34results about How to "Improve step counting accuracy" patented technology

The invention provides a step counting method and a terminal device. The step counting method comprises the steps: acquiring an acceleration magnitude of the terminal device in real time; determining maximal values and minimal values in the acceleration magnitude; transforming the frequency domain of the acceleration magnitude between each two adjacent maximal values and two adjacent minimal values when the difference between the adjacent maximal value and minimal value is greater than an acceleration threshold value, and acquiring a walking frequency in the time corresponding to the two adjacent maximal values or the two adjacent minimal values; determining that a user carrying the terminal device moves a step in the corresponding time if the walking frequency in the corresponding time is greater than a preset frequency threshold value, and adding 1 to the step number. By adopting the technical scheme, the probability in misjudging when the step is counted can be reduced, and the step counting precision is improved.

The invention provides a step calculation method, which reduces the interference of body situation of a user in step calculation and improve the step calculation accuracy. The method comprises the following steps: based on a step calculation device with sound recognition function, starting walking, prompting the currently various walking states of the step calculation device, and collecting the user step parameters by a sensor; setting an acceleration threshold for step calculation; collecting the acceleration parameter during walking through the sensor, and the like. Information of walking status corresponding steps can be obtained by combining the classification of acceleration values according to the walking states and the check and countering of an envelope line, the user experience is increased, and the step calculation accuracy of the user with weak or bad body status can be improved.

The invention provides a state recognition and distinguishing method, device, and terminal. The method includes: S100 acceleration original data acquisition; S101 acceleration original data filtering;S102 general state distinguishing according to a filtering reference value; S103 abnormal state distinguishing based on a motion characteristic value in the filtering reference value; and S104 step-counting processing. The invention adopts certain methods, like lowpass filtering, Kalman filtering, energy analysis, frequency analysis and the like to process the acceleration data and extract corresponding acceleration data characteristics. Then, corresponding acceleration information is utilized to judge whether the obtained information is an abnormal situation, if in an abnormal situation, step-counting detection can be carried out, otherwise data can be collected again. The treatment strategy can significantly improve the step-counting precision of a pedometer.

The invention provides a universal gait autocorrelation pedometer for IOS and android platforms and relates to an implementation method of the universal pedometer for the IOS and android platforms and the pedometer. According to the method, a high-precision step calculation function is realized on the basis of data of an acceleration sensor of a mobile phone, and the mobile phone can be carried by a user in any postures, for example, the mobile phone can be held in hands and placed in a pocket of a coat/trousers or a backpack and the like. The method comprises steps as follows: determining sampling frequency of the acceleration sensor, performing low-pass filtering treatment on original data to eliminate noise, calculating fluctuation degree and gait autocorrelation coefficient with a dynamic autocorrelation algorithm, and counting the number of steps. The universal gait autocorrelation pedometer can be used for counting the number of daily walking steps for the mobile phones provided with the acceleration sensor and IOS/android operating systems, the method is provided for various APPs for determining walking behavior of the user, a tool is provided for the user for recording daily activities, and the universal gait autocorrelation pedometer has the characteristics that user behaviors are not required to be preset for training, the statistical accuracy is high, cross-platform use can be realized and the like.

The embodiment of the invention provides a step counting method, equipment and a terminal. The method comprises the following steps: first equipment acquires step counting data of at least two sets of equipment carried by the same user, wherein the first equipment is one of the at least two sets of equipment, or the first equipment is different from the at least two sets of equipment; the first equipment determines the number of steps of the user according to the step counting data of the at least two sets of equipment. According to the step counting method disclosed by the embodiment of the invention, the number of steps of the user is determined according to the step counting data of the at least two sets of equipment of the same user, so that the step counting error generated by step counting of single equipment can be avoided, and the step counting accuracy can be improved.

The invention discloses a method and device for improving the step counting precision and a mobile terminal. The method for improving the step counting precision includes the steps that the movement speed of a user and the duration of the movement speed are acquired; a step counter is controlled to enter a corresponding mode according to the movement speed and the duration; the movement frequency of the user is acquired, and the amplitude threshold value of the step counter is adjusted according to the movement frequency. According to the method and device for improving the step counting precision and the mobile terminal, by acquiring the movement speed of the user and the duration of the movement speed, then controlling the step counter to enter the corresponding mode according to the movement speed and the duration, acquiring the movement frequency of the user and adjusting the amplitude threshold value of the step counter according to the movement frequency, wrong step counting can be effectively eliminated, the step counting precision is improved, an obtained step counting result is more accurate, and the use experience of the user is improved.

The invention discloses a step counting method, a step counting device and a computer readable storage medium. The step counting method comprises the steps of: acquiring acceleration data which comprises effective wave crests; determining a time interval between the current effective wave crest and an effective wave crest obtained last time; when the time interval is greater than a preset interval, acquiring a data area of the effective wave crests until a next time interval is greater than the preset interval; when the number of the effective wave crests in the data area is smaller than a preset value, determining feature information of the effective wave crests in the data area; and when the feature information of the effective wave crests in the data area meets a preset condition, updating step counting data. The step counting method, the step counting device and the computer readable storage medium provided by the invention aim to solve the problem of low step counting precision ofa step counting device in the prior art.

The invention provides a step-counting preprocessing method, a device and a terminal. The method includes the steps of: S101, acquiring acceleration original data; S101, subjecting the acceleration original data to unit conversion to obtain an acceleration value; S102, conducting real-time dynamic threshold calculation according to the acceleration value; S103, judging whether the acceleration value conforms to a real-time dynamic threshold; and S104, carrying out step-counting processing according to the judgment result of the above steps. The invention employs a dynamic threshold method to increase the step-counting precision, thus reducing the influence of arm swing during walking on the step-counting precision. The method mainly involves the application of acceleration model root-finding, acceleration variance, walking frequency, signal energy and other related concepts, and can effectively improve the step-counting precision under the conditions of a small walking range and abnormal gait.

The invention discloses an energy-saving step counting method of intelligent electronic equipment and a pedometer. The pedometer adopts the energy-saving step counting method, a time window firstly receives triaxial acceleration data of intelligent electronic equipment, then triaxial acceleration sample data in the time window is extracted, and then the average dispersion of the triaxial acceleration sample data of a walking period is calculated and used as a threshold value for determining the displacement action of a pedestrian according to the extracted triaxial acceleration sample data of the current time window; the maximum autocorrelation coefficient of adjacent walking periods is calculated and adopted to determine the state of the pedestrian to avoid misjudgment of other daily activities as walking actions, and reduce misjudgment caused by interference actions; in the continuous walking process of the pedestrian, the fixed threshold is changed into the dynamic threshold through adoption of the self-adaptive strategy, the current state of the pedestrian is dynamically detected, the self-adaptive capacity of the method is enhanced, and the phenomenon of losing step counting results caused by using the fixed threshold is avoided. The problems that a current pedometer is high in energy consumption and low in step counting accuracy are solved.

The invention provides a power-driven treadmill control system and a step-counting method. The power-driven treadmill control system comprises two parts of a treadmill end module and a cloud end server module; the treadmill end module has the functions of uploading data, receiving data, judging states, counting steps and the like; the cloud end server module has the functions of receiving data, conducting machine learning, issuing data and storing data; the cloud end server module comprises at least one database and a machine learning module. Through the coordination of the treadmill end module and the cloud end server module, a more accurate, economical and intelligent step-counting scheme can be implemented.

The invention discloses a motion judgment method and device and a computer readable storage medium, and the method comprises the steps: obtaining acceleration data which comprises an effective wave crest; determining a characteristic value of an effective wave crest and a characteristic time point corresponding to the characteristic value according to the acceleration data; determining a first parameter value according to the characteristic value and determining a second parameter value according to a characteristic time point; and determining the motion state of the user according to the first parameter value and the second parameter value. The invention provides a motion judgment method, a judgment device and a computer readable storage medium, and aims to solve the problem of low step counting accuracy of a step counting device due to the fact that the step counting device does not process acceleration data according to the motion state of a user in the prior art.

The invention provides a runner identity identification and step counting method based on a running machine. The runner identity identification and step counting method comprises the steps of: 1, collecting current values of the running machine at different speeds separately; 2, transmitting the current values to a database of a cloud server separately by means of the running machine; 3, extracting features of the current values by means of the cloud server separately, and carrying out normalization processing on the features; 4, training the cloud server based on the normalized features to obtain classification parameters; 5, and transmitting the parameters to a controller of the running machine by means of the cloud server, identifying the identity of a runner according to the classification parameters by means of the controller, and counting a number of steps by means of the controller. The runner identity identification and step counting method improves the precision of runner identity identification and step counting, enhances the function of the running machine, and is economical and practical.

The invention is applicable to the technical field of computers, and relates to a gait detection algorithm, device and system. The gait detection algorithm comprises the following steps: resetting a climbing number and a downhill number to 0 until a resultant acceleration module value is larger than a preset threshold value; updating the climbing number and the downhill number until the climbing number is larger than a preset threshold value, wherein the resultant acceleration module value is at a peak value; resetting the downhill number to 0, and updating the downhill number until the downhill number is larger than a preset threshold value, wherein the resultant acceleration module value is at a valley value; and resetting the uphill number to 0, and updating the uphill number until theuphill number is larger than the preset threshold value, wherein the resultant acceleration module value meets a preset requirement, and the step number is increased by 1. According to the gait detection algorithm disclosed by the invention, the difference value between the resultant acceleration module value and the resultant acceleration module value at the adjacent time are compared with a plurality of preset threshold values, and each state in a walking period is determined, so that a complete walking period is obtained, step counting is realized, and the gait detection algorithm is more accurate than a conventional step counting algorithm.