CN112268583B - Method and device for detecting track of pedestrian going up and down stairs - Google Patents
Method and device for detecting track of pedestrian going up and down stairs Download PDFInfo
- Publication number
- CN112268583B CN112268583B CN202011145668.7A CN202011145668A CN112268583B CN 112268583 B CN112268583 B CN 112268583B CN 202011145668 A CN202011145668 A CN 202011145668A CN 112268583 B CN112268583 B CN 112268583B
- Authority
- CN
- China
- Prior art keywords
- single step
- pedestrian
- state
- label
- space
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
Abstract
The invention discloses a track detection method and a track detection device for a pedestrian ascending and descending stair state, wherein the method comprises the steps of acquiring motion parameters of the pedestrian to generate sampling point sequence data; judging the sampling point sequence data to obtain the walking state of the pedestrian; when in a walking state, further generating a pedestrian single step sequence set from the sampling point sequence data in the corresponding state, and numbering and detecting each single step in the set to obtain a label of each single step, wherein the label comprises an initial step label and an intermediate step label; detecting the state of the pedestrian climbing up and down the stairs from the single step marked as the middle step label, and identifying the motion state of the single step of each middle step label; obtaining the measuring track of the pedestrian when going up and down the stairs according to the motion state; the beneficial effects are as follows: the motion parameters of the pedestrians are measured and processed, so that the states and the tracks of the pedestrians going up and down the stairs are automatically detected, and the problem that the prior art cannot be applied to automatic detection and measurement of the tracks of the states of the pedestrians going up and down the stairs is solved.
Description
Technical Field
The invention relates to the technical field of indoor positioning, in particular to a method and a device for detecting a track of a pedestrian ascending and descending stair state.
Background
In the prior art, a pedestrian track positioning technology is effectively applied, but from the application range, the pedestrian track positioning technology is mostly applied to outdoor track positioning detection, when a pedestrian enters an indoor space, due to the particularity of the environment, the current technology mainly realizes the track positioning of the pedestrian in a horizontal space, however, the track of the pedestrian in the indoor space not only has a walking track in the horizontal space, but also has the situation that the pedestrian in the indoor space goes up and down stairs. Therefore, existing processing schemes are not applicable to this situation.
Disclosure of Invention
The invention aims to: a method and a device for detecting the track of a pedestrian ascending and descending stairs are provided, so that the condition of the pedestrian ascending and descending stairs is detected indoors and the track of the pedestrian ascending and descending stairs is measured.
In a first aspect: a trajectory detection method for a pedestrian ascending and descending stair state, the method comprising:
acquiring motion parameters of pedestrians and generating sampling point sequence data according to the measuring time sequence, wherein the motion parameters are obtained by real-time measurement of wearable equipment;
judging the sampling point sequence data to obtain a state result of the pedestrian, wherein the state result comprises a walking state and a non-walking state;
when the pedestrian is in a walking state, further generating a pedestrian single-step sequence set by the sampling point sequence data in the corresponding state, wherein each single step in the set comprises an altitude parameter and an azimuth angle parameter;
numbering and state detecting are carried out on each single step in the pedestrian single step sequence set to obtain a detection result of each single step, and a corresponding label is marked on each single step according to the detection result of the single step state, wherein the label comprises an initial step label and a middle step label;
then, according to the numbering sequence of each single step, detecting the states of the pedestrians going up and down the stairs from the first single step to the single step marked as the middle step label, and identifying the motion state of each middle step label single step according to the height relation between the adjacent single steps of which the numbers are within the preset numbering range;
and finally, obtaining the measuring track of the pedestrian when going up and down the stairs according to the single-step motion state of each intermediate step label.
As an optional embodiment of the present application, the height parameter is a measurement value of the wearable device at each time of starting or ending of a single step;
the azimuth angle parameter is a measured value of the wearable device at each single step starting or ending moment.
As an optional implementation manner of the present application, the step of marking a corresponding tag for each single step according to the single step status detection result includes the following steps:
firstly, a first single step in a pedestrian single step sequence set is defaulted to be marked with an initial step label, and the label is one;
and detecting each single step from the second single step in the pedestrian single step sequence set, and if the height difference between the height of the current single step and the height of the previous single step is greater than a height threshold value, marking the initial step label for the single step, otherwise, marking the middle step label for the single step.
As an optional implementation manner of the present application, the identifying a motion state of each intermediate step tag single step specifically includes:
for the single-step SPACE (i) of the middle-step label, identifying the single-step SPACE (i) of the middle-step label into three motion states according to the height relation between the single-step SPACE (j) with the single-step number j in the range of (i-N, i) and the adjacent SPACE (j + 1): going upstairs, going downstairs and walking on the plane; wherein N is a preset step interval threshold, and i is a single step number;
if the relationship between the height PHigh (j) of each single step SPACE (j) in the range of (i-N, i) and the height PHigh (j +1) of the adjacent single step SPACE (j +1) meets the requirement that the heights PHigh (j +1) -PHigh (j) are larger than Hstep, namely the adjacent single step heights are in an increasing relationship, the single step SPACE (i) of the middle step label is identified as ascending;
if the relationship between the height PHigh (j) of each single step SPACE (j) and the height PHigh (j +1) of the adjacent single step SPACE (j) in the range of (i-N, i) meets the requirement of PHigh (j +1) -PHigh (j) < -Hstep, namely the adjacent single step heights are in descending relationship, the single step SPACE (i) of the middle step label is identified as descending stairs;
wherein Hstep is a preset single step height threshold.
As an optional implementation manner of the present application, the obtaining of the measurement trajectory of the pedestrian when going up and down the stairs according to the motion state of each middle step tag single step specifically includes:
when the state is ascending or descending stairs, the track point of the single step SPACE (i) is shifted by a vertical distance MSPH (i) upwards or downwards in the vertical height direction relative to the track point of the single step SPACE (i-1), and the track point of the single step SPACE (i) is shifted by a horizontal distance MSPL (i) relative to the track point of the SPACE (i-1) according to an azimuth angle PAzim (i) in the plane direction;
and obtaining the measuring track of the pedestrian when going up and down the stairs according to the offset vertical distance MSPH (i) and the offset horizontal distance MSPL (i) obtained in each state.
In a second aspect: a trajectory detection device for a pedestrian ascending and descending stair state, comprising:
the indoor pedestrian motion parameter measuring unit is used for acquiring the motion parameters of pedestrians and generating sampling point sequence data according to the measuring time sequence, and the motion parameters are obtained by real-time measurement through wearable equipment;
an indoor pedestrian walking state detection unit for:
judging the sampling point sequence data to obtain a state result of the pedestrian, wherein the state result comprises a walking state and a non-walking state;
when the pedestrian walks, the sampling point sequence data in the corresponding state is used as a pedestrian single step sequence set, and each single step in the set comprises an altitude parameter and an azimuth angle parameter;
the indoor pedestrian up-and-down stair state detection unit comprises an indoor pedestrian single step state detection module and an indoor pedestrian up-and-down stair state detection module;
the indoor pedestrian single-step state detection module is used for numbering and state detection of each single step in the pedestrian single-step sequence set to obtain a detection result of each single step, and marking a corresponding label for each single step according to the detection result of the single step state, wherein the label comprises an initial step label and a middle step label;
the indoor pedestrian stair ascending and descending state detection module is used for detecting the pedestrian stair ascending and descending state of the single step marked as the middle step label from the first single step according to the serial number sequence of each single step, and identifying the motion state of each middle step label single step according to the height relation between the adjacent single steps of which the serial numbers are within the preset serial number range;
and the indoor pedestrian ascending and descending stair track measuring unit is used for obtaining the measuring track of the pedestrian ascending and descending stair according to the single-step motion state of each middle step label.
As an optional implementation manner of the present application, the indoor pedestrian ascending and descending stair state detection unit further includes an indoor pedestrian ascending and descending stair stopping state detection module;
the indoor pedestrian up and down stair state detection module is used for stopping pedestrian up and down stair state detection and pedestrian up and down stair track measurement in the pedestrian up and down stair state detection process when detecting that any trigger condition is met.
As an optional implementation manner of the present application, the step of marking a corresponding tag for each single step according to the single step status detection result includes the following steps:
firstly, a first single step in a pedestrian single step sequence set is defaulted to be marked with an initial step label, and the label is one;
and detecting each single step from the second single step in the pedestrian single step sequence set, and if the height difference between the height of the current single step and the height of the previous single step is greater than a height threshold value, marking the initial step label for the single step, otherwise, marking the middle step label for the single step.
As an optional implementation manner of the present application, the identifying a motion state of each intermediate step tag single step specifically includes:
for the single-step SPACE (i) of the middle-step label, identifying the single-step SPACE (i) of the middle-step label into three motion states according to the height relation between the single-step SPACE (j) with the single-step number j in the range of (i-N, i) and the adjacent SPACE (j + 1): going upstairs, going downstairs and walking on the plane; wherein N is a preset step interval threshold, and i is a single step number;
if the relationship between the height PHigh (j) of each single step SPACE (j) in the range of (i-N, i) and the height PHigh (j +1) of the adjacent single step SPACE (j +1) meets the requirement that the heights PHigh (j +1) -PHigh (j) are larger than Hstep, namely the adjacent single step heights are in an increasing relationship, the single step SPACE (i) of the middle step label is identified as ascending;
if the relationship between the height PHigh (j) of each single step SPACE (j) and the height PHigh (j +1) of the adjacent single step SPACE (j) in the range of (i-N, i) meets the requirement of PHigh (j +1) -PHigh (j) < -Hstep, namely the adjacent single step heights are in descending relationship, the single step SPACE (i) of the middle step label is identified as descending stairs;
wherein Hstep is a preset single step height threshold.
As an optional implementation manner of the present application, the obtaining of the measurement trajectory of the pedestrian when going up and down the stairs according to the motion state of each middle step tag single step specifically includes:
when the state is ascending or descending stairs, the track point of the single step SPACE (i) is shifted by a vertical distance MSPH (i) upwards or downwards in the vertical height direction relative to the track point of the single step SPACE (i-1), and the track point of the single step SPACE (i) is shifted by a horizontal distance MSPL (i) relative to the track point of the SPACE (i-1) according to an azimuth angle PAzim (i) in the plane direction;
and obtaining the measuring track of the pedestrian when going up and down the stairs according to the offset vertical distance MSPH (i) and the offset horizontal distance MSPL (i) obtained in each state.
By adopting the technical scheme, the method has the following advantages: according to the method and the device for detecting the pedestrian up-and-down stair state track, the wearable equipment is used for measuring the motion parameters of the pedestrian and processing the acquired data, so that the pedestrian up-and-down stair state and track calculation are automatically detected, the detection in a horizontal space is realized, the pedestrian up-and-down stair state judgment in an indoor space is also realized, and the problem that the indoor pedestrian track navigation technology cannot be applied to the automatic track detection and track measurement of the pedestrian up-and-down stair state in the prior art is solved.
Drawings
Fig. 1 is a flowchart of a method for detecting a pedestrian's ascending/descending trajectory according to an embodiment of the present invention;
fig. 2 is a structural diagram of a trajectory detection device for a pedestrian ascending and descending stair state according to an embodiment of the present invention.
Detailed Description
Specific embodiments of the present invention will be described in detail below, and it should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that: it is not necessary to employ these specific details to practice the present invention. In other instances, well-known circuits, software, or methods have not been described in detail so as not to obscure the present invention.
Throughout the specification, reference to "one embodiment," "an embodiment," "one example," or "an example" means: the particular features, structures, or characteristics described in connection with the embodiment or example are included in at least one embodiment of the invention. Thus, the appearances of the phrases "in one embodiment," "in an embodiment," "one example" or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combination and/or sub-combination in one or more embodiments or examples. Further, those of ordinary skill in the art will appreciate that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale.
The present invention will be described in detail below with reference to the accompanying drawings.
Referring to fig. 1, a method for detecting a pedestrian's ascending/descending trajectory, the method comprising:
s101, acquiring motion parameters of the pedestrian and generating sampling point sequence data according to the measurement time sequence, wherein the motion parameters are obtained through real-time measurement of wearable equipment.
In particular, the wearable device is a portable device worn directly on the body, or integrated into the clothing or accessories of the user; the motion parameters include motion parameters such as three-dimensional acceleration, three-dimensional Euler angle, azimuth angle, altitude (distance measurement value) and the like.
And forming motion parameter sampling point sequence data according to the measurement time sequence, wherein the data of each motion parameter sampling point in the collection point sequence comprises sampling time Ts and a measured motion parameter, such as motion acceleration ACCSUm, horizontal acceleration ACCLEVER, vertical acceleration ACCVIertical, azimuth angle Azimu, altitude (distance measurement value) highlevel and the like, wherein the motion acceleration ACCSUm is the vector sum of the horizontal acceleration ACCLEVER and the vertical acceleration ACCVIertical, and the altitude is the altitude.
And S102, judging the sampling point sequence data to obtain a state result of the pedestrian, wherein the state result comprises a walking state and a non-walking state.
Specifically, the walking state detection of the pedestrians in the individual rooms is carried out on the motion parameter sampling point sequence, and the motion parameter sampling points are divided into two types according to the detection result: walking, non-walking; the motion parameter sampling point data of the walking state is further used for subsequent indoor pedestrian stair climbing state detection;
the indoor pedestrian walking motion state detection method is a known technology (also embodied in the background art), and therefore is not described herein again.
S103, in the walking state, the sampling point sequence data in the corresponding state is used as a pedestrian single step sequence set, and each single step in the set comprises an altitude parameter and an azimuth angle parameter.
Specifically, human walking gait is periodic, each single step gait cycle is a process from single-foot step lifting to single-foot step landing, the reciprocating walking motion of two feet forms a complete pedestrian walking motion state, the motion states of the pedestrian single step gait starting and ending can be detected by using the motion parameters of the pedestrian, a pedestrian single step sequence set SPACE is generated according to the motion parameter sampling point data, and the single step (i) in the set SPACE has the following parameters: height PHigh and azimuth angle PAzim, wherein i is a single step number with an increasing sequence, and the height parameter is a measured value of the wearable device at the starting or ending time of each single step; the azimuth angle parameter is a measured value of the wearable device at each single step starting or ending moment;
generally, the height PHigh and the azimuth PAzim should be measured by the wearable device at the same time to obtain parameter values, such as a single-step start time or a single-step end time.
And S104, numbering and state detection are carried out on each single step in the pedestrian single step sequence set to obtain a detection result of each single step, and a corresponding label is marked on each single step according to the detection result of the single step state, wherein the label comprises an initial step label and a middle step label.
Specifically, firstly, a first single step in a pedestrian single step sequence set is defaulted to be marked with an initial step label, and the label is one;
detecting each single step from the second single step in the pedestrian single step sequence set, and if the height difference between the height of the current single step and the height of the previous single step is greater than a height threshold value, marking the initial step label for the single step, or else, marking the middle step label for the single step;
for example, if the height difference dspight (i) between height PHigh (i) of single-step SPACE (i) and height PHigh (i-1) of SPACE (i-1) is dspight (i) ═ PHigh (i) -PHigh (i) |, and is greater than threshold value MPHIGHT, then the start step label is applied to single-step SPACE (i), otherwise the middle step label is applied to single-step SPACE (i).
And S105, starting the first single step according to the numbering sequence of each single step, detecting the states of the pedestrians going up and down the stairs from the single step marked as the middle step label, and identifying the motion state of each middle step label single step according to the height relation between the adjacent single steps of which the numbers are within the preset numbering range.
Specifically, the motion state of each single step marked as a middle step label can be obtained, and the motion state can also be understood as a middle single step, and the two have the same meaning;
for the single-step SPACE (i) of the middle-step label, identifying the single-step SPACE (i) of the middle-step label into three motion states (namely motion states) according to the height relation between the single-step SPACE (j) with the single-step number j in the range of (i-N, i) and the adjacent SPACE (j + 1): going upstairs, going downstairs and walking on the plane; wherein N is a preset step interval threshold, and i is a single step number;
if the relationship between the height PHigh (j) of each single step SPACE (j) in the range of (i-N, i) and the height PHigh (j +1) of the adjacent single step SPACE (j +1) meets the requirement that the heights PHigh (j +1) -PHigh (j) are larger than Hstep, namely the adjacent single step heights are in an increasing relationship, the single step SPACE (i) of the middle step label is identified as ascending;
if the relationship between the height PHigh (j) of each single step SPACE (j) and the height PHigh (j +1) of the adjacent single step SPACE (j) in the range of (i-N, i) meets the requirement of PHigh (j +1) -PHigh (j) < -Hstep, namely the adjacent single step heights are in descending relationship, the single step SPACE (i) of the middle step label is identified as descending stairs;
wherein Hstep is a preset single step height threshold.
Namely, detecting the ascending and descending stair state for each middle single step in the pedestrian single step sequence set until the detection of the pedestrian walking motion state is finished.
In practice, when the single step status is detected as ascending stairs or descending stairs for the first time, the single step status of each single step SPACE (j) numbered in the range of (i-N, i-1) can be labeled as the single step status of SPACE (i).
And S106, finally, obtaining the measuring track of the pedestrian when going up and down the stairs according to the single-step motion state of each middle step label.
Specifically, when the state is ascending or descending, the single step SPACE (i) track point is shifted by a vertical distance msph (i) upwards or downwards in the vertical height direction relative to the track point of the single step SPACE (i-1), and is shifted by a horizontal distance mspl (i) relative to the track point of the SPACE (i-1) according to the azimuth angle pazim (i) of the single step SPACE (i) in the plane direction;
wherein, the vertical distance MSPH (i) can adopt a height difference of single-step PACE (i) and single-step SPACE (i-1), and the horizontal distance MSPL (i) can adopt a stair fixed width value;
and obtaining the measuring track of the pedestrian when going up and down the stairs according to the offset vertical distance MSPH (i) and the offset horizontal distance MSPL (i) obtained in each state.
When the method is applied, in the pedestrian stair ascending and descending state detection process, when any trigger condition is detected to be met, the pedestrian stair ascending and descending state detection and the pedestrian stair ascending and descending track measurement are stopped;
the trigger condition comprises that the detection analysis of all single-step SPACE (i) in the single-step sequence set is completed; if the pedestrian stops walking, stopping detecting the state of going upstairs and downstairs of the pedestrian and measuring the track of going upstairs and downstairs of the pedestrian;
and when the single step label is detected as the initial step, stopping the detection of the pedestrian stair ascending and descending state, and starting to detect the subsequent single step SPACE (i) marked as the middle step label for the pedestrian stair ascending and descending state again.
By adopting the scheme, the motion parameters acquired by the wearable equipment are measured and processed to determine whether the pedestrian is in a walking state or a non-walking state, and the calculation of the state and the track of the pedestrian climbing up and down the stairs is automatically detected by processing the data acquired by the walking state; the defect that in the prior art, the indoor map is matched with the signal points to cause inconvenience in use and the defect that whether pedestrians walk up and down stairs or not cannot be distinguished is overcome.
Based on the same inventive concept, the embodiment of the invention also discloses a track detection device for the states of ascending and descending stairs of pedestrians, which comprises:
the indoor pedestrian motion parameter measuring unit is used for acquiring the motion parameters of pedestrians and generating sampling point sequence data according to the measuring time sequence, and the motion parameters are obtained by real-time measurement through wearable equipment; and synchronously outputting sampling point sequence data generated by the motion parameters to an indoor pedestrian walking state detection unit;
an indoor pedestrian walking state detection unit for:
judging the sampling point sequence data to obtain a state result of the pedestrian, wherein the state result comprises a walking state and a non-walking state;
when the pedestrian walks, the sampling point sequence data in the corresponding state is used as a pedestrian single step sequence set, and each single step in the set comprises an altitude parameter and an azimuth angle parameter;
the indoor pedestrian up-and-down stair state detection unit comprises an indoor pedestrian single step state detection module and an indoor pedestrian up-and-down stair state detection module;
the indoor pedestrian single-step state detection module is used for numbering and state detection of each single step in the pedestrian single-step sequence set to obtain a detection result of each single step, and marking a corresponding label for each single step according to the detection result of the single step state, wherein the label comprises an initial step label and a middle step label; the method comprises the following steps:
firstly, a first single step in a pedestrian single step sequence set is defaulted to be marked with an initial step label, and the label is one;
and detecting each single step from the second single step in the pedestrian single step sequence set, and if the height difference between the height of the current single step and the height of the previous single step is greater than a height threshold value, marking the initial step label for the single step, otherwise, marking the middle step label for the single step.
The indoor pedestrian stair ascending and descending state detection module is used for detecting the pedestrian stair ascending and descending state of the single step marked as the middle step label from the first single step according to the serial number sequence of each single step, and identifying the motion state of each middle step label single step according to the height relation between the adjacent single steps of which the serial numbers are within the preset serial number range; the step of identifying the motion state of each intermediate step label single step specifically comprises the following steps:
for the single-step SPACE (i) of the middle-step label, identifying the single-step SPACE (i) of the middle-step label into three motion states according to the height relation between the single-step SPACE (j) with the single-step number j in the range of (i-N, i) and the adjacent SPACE (j + 1): going upstairs, going downstairs and walking on the plane; wherein N is a preset step interval threshold, and i is a single step number;
if the relationship between the height PHigh (j) of each single step SPACE (j) in the range of (i-N, i) and the height PHigh (j +1) of the adjacent single step SPACE (j +1) meets the requirement that the heights PHigh (j +1) -PHigh (j) are larger than Hstep, namely the adjacent single step heights are in an increasing relationship, the single step SPACE (i) of the middle step label is identified as ascending;
if the relationship between the height PHigh (j) of each single step SPACE (j) and the height PHigh (j +1) of the adjacent single step SPACE (j) in the range of (i-N, i) meets the requirement of PHigh (j +1) -PHigh (j) < -Hstep, namely the adjacent single step heights are in descending relationship, the single step SPACE (i) of the middle step label is identified as descending stairs;
wherein Hstep is a preset single step height threshold.
And the indoor pedestrian ascending and descending stair track measuring unit is used for obtaining the measuring track of the pedestrian ascending and descending stair according to the single-step motion state of each middle step label.
Specifically, when the state is ascending or descending, the single step SPACE (i) track point is shifted by a vertical distance msph (i) upwards or downwards in the vertical height direction relative to the track point of the single step SPACE (i-1), and is shifted by a horizontal distance mspl (i) relative to the track point of the SPACE (i-1) according to the azimuth angle pazim (i) of the single step SPACE (i) in the plane direction;
and obtaining the measuring track of the pedestrian when going up and down the stairs according to the offset vertical distance MSPH (i) and the offset horizontal distance MSPL (i) obtained in each state.
When the indoor pedestrian ascending and descending stair state detection unit is applied, the indoor pedestrian ascending and descending stair state detection unit further comprises an indoor pedestrian ascending and descending stair stopping state detection module;
the indoor pedestrian up and down stair state detection module is used for stopping pedestrian up and down stair state detection and pedestrian up and down stair track measurement in the pedestrian up and down stair state detection process when detecting that any trigger condition is met.
The trigger condition comprises that the detection analysis of all single-step SPACE (i) in the single-step sequence set is completed; if the pedestrian stops walking, stopping detecting the state of going upstairs and downstairs of the pedestrian and measuring the track of going upstairs and downstairs of the pedestrian;
when the single-step SPACE (i) label is detected as the initial step, the detection of the stair climbing state of the pedestrian at this time is stopped, and the detection of the stair climbing state of the pedestrian at the subsequent single-step SPACE (j) labeled as the intermediate step label is carried out again.
Through above-mentioned scheme, through utilizing wearable equipment to measure pedestrian's motion parameter to handle the data that acquire, thereby the calculation of the state and the orbit that the automated inspection goes up and down the stair of pedestrian, not only realize the detection in horizontal space, still realize the state judgement of going up and down the stair of pedestrian in the indoor space, in order to overcome prior art, indoor pedestrian orbit navigation technique can not be applied to the orbit automated inspection and the orbit measurement's of pedestrian's state of going up and down the stair problem.
It should be noted that, for the specific implementation in the foregoing embodiment of the apparatus, reference may be made to the description in the foregoing embodiment of the method, and details are not described herein again.
The working process of the technical scheme provided by the embodiment is as follows:
(1) the pedestrian carries human wearing equipment, opens indoor pedestrian motion parameter measurement unit, begins to measure indoor pedestrian motion parameter, gives indoor pedestrian state of walking detection unit with motion parameter sampling point data synchronization output.
(2) The pedestrian walks on the indoor floor, the indoor pedestrian walking state detection unit detects the motion parameter sampling point data during the walking period of the indoor pedestrian as the walking state, and outputs the motion parameter sampling point data to the indoor pedestrian up-down stair state detection unit.
(3) The indoor pedestrian stair ascending and descending state detection unit generates a pedestrian single-step sequence set according to the motion parameter sampling point data and detects the pedestrian single-step sequence set, the first step in the pedestrian single-step sequence set is marked as an initial step, the subsequent single step is marked as a middle step, and the single step for detecting indoor flat walking is marked as plane walking.
(4) When the pedestrian finishes the flat-layer walking and starts to walk to other floors, the indoor pedestrian ascending and descending stair state detection unit detects the state of ascending the stairs in a single step, and marks the single step of ascending the stairs in the walking as ascending the stairs.
(5) The pedestrian finishes going upstairs to enter the floor and continues walking movement, and the indoor pedestrian upstairs and downstairs state detection unit marks the detected single step after walking on the entering floor as plane walking.
(6) The pedestrian finishes walking, and the indoor pedestrian walking state detection unit and the indoor pedestrian stair ascending and descending state detection unit finish detection.
(7) The pedestrian walking track is measured, the track position of a single step with a single step mark value of ascending stairs or descending stairs is offset by the height difference MSPH (i) of the previous single step in the vertical height direction relative to the track position of the previous single step, and the track position is offset by a preset stair width value MSPL in the horizontal direction according to the single step azimuth angle PAzim azimuth.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (7)
1. A track detection method for a pedestrian ascending and descending stair state is characterized by comprising the following steps:
acquiring motion parameters of pedestrians and generating sampling point sequence data according to the measuring time sequence, wherein the motion parameters are obtained by real-time measurement of wearable equipment; the motion parameters comprise three-dimensional acceleration, three-dimensional Euler angle, azimuth angle and height parameters;
judging the sampling point sequence data to obtain a state result of the pedestrian, wherein the state result comprises a walking state and a non-walking state;
when the pedestrian is in a walking state, further generating a pedestrian single-step sequence set by the sampling point sequence data in the corresponding state, wherein each single step in the set comprises an altitude parameter and an azimuth angle parameter;
numbering and state detecting are carried out on each single step in the pedestrian single step sequence set to obtain a detection result of each single step, and a corresponding label is marked on each single step according to the detection result of the single step state, wherein the label comprises an initial step label and a middle step label;
then, according to the numbering sequence of each single step, detecting the states of the pedestrians going up and down the stairs from the first single step to the single step marked as the middle step label, and identifying the motion state of each middle step label single step according to the height relation between the adjacent single steps of which the numbers are within the preset numbering range;
finally, obtaining the measuring track of the pedestrian when going up and down the stairs according to the single-step motion state of each intermediate step label; the height parameter is a measured value of the wearable equipment at each single step starting or ending moment;
the azimuth angle parameter is a measured value of the wearable device at each single step starting or ending moment;
the step of marking a corresponding label on each single step according to the single step state detection result comprises the following steps:
firstly, a first single step in a pedestrian single step sequence set is defaulted to be marked with an initial step label, and the label is one;
and detecting each single step from the second single step in the pedestrian single step sequence set, and if the height difference between the height of the current single step and the height of the previous single step is greater than a height threshold value, marking the initial step label for the single step, otherwise, marking the middle step label for the single step.
2. The method for detecting the pedestrian ascending and descending stair state trajectory according to claim 1, wherein the step of identifying the motion state of each intermediate step tag single step specifically comprises:
for the single-step SPACE (i) of the middle-step label, identifying the single-step SPACE (i) of the middle-step label into three motion states according to the height relation between the single-step SPACE (j) with the single-step number j in the range of (i-N, i) and the adjacent SPACE (j + 1): going upstairs, going downstairs and walking on the plane; wherein N is a preset step interval threshold, and i is a single step number;
if the relationship between the height PHigh (j) of each single step SPACE (j) in the range of (i-N, i) and the height PHigh (j +1) of the adjacent single step SPACE (j +1) meets the requirement that the heights PHigh (j +1) -PHigh (j) are larger than Hstep, namely the adjacent single step heights are in an increasing relationship, the single step SPACE (i) of the middle step label is identified as ascending;
if the relationship between the height PHigh (j) of each single step SPACE (j) and the height PHigh (j +1) of the adjacent single step SPACE (j) in the range of (i-N, i) meets the requirement of PHigh (j +1) -PHigh (j) < -Hstep, namely the adjacent single step heights are in descending relationship, the single step SPACE (i) of the middle step label is identified as descending stairs;
wherein Hstep is a preset single step height threshold.
3. The method for detecting the pedestrian ascending and descending stair state trajectory according to claim 2, wherein the step of obtaining the pedestrian ascending and descending stair measurement trajectory according to the single step motion state of each intermediate step tag specifically comprises:
when the state is ascending or descending stairs, the track point of the single step SPACE (i) is shifted by a vertical distance MSPH (i) upwards or downwards in the vertical height direction relative to the track point of the single step SPACE (i-1), and the track point of the single step SPACE (i) is shifted by a horizontal distance MSPL (i) relative to the track point of the SPACE (i-1) according to an azimuth angle PAzim (i) in the plane direction;
and obtaining the measuring track of the pedestrian when going up and down the stairs according to the offset vertical distance MSPH (i) and the offset horizontal distance MSPL (i) obtained in each state.
4. A pedestrian's orbit detection device of stair state that goes up and down, its characterized in that includes:
the indoor pedestrian motion parameter measuring unit is used for acquiring the motion parameters of pedestrians and generating sampling point sequence data according to the measuring time sequence, and the motion parameters are obtained by real-time measurement through wearable equipment;
an indoor pedestrian walking state detection unit for:
judging the sampling point sequence data to obtain a state result of the pedestrian, wherein the state result comprises a walking state and a non-walking state;
when the pedestrian is in a walking state, further generating a pedestrian single-step sequence set by the sampling point sequence data in the corresponding state, wherein each single step in the set comprises an altitude parameter and an azimuth angle parameter;
the indoor pedestrian up-and-down stair state detection unit comprises an indoor pedestrian single step state detection module and an indoor pedestrian up-and-down stair state detection module;
the indoor pedestrian single-step state detection module is used for numbering and state detection of each single step in the pedestrian single-step sequence set to obtain a detection result of each single step, and marking a corresponding label for each single step according to the detection result of the single step state, wherein the label comprises an initial step label and a middle step label;
the indoor pedestrian stair ascending and descending state detection module is used for detecting the pedestrian stair ascending and descending state from the first single step to the single step marked as the middle step label according to the serial number sequence of each single step, and identifying the motion state of each middle step label single step according to the height relation between the adjacent single steps of which the serial numbers are within the preset serial number range;
the indoor pedestrian ascending and descending stair track measuring unit is used for obtaining a measuring track of a pedestrian ascending and descending stair according to the single-step motion state of each middle step label;
the step of marking a corresponding label on each single step according to the single step state detection result comprises the following steps:
firstly, a first single step in a pedestrian single step sequence set is defaulted to be marked with an initial step label, and the label is one;
and detecting each single step from the second single step in the pedestrian single step sequence set, and if the height difference between the height of the current single step and the height of the previous single step is greater than a height threshold value, marking the initial step label for the single step, otherwise, marking the middle step label for the single step.
5. The device for detecting the pedestrian ascending and descending stair state trajectory according to claim 4, wherein the indoor pedestrian ascending and descending stair state detection unit further comprises an indoor pedestrian stopping ascending and descending stair state detection module;
the indoor pedestrian up and down stair state detection module is used for stopping pedestrian up and down stair state detection and pedestrian up and down stair track measurement in the pedestrian up and down stair state detection process when detecting that any trigger condition is met.
6. The device for detecting the pedestrian's ascending and descending stair state trajectory according to claim 5, wherein the step of identifying the motion state of each intermediate step tag single step specifically comprises:
for the single-step SPACE (i) of the middle-step label, identifying the single-step SPACE (i) of the middle-step label into three motion states according to the height relation between the single-step SPACE (j) with the single-step number j in the range of (i-N, i) and the adjacent SPACE (j + 1): going upstairs, going downstairs and walking on the plane; wherein N is a preset step interval threshold, and i is a single step number;
if the relationship between the height PHigh (j) of each single step SPACE (j) in the range of (i-N, i) and the height PHigh (j +1) of the adjacent single step SPACE (j +1) meets the requirement that the heights PHigh (j +1) -PHigh (j) are larger than Hstep, namely the adjacent single step heights are in an increasing relationship, the single step SPACE (i) of the middle step label is identified as ascending;
if the relationship between the height PHigh (j) of each single step SPACE (j) and the height PHigh (j +1) of the adjacent single step SPACE (j) in the range of (i-N, i) meets the requirement of PHigh (j +1) -PHigh (j) < -Hstep, namely the adjacent single step heights are in descending relationship, the single step SPACE (i) of the middle step label is identified as descending stairs;
wherein Hstep is a preset single step height threshold.
7. The device for detecting the pedestrian ascending and descending stair state trajectory according to claim 6, wherein the step of obtaining the pedestrian ascending and descending stair measurement trajectory according to the single step motion state of each intermediate step tag specifically comprises:
when the state is ascending or descending stairs, the track point of the single step SPACE (i) is shifted by a vertical distance MSPH (i) upwards or downwards in the vertical height direction relative to the track point of the single step SPACE (i-1), and the track point of the single step SPACE (i) is shifted by a horizontal distance MSPL (i) relative to the track point of the SPACE (i-1) according to an azimuth angle PAzim (i) in the plane direction;
and obtaining the measuring track of the pedestrian when going up and down the stairs according to the offset vertical distance MSPH (i) and the offset horizontal distance MSPL (i) obtained in each state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011145668.7A CN112268583B (en) | 2020-10-23 | 2020-10-23 | Method and device for detecting track of pedestrian going up and down stairs |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011145668.7A CN112268583B (en) | 2020-10-23 | 2020-10-23 | Method and device for detecting track of pedestrian going up and down stairs |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112268583A CN112268583A (en) | 2021-01-26 |
| CN112268583B true CN112268583B (en) | 2021-09-24 |
Family
ID=74342510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011145668.7A Active CN112268583B (en) | 2020-10-23 | 2020-10-23 | Method and device for detecting track of pedestrian going up and down stairs |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112268583B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106643739A (en) * | 2017-02-23 | 2017-05-10 | 烟台中飞海装科技有限公司 | Indoor environment personnel location method and system |
| CN106768032A (en) * | 2016-12-06 | 2017-05-31 | 水利部交通运输部国家能源局南京水利科学研究院 | A kind of processing method for improving Dam safety automation monitoring data reliability |
| CN107990895A (en) * | 2017-11-08 | 2018-05-04 | 北京工商大学 | A kind of building floor gap pedestrian track tracking and system based on wearable IMU |
| CN109827577A (en) * | 2019-03-26 | 2019-05-31 | 电子科技大学 | High-precision inertial navigation location algorithm based on motion state detection |
| CN109974694A (en) * | 2019-03-11 | 2019-07-05 | 东南大学 | One kind is based on the barometrical indoor pedestrian's 3D localization method of UWB/IMU/ |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2005224786B2 (en) * | 2004-03-12 | 2010-03-25 | Vectronix Ag | Apparatus and method of determining 3D pedestrian motion by using projection planes |
| CA2653622C (en) * | 2006-05-31 | 2017-07-04 | Trx Systems, Inc. | Method and system for locating and monitoring first responders |
| KR20160099414A (en) * | 2015-02-12 | 2016-08-22 | 김형철 | Supporting tag, tag reader, controller to enable pass a stairs |
| CN105243352A (en) * | 2015-09-07 | 2016-01-13 | 苏州大学张家港工业技术研究院 | 3D motion recognition method and device |
| CN110426037A (en) * | 2019-08-08 | 2019-11-08 | 扆亮海 | A kind of pedestrian movement track real time acquiring method under enclosed environment |
-
2020
- 2020-10-23 CN CN202011145668.7A patent/CN112268583B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106768032A (en) * | 2016-12-06 | 2017-05-31 | 水利部交通运输部国家能源局南京水利科学研究院 | A kind of processing method for improving Dam safety automation monitoring data reliability |
| CN106643739A (en) * | 2017-02-23 | 2017-05-10 | 烟台中飞海装科技有限公司 | Indoor environment personnel location method and system |
| CN107990895A (en) * | 2017-11-08 | 2018-05-04 | 北京工商大学 | A kind of building floor gap pedestrian track tracking and system based on wearable IMU |
| CN109974694A (en) * | 2019-03-11 | 2019-07-05 | 东南大学 | One kind is based on the barometrical indoor pedestrian's 3D localization method of UWB/IMU/ |
| CN109827577A (en) * | 2019-03-26 | 2019-05-31 | 电子科技大学 | High-precision inertial navigation location algorithm based on motion state detection |
Non-Patent Citations (1)
| Title |
|---|
| 基于短期数据融合的自主三维导航系统;陈莹超 等;《仪表技术与传感器》;20170115(第1期);第130-133、138页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112268583A (en) | 2021-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107174255B (en) | Three-dimensional gait information acquisition and analysis method based on Kinect somatosensory technology | |
| CN105973143B (en) | A kind of measurement method and device of biped walking walking parameter | |
| CN106643739B (en) | Indoor environment personnel positioning method and system | |
| CN107289941B (en) | Inertial navigation-based indoor positioning method and device | |
| CN104554341B (en) | The system and method for detecting rail smooth degree | |
| EP1770370B1 (en) | Walker behavior detection apparatus | |
| CN106851578B (en) | Personnel positioning system and method in complex unknown indoor environment | |
| US9339214B2 (en) | Body movement detection device | |
| EP1764581A1 (en) | Apparatus and method for detecting step in a personal navigator | |
| JP3775779B2 (en) | Walking navigation device and navigation system using the same | |
| CN103968827A (en) | Wearable human body gait detection self-localization method | |
| US20110153042A1 (en) | Performance metrics | |
| US9255943B2 (en) | Information processing apparatus and information processing method | |
| JP5938760B2 (en) | Travel amount estimation system, travel amount estimation method, mobile terminal | |
| CN108182402A (en) | A kind of steel box-girder method for inspecting for using acquisition robot and deep learning algorithm | |
| KR101674816B1 (en) | Device and method for gait pattern analysis with imu | |
| CN111024075A (en) | Pedestrian navigation error correction filtering method combining Bluetooth beacon and map | |
| JPH10334207A (en) | Human stream measuring instrument | |
| CN112268583B (en) | Method and device for detecting track of pedestrian going up and down stairs | |
| CN109084763B (en) | Wearable three-dimensional indoor positioning device and method based on attitude angle measurement | |
| Faulkner et al. | Altitude accuracy while tracking pedestrians using a boot-mounted IMU | |
| JP2005334083A (en) | Walking equilibrium function test apparatus | |
| CN112268556B (en) | Method and device for detecting state of pedestrian taking escalator | |
| CN112304316B (en) | Method and device for automatically detecting state and track of pedestrian taking elevator | |
| CN104567862B (en) | A kind of movement locus acquisition methods positioned based on bipod |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |