, its dynamic threshold preset based on gait before, by judging that changing between the crest section of the identification signal of described current gait and trough section determines whether current gait is complete gait.
According to the example of this Gait Recognition device, described judgment means can be configured to judge that whether current gait is effective according to the time span of current gait and peak-to-peak value further, and correspondingly counts step.
Those skilled in the art also will understand, and above-mentioned Gait Recognition device includes but not limited to above-described structure.Similarly, above method characteristic described in gait recognition method all can be realized by the related device in Gait Recognition device, all technique effects that above-mentioned gait recognition method realizes can be realized thus.
Give instructions of the present disclosure for the object illustrated and describe, but it is not intended to be exhaustive or be limited to the invention of disclosed form.It may occur to persons skilled in the art that a lot of amendment and variant.It will be appreciated by those skilled in the art that the method and apparatus in disclosure embodiment can realize with software, hardware, firmware or its combination.
Therefore; embodiment is to principle of the present disclosure, practical application are described better and enable the other staff in those skilled in the art understand following content and select and describe; namely; under the prerequisite not departing from disclosure spirit, all modifications made and replacement all will fall in the disclosure protection domain of claims definition.
Claims (25)
1. a gait recognition method, comprises the following steps:
Gather acceleration signal during wrist motion, described acceleration signal comprises the first sensitive axes signal and the second sensitive axes signal;
According to the motion state of gait before, select one of described first sensitive axes signal and second sensitive axes signal as the identification signal of current gait; And
Based on the dynamic threshold that gait before presets, by judging that changing between the crest section of the identification signal of described current gait and trough section determines whether current gait is complete gait.
2. gait recognition method according to claim 1, also comprises,
Judge whether current gait is effective gait according to the time span of current gait and peak-to-peak value, and correspondingly count step.
3. gait recognition method according to claim 1 and 2, comprises further:
If the time span of not carrying out the described acceleration signal of motion state judgement current met for first schedule time, then judge the motion state in described first schedule time in conjunction with described first sensitive axes signal and the second sensitive axes signal.
4. gait recognition method according to claim 1 and 2, comprises further:
If the time span of current gait reached for second schedule time, then give up the gait parameter of current gait, gait parameter described in initialization, start the identification of next gait.
5. gait recognition method according to claim 3, wherein, the judgement of the motion state in described first schedule time comprises following three judgements:
First judges: judge whether the maximum variable quantity of described second sensitive axes signal is greater than first threshold;
Second judges: judge described first sensitive axes signal, whether the maximum variable quantity sum of the second sensitive axes signal be greater than Second Threshold;
3rd judges: judge whether the absolute value of the described maximal value of the second sensitive axes signal and the average of minimum value is greater than the 3rd threshold value;
Wherein, if above-mentioned three results judged are all that the former is greater than the latter, then judge that the motion state in described first schedule time is running state, otherwise walk line state for other.
6. gait recognition method according to claim 5, wherein, the judgement of the motion state in described first schedule time also comprises:
Judge by described first and described second to judge, will be careful with hurry up, state area of running separates, and further by described 3rd judgement, will hurry up and to distinguish with running state, the differentiation of state three thus realization is careful, hurries up and is run.
7. gait recognition method according to claim 1, wherein, described dynamic threshold determines according to the gait parameter of described gait before.
8. gait recognition method according to claim 7, wherein,
If the motion state of current gait is running state, then keep current dynamic threshold constant, and as the dynamic threshold of next gait; Dynamic threshold under described running state sets based on the value of described second sensitive axes signal.
9. gait recognition method according to claim 7, wherein,
If the motion state of current gait is other except running state walk line state, then dynamic threshold sets based on the value of described first sensitive axes signal.
10. gait recognition method according to claim 7, wherein, if the motion state of current gait is other except running state walk line state, also sets the dynamic threshold of next gait according to following steps:
If current gait is invalid gait, then the dynamic threshold of next gait is the current maximal value of the first sensitive axes signal that identifies and the average of minimum value;
If current gait is effective gait, but last gait is invalid gait, then the dynamic threshold of next gait is the crest value of current gait and the average of trough value;
If current gait and last gait are effective gait, the then dynamic threshold dyn_thre=(thre2+thre3 × 3)/4 of next gait, wherein thre2 is the crest value of current gait and the average of trough value, and thre3 is the crest value of last effective gait and the average of trough value.
11. gait recognition methods according to any one of claim 1 and 7-10, wherein,
If described in the difference of the dynamic threshold that presets and current selected acceleration signal excessive, then the described dynamic threshold preset is revised.
12. gait recognition methods according to claim 2, comprise further,
Judge whether that needs carry out meter step and compensate according to the parameter information of effective gait.
13. gait recognition methods according to claim 12, wherein,
If the time span of current gait meets the time span of two continuous gaits, and the T.T. of current gait is only than the time of a half-wave duration gait mostly, then compensate meter step number.
14. gait recognition methods according to claim 12, wherein,
If half-wave duration meets the time span of half gait, and is about 3 to 4 times of half-wave duration the T.T. of current gait, then meter step number is compensated.
15. gait recognition methods according to claim 12, wherein,
If identify gait to become running modes from the pattern of walking, then meter step number is compensated.
16. gait recognition methods according to claim 12, wherein,
If identify gait to become other patterns of walking from running modes, then meter step number is compensated.
17. gait recognition methods according to claim 1 and 2, also comprise:
After having gathered described acceleration signal, filtering is carried out to described acceleration signal.
18. gait recognition methods according to claim 4, wherein,
Described gait parameter comprises crest value, trough value, the relative point in time of crest value in gait, the relative point in time of trough value in gait and the T.T. length of gait.
19. 1 kinds of passometers, comprising:
Data acquisition module, acceleration signal during its collection wrist motion, described acceleration signal comprises the first sensitive axes signal and the second sensitive axes signal;
Data processing module, it is configured to perform following steps:
According to the motion state of gait before, select one of described first sensitive axes signal and second sensitive axes signal as the identification signal of current gait; And
Based on the dynamic threshold that gait before presets, by judging that changing between the crest section of the identification signal of described current gait and trough section determines whether current gait is complete gait; And
Data memory module, it stores the data result of described data acquisition module and described data processing module.
20. passometers according to claim 19, wherein,
Described data processing module is also configured to, and judges that whether current gait is effective, and correspondingly count step according to the time span of current gait and peak-to-peak value.
21. passometers according to claim 19 or 20, comprise further:
Display module, is configured to the information showing described data processing module and/or data memory module output.
22. passometers according to claim 19 or 20, comprise further:
External interface module, it comprises button selection, transmission line interface and/or wireless transmission interface.
23. passometers according to claim 19 or 20, wherein,
Described data memory module is storing history data also.
24. 1 kinds of Gait Recognition devices, comprising:
Harvester, acceleration signal during its collection wrist motion, described acceleration signal comprises the first sensitive axes signal and the second sensitive axes signal;
Selecting arrangement, it, according to the motion state of gait before, selects one of described first sensitive axes signal and second sensitive axes signal as the identification signal of current gait; And
Judgment means, its dynamic threshold preset based on gait before, by judging that changing between the crest section of the identification signal of described current gait and trough section determines whether current gait is complete gait.
25. Gait Recognition devices according to claim 24, wherein, described judgment means is also configured to, and judges that whether current gait is effective, and correspondingly count step according to the time span of current gait and peak-to-peak value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510153005.2A CN104713568A (en) | 2015-03-31 | 2015-03-31 | Gait recognition method and corresponding pedometer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510153005.2A CN104713568A (en) | 2015-03-31 | 2015-03-31 | Gait recognition method and corresponding pedometer |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104713568A true CN104713568A (en) | 2015-06-17 |
Family
ID=53413099
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510153005.2A Pending CN104713568A (en) | 2015-03-31 | 2015-03-31 | Gait recognition method and corresponding pedometer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104713568A (en) |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105342583A (en) * | 2015-12-17 | 2016-02-24 | 重庆邮电大学 | Intelligent monitoring device with high-precision step counting function for old people |
| CN105651303A (en) * | 2016-03-04 | 2016-06-08 | 江苏大学 | Pace counting system and pace counting method based on three-axis acceleration sensor |
| CN105682034A (en) * | 2016-01-28 | 2016-06-15 | 腾讯科技（深圳）有限公司 | Step counting method and related device, detection method and related device |
| CN106017502A (en) * | 2016-05-17 | 2016-10-12 | 中国地质大学（武汉） | Step counting method and electronic device |
| CN106178469A (en) * | 2016-08-08 | 2016-12-07 | 张阳 | Hurry up motion sharing method and system |
| CN106197412A (en) * | 2016-06-30 | 2016-12-07 | 北京海顿中科技术有限公司 | The pinpoint method of micro-inertial navigation is carried out based on accelerometer, gyroscope |
| CN106248100A (en) * | 2016-07-07 | 2016-12-21 | 深圳市金立通信设备有限公司 | A kind of step-recording method and terminal |
| CN106790966A (en) * | 2016-11-04 | 2017-05-31 | 上海斐讯数据通信技术有限公司 | The changing method of intelligent terminal motor pattern, system and intelligent terminal |
| CN106767889A (en) * | 2016-12-05 | 2017-05-31 | 广东思派康电子科技有限公司 | A kind of step-recording method for being based on three axle G sensor |
| CN107317934A (en) * | 2017-06-30 | 2017-11-03 | 北京奇虎科技有限公司 | User Activity state based on mobile terminal determines method, device and mobile terminal |
| CN107588784A (en) * | 2016-07-08 | 2018-01-16 | 深圳达阵科技有限公司 | A kind of state recognition and the method, apparatus and terminal distinguished |
| CN107784298A (en) * | 2017-11-23 | 2018-03-09 | 维沃移动通信有限公司 | A kind of recognition methods and device |
| CN107970590A (en) * | 2016-10-25 | 2018-05-01 | 四川理工学院 | A kind of running body-building data system and method based on Android platform |
| CN107970574A (en) * | 2016-10-25 | 2018-05-01 | 四川理工学院 | A kind of running body-building system and its data processing method based on Android platform |
| CN108761496A (en) * | 2018-05-23 | 2018-11-06 | 四川斐讯信息技术有限公司 | A kind of method and device automatically turning on GPS |
| CN108986883A (en) * | 2017-06-02 | 2018-12-11 | 四川理工学院 | A kind of moving state identification system and method based on Android platform |
| CN109141465A (en) * | 2018-07-19 | 2019-01-04 | 歌尔科技有限公司 | A kind of step-recording method, wearable device and computer readable storage medium |
| CN109561854A (en) * | 2016-08-02 | 2019-04-02 | 美敦力公司 | It is detected using the paces of accelerometer axis |
| CN109582713A (en) * | 2018-11-30 | 2019-04-05 | 歌尔科技有限公司 | A kind of recognition methods of motion state, device and terminal |
| CN109620247A (en) * | 2018-12-25 | 2019-04-16 | 努比亚技术有限公司 | A kind of equivalent step-recording method, equipment and computer readable storage medium |
| CN109862831A (en) * | 2016-10-07 | 2019-06-07 | 松下知识产权经营株式会社 | Cognitive Function device, Cognitive Function method and program |
| CN109893137A (en) * | 2019-03-07 | 2019-06-18 | 山东科技大学 | Improve the method for gait detection under different carrying positions based on mobile terminal |
| CN109993037A (en) * | 2018-01-02 | 2019-07-09 | 中国移动通信有限公司研究院 | Action identification method, device, wearable device and computer readable storage medium |
| CN110300882A (en) * | 2017-02-16 | 2019-10-01 | 罗伯特·博世有限公司 | The method and apparatus of stationary vehicle for identification |
| CN110595501A (en) * | 2019-10-09 | 2019-12-20 | 成都乐动信息技术有限公司 | Running distance correction method based on three-axis sensor |
| CN110638459A (en) * | 2019-09-03 | 2020-01-03 | 杭州雄芯物联科技有限公司 | Human motion falling detection device and method based on acceleration sensor |
| CN110721456A (en) * | 2019-10-09 | 2020-01-24 | 成都乐动信息技术有限公司 | Pedal frequency detection method based on three-axis sensor |
| CN111189469A (en) * | 2019-12-31 | 2020-05-22 | 歌尔科技有限公司 | Step counting method, terminal device and storage medium |
| CN111435083A (en) * | 2019-01-11 | 2020-07-21 | 阿里巴巴集团控股有限公司 | Pedestrian track calculation method, navigation method and device, handheld terminal and medium |
| CN111667609A (en) * | 2019-03-07 | 2020-09-15 | 意法半导体股份有限公司 | Three-level motion detector using accelerometer device in key card applications |
| CN112539763A (en) * | 2020-12-08 | 2021-03-23 | 歌尔科技有限公司 | Motion state classification method, step counting device and readable storage medium |
| CN112906784A (en) * | 2021-02-07 | 2021-06-04 | 北京小米移动软件有限公司 | Step counting method and device, mobile terminal and storage medium |
| CN113340322A (en) * | 2021-06-25 | 2021-09-03 | 歌尔科技有限公司 | Step counting method and device, electronic equipment and readable storage medium |
| CN114298105A (en) * | 2021-12-29 | 2022-04-08 | 东莞市猎声电子科技有限公司 | Signal processing method for quickly responding to wrist lifting action and brightening screen in running process |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101750096A (en) * | 2008-11-28 | 2010-06-23 | 佛山市顺德区顺达电脑厂有限公司 | Step-counting processing system and method |
| US7805277B2 (en) * | 2006-02-16 | 2010-09-28 | Seiko Instruments Inc. | Step number measuring apparatus |
| CN102654405A (en) * | 2011-03-04 | 2012-09-05 | 美新半导体（无锡）有限公司 | Gait counting method and device based on acceleration sensor |
| CN104075730A (en) * | 2014-07-02 | 2014-10-01 | 电子科技大学 | Gait counting method and gait counter |
| CN104121925A (en) * | 2014-08-08 | 2014-10-29 | 沈迪 | Step counting method and device |
-
2015
- 2015-03-31 CN CN201510153005.2A patent/CN104713568A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7805277B2 (en) * | 2006-02-16 | 2010-09-28 | Seiko Instruments Inc. | Step number measuring apparatus |
| CN101750096A (en) * | 2008-11-28 | 2010-06-23 | 佛山市顺德区顺达电脑厂有限公司 | Step-counting processing system and method |
| CN102654405A (en) * | 2011-03-04 | 2012-09-05 | 美新半导体（无锡）有限公司 | Gait counting method and device based on acceleration sensor |
| CN104075730A (en) * | 2014-07-02 | 2014-10-01 | 电子科技大学 | Gait counting method and gait counter |
| CN104121925A (en) * | 2014-08-08 | 2014-10-29 | 沈迪 | Step counting method and device |
Non-Patent Citations (2)
| Title |
|---|
| CROUTER SE,等: "Validity of 10 Electronic Pedometers for Measuring Steps,Distance,and Energy Cost", 《MED SCI SPORTS EXERC》 * |
| 陈泓竹: "一种基于物联网的计步器设计", 《现代计算机》 * |
Cited By (53)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105342583B (en) * | 2015-12-17 | 2019-01-25 | 重庆邮电大学 | A kind of the elderly's intelligent monitoring device of high-precision step counting |
| CN105342583A (en) * | 2015-12-17 | 2016-02-24 | 重庆邮电大学 | Intelligent monitoring device with high-precision step counting function for old people |
| CN105682034A (en) * | 2016-01-28 | 2016-06-15 | 腾讯科技（深圳）有限公司 | Step counting method and related device, detection method and related device |
| CN105682034B (en) * | 2016-01-28 | 2020-08-21 | 腾讯科技（深圳）有限公司 | Step counting method and related device, detection method and related device |
| CN105651303A (en) * | 2016-03-04 | 2016-06-08 | 江苏大学 | Pace counting system and pace counting method based on three-axis acceleration sensor |
| CN106017502A (en) * | 2016-05-17 | 2016-10-12 | 中国地质大学（武汉） | Step counting method and electronic device |
| CN106017502B (en) * | 2016-05-17 | 2019-02-26 | 中国地质大学（武汉） | A kind of step-recording method and electronic equipment |
| CN106197412A (en) * | 2016-06-30 | 2016-12-07 | 北京海顿中科技术有限公司 | The pinpoint method of micro-inertial navigation is carried out based on accelerometer, gyroscope |
| CN106248100A (en) * | 2016-07-07 | 2016-12-21 | 深圳市金立通信设备有限公司 | A kind of step-recording method and terminal |
| CN107588784A (en) * | 2016-07-08 | 2018-01-16 | 深圳达阵科技有限公司 | A kind of state recognition and the method, apparatus and terminal distinguished |
| CN109561854A (en) * | 2016-08-02 | 2019-04-02 | 美敦力公司 | It is detected using the paces of accelerometer axis |
| CN109561854B (en) * | 2016-08-02 | 2022-01-04 | 美敦力公司 | Step detection using accelerometer axes |
| CN106178469A (en) * | 2016-08-08 | 2016-12-07 | 张阳 | Hurry up motion sharing method and system |
| CN109862831A (en) * | 2016-10-07 | 2019-06-07 | 松下知识产权经营株式会社 | Cognitive Function device, Cognitive Function method and program |
| CN107970590A (en) * | 2016-10-25 | 2018-05-01 | 四川理工学院 | A kind of running body-building data system and method based on Android platform |
| CN107970574A (en) * | 2016-10-25 | 2018-05-01 | 四川理工学院 | A kind of running body-building system and its data processing method based on Android platform |
| CN107970590B (en) * | 2016-10-25 | 2019-05-21 | 四川理工学院 | A kind of running body-building data system and method based on Android platform |
| CN107970574B (en) * | 2016-10-25 | 2019-05-14 | 四川理工学院 | A kind of running body-building system and its data processing method based on Android platform |
| CN106790966A (en) * | 2016-11-04 | 2017-05-31 | 上海斐讯数据通信技术有限公司 | The changing method of intelligent terminal motor pattern, system and intelligent terminal |
| CN106767889A (en) * | 2016-12-05 | 2017-05-31 | 广东思派康电子科技有限公司 | A kind of step-recording method for being based on three axle G sensor |
| CN110300882A (en) * | 2017-02-16 | 2019-10-01 | 罗伯特·博世有限公司 | The method and apparatus of stationary vehicle for identification |
| CN108986883B (en) * | 2017-06-02 | 2021-08-10 | 四川理工学院 | Motion state identification system and method based on Android platform |
| CN108986883A (en) * | 2017-06-02 | 2018-12-11 | 四川理工学院 | A kind of moving state identification system and method based on Android platform |
| CN107317934A (en) * | 2017-06-30 | 2017-11-03 | 北京奇虎科技有限公司 | User Activity state based on mobile terminal determines method, device and mobile terminal |
| CN107784298B (en) * | 2017-11-23 | 2020-06-19 | 维沃移动通信有限公司 | Identification method and device |
| CN107784298A (en) * | 2017-11-23 | 2018-03-09 | 维沃移动通信有限公司 | A kind of recognition methods and device |
| CN109993037A (en) * | 2018-01-02 | 2019-07-09 | 中国移动通信有限公司研究院 | Action identification method, device, wearable device and computer readable storage medium |
| CN109993037B (en) * | 2018-01-02 | 2021-08-06 | 中国移动通信有限公司研究院 | Action recognition method and device, wearable device and computer-readable storage medium |
| CN108761496A (en) * | 2018-05-23 | 2018-11-06 | 四川斐讯信息技术有限公司 | A kind of method and device automatically turning on GPS |
| CN109141465A (en) * | 2018-07-19 | 2019-01-04 | 歌尔科技有限公司 | A kind of step-recording method, wearable device and computer readable storage medium |
| CN109141465B (en) * | 2018-07-19 | 2021-06-22 | 歌尔科技有限公司 | Step counting method, wearable device and computer readable storage medium |
| CN109582713A (en) * | 2018-11-30 | 2019-04-05 | 歌尔科技有限公司 | A kind of recognition methods of motion state, device and terminal |
| CN109582713B (en) * | 2018-11-30 | 2023-05-19 | 歌尔科技有限公司 | Motion state identification method, motion state identification device and terminal |
| CN109620247A (en) * | 2018-12-25 | 2019-04-16 | 努比亚技术有限公司 | A kind of equivalent step-recording method, equipment and computer readable storage medium |
| CN111435083A (en) * | 2019-01-11 | 2020-07-21 | 阿里巴巴集团控股有限公司 | Pedestrian track calculation method, navigation method and device, handheld terminal and medium |
| US11721202B2 (en) | 2019-03-07 | 2023-08-08 | Stmicroelectronics S.R.L. | Three-level motion detector using accelerometer device in key fob application |
| CN109893137A (en) * | 2019-03-07 | 2019-06-18 | 山东科技大学 | Improve the method for gait detection under different carrying positions based on mobile terminal |
| CN109893137B (en) * | 2019-03-07 | 2021-09-03 | 山东科技大学 | Method for improving gait detection based on mobile terminal at different carrying positions |
| CN111667609A (en) * | 2019-03-07 | 2020-09-15 | 意法半导体股份有限公司 | Three-level motion detector using accelerometer device in key card applications |
| CN110638459B (en) * | 2019-09-03 | 2023-05-05 | 宁波路晟电器科技有限公司 | Human body movement falling detection device and method based on acceleration sensor |
| CN110638459A (en) * | 2019-09-03 | 2020-01-03 | 杭州雄芯物联科技有限公司 | Human motion falling detection device and method based on acceleration sensor |
| CN110595501B (en) * | 2019-10-09 | 2022-10-04 | 成都乐动信息技术有限公司 | Running distance correction method based on three-axis sensor |
| CN110721456B (en) * | 2019-10-09 | 2020-12-25 | 成都乐动信息技术有限公司 | Pedal frequency detection method based on three-axis sensor |
| CN110595501A (en) * | 2019-10-09 | 2019-12-20 | 成都乐动信息技术有限公司 | Running distance correction method based on three-axis sensor |
| CN110721456A (en) * | 2019-10-09 | 2020-01-24 | 成都乐动信息技术有限公司 | Pedal frequency detection method based on three-axis sensor |
| CN111189469A (en) * | 2019-12-31 | 2020-05-22 | 歌尔科技有限公司 | Step counting method, terminal device and storage medium |
| CN112539763B (en) * | 2020-12-08 | 2023-03-14 | 歌尔科技有限公司 | Motion state classification method, step counting device and readable storage medium |
| CN112539763A (en) * | 2020-12-08 | 2021-03-23 | 歌尔科技有限公司 | Motion state classification method, step counting device and readable storage medium |
| CN112906784A (en) * | 2021-02-07 | 2021-06-04 | 北京小米移动软件有限公司 | Step counting method and device, mobile terminal and storage medium |
| CN113340322B (en) * | 2021-06-25 | 2023-04-07 | 歌尔科技有限公司 | Step counting method and device, electronic equipment and readable storage medium |
| CN113340322A (en) * | 2021-06-25 | 2021-09-03 | 歌尔科技有限公司 | Step counting method and device, electronic equipment and readable storage medium |
| CN114298105A (en) * | 2021-12-29 | 2022-04-08 | 东莞市猎声电子科技有限公司 | Signal processing method for quickly responding to wrist lifting action and brightening screen in running process |
| CN114298105B (en) * | 2021-12-29 | 2023-08-22 | 东莞市猎声电子科技有限公司 | Signal processing method for quickly responding to wrist lifting action and brightening screen in running process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104713568A (en) | Gait recognition method and corresponding pedometer | |
| CN104075730B (en) | Gait counting method and gait counter | |
| KR101782240B1 (en) | Step counting method and apparatus | |
| CN104146712B (en) | Wearable plantar pressure detection device and plantar pressure detection and attitude prediction method | |
| WO2018127506A1 (en) | Apparatus and method for triggering a fall risk alert to a person | |
| CN206026334U (en) | Motion amount detection device and intelligent wearable equipment comprising same | |
| CN102654405B (en) | Gait counting method and device based on acceleration sensor | |
| US9165113B2 (en) | System and method for quantitative assessment of frailty | |
| CN102551735B (en) | Blood oxygen measuring instrument | |
| CN106030246B (en) | The equipment that is counted for the number of cycles of the cycle movement to object, method and system | |
| CN105496416A (en) | Human motion state recognition method and device | |
| CN104406603A (en) | Step-counting method based on acceleration sensor and device thereof | |
| JP6362521B2 (en) | Behavior classification system, behavior classification device, and behavior classification method | |
| CN105792740A (en) | Detection and calculation of heart rate recovery in non-clinical settings | |
| CN110057380A (en) | Step-recording method, device, terminal and storage medium | |
| CN107890166A (en) | A kind of Intelligent insole based on plantar pressure gesture recognition | |
| CN108958482B (en) | Similarity action recognition device and method based on convolutional neural network | |
| CN112869733B (en) | Real-time heart beat interval measuring and calculating method for ballistocardiogram | |
| JP2010146221A (en) | Behavior recording input support system, behavior input support method, and server | |
| JP2010146223A (en) | Behavior extraction system, behavior extraction method, and server | |
| JP2016010562A (en) | Data analyzer, data analysis method, and data analysis program | |
| CN107393260A (en) | A kind of sitting based reminding method, device and wrist type sitting reminiscences | |
| CN111931568A (en) | Human body falling detection method and system based on enhanced learning | |
| CN104586402A (en) | Feature extracting method for body activities | |
| CN116682171A (en) | Method for training a panic-tense gait recognition model, gait recognition method and related device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150617 |
|
| WD01 | Invention patent application deemed withdrawn after publication |