Motion direction detection method and apparatus, electronic device, and storage medium

Abstract

The present disclosure relates to a motion direction detection method and device, electronic equipment and storage medium. The motion direction detection method comprises: acquiring multi-source sensor data collected by a wearable device, and performing fusion processing on the multi-source sensor data to obtain attitude information of the wearable device; wherein the wearable device is worn on a moving object; and the attitude information of key points in the multi-source sensor data is solved by using multiple attitude solving methods to obtain the current forward direction and / or direction change of the moving object. The present disclosure can make the wearable device not be affected by the wearing position, and improve the accuracy of the motion direction estimation result of the moving object in the case that the attitude of the wearable device changes complexly with the moving object.

Description

Technical Field

[0001] This disclosure relates to the field of wearable device technology, and in particular to a motion direction detection method, device, electronic device, and storage medium. Background Technology

[0002] In related technologies, methods for estimating motion direction based on wearable devices are mostly based on wearable devices worn in relatively stable positions, such as the torso or head. However, for wearable devices that may undergo complex posture changes with the movement of an object, it is difficult to accurately obtain the object's motion direction or the amount of change in direction. For example, a wearable device worn on the arm will change posture with the runner's arm movements during running. Analyzing the runner's motion direction based on the wearable device's posture during running is quite difficult. Summary of the Invention

[0003] To overcome the problems existing in related technologies, this disclosure provides a motion direction detection method, device, electronic device, and storage medium.

[0004] According to a first aspect of the present disclosure, a motion direction detection method is provided, comprising:

[0005] The wearable device acquires multi-source sensor data collected by the wearable device and performs fusion processing on the multi-source sensor data to obtain the attitude information of the wearable device; wherein the wearable device is worn on a moving object.

[0006] Multiple attitude calculation methods are used to calculate the attitude information of key points in the multi-source sensor data to obtain the current forward direction and / or the change in direction of the moving object.

[0007] Optionally, in some embodiments of this disclosure, the step of using multiple attitude calculation methods to calculate the attitude information of key points in the multi-source sensor data to obtain the current forward direction and / or change in direction of the moving object includes: in response to detecting that the motion of the moving object is periodic motion based on the multi-source sensor data and the attitude information, performing motion period feature analysis on the multi-source sensor data and the attitude information to obtain motion period feature information; obtaining the attitude information of key points within the current motion period from the attitude information based on the motion period feature information; and using the multiple attitude calculation methods to calculate the attitude information of key points within the current motion period to obtain the current forward direction and / or change in direction of the moving object.

[0008] Optionally, in some embodiments of this disclosure, the step of using multiple attitude calculation methods to calculate the attitude information of key points within the current motion cycle to obtain the current forward direction and / or change in direction of the moving object includes: determining the Euler angle rotation order corresponding to each of the multiple attitude calculation methods; performing attitude calculation on the attitude information of key points within the current motion cycle based on the corresponding Euler angle rotation order to obtain multiple Euler angles of key points within the current motion cycle; and determining the current forward direction and / or change in direction of the moving object based on the multiple Euler angles of key points within the current motion cycle.

[0009] Optionally, in some embodiments of this disclosure, determining the current forward direction and / or change in direction of the moving object based on multiple Euler angles of key points within the current motion cycle includes: obtaining the heading angle of each of the multiple Euler angles; optimizing the heading angles of each of the multiple Euler angles according to a preset algorithm to obtain the target heading angle of the key point within the current motion cycle; and determining the current forward direction and / or change in direction of the moving object based on the target heading angle of the key point within the current motion cycle; wherein the preset algorithm includes at least any one of the following: clustering algorithm, extreme value removal and averaging algorithm, and averaging algorithm.

[0010] Optionally, in some embodiments of this disclosure, determining the current forward direction and / or direction change of the moving object based on the target heading angle of the key point in the current motion cycle includes: obtaining the target heading angle of the key point in the previous motion cycle, and determining the heading angle change of the current motion cycle compared to the previous motion cycle based on the target heading angle of the key point in the current motion cycle and the target heading angle of the key point in the previous motion cycle; determining the current direction change of the moving object based on the heading angle change; and determining the current forward direction of the moving object based on the current direction change of the moving object and the forward direction of the moving object in the previous motion cycle.

[0011] Optionally, in some embodiments of this disclosure, the method further includes: in response to detecting that the motion of the moving object is a non-periodic motion based on the multi-source sensor data and the attitude information, performing attitude change analysis on the multi-source sensor data and the attitude information to obtain attitude information within a target time period; wherein, the target time period is the time period during which the attitude of the wearable device changes; and determining the current forward direction and / or the amount of direction change of the moving object based on the attitude information within the target time period.

[0012] Optionally, in some embodiments of this disclosure, determining the current forward direction of the moving object based on the attitude information within the target time period includes: performing attitude calculation on the attitude information within the target time period using multiple attitude calculation methods to obtain the current forward direction of the moving object.

[0013] Optionally, in some embodiments of this disclosure, the step of using multiple attitude calculation methods to calculate the attitude information of key points in the multi-source sensor data to obtain the current forward direction and / or change in direction of the moving object includes: inputting the multi-source sensor data into a pre-trained motion type switching recognition model to determine whether the moving object is currently undergoing a motion type switch; wherein the motion type switching recognition model has learned the mapping relationship between motion type switching and multi-source sensor data; when the moving object is currently undergoing a motion type switch, using multiple attitude calculation methods to calculate the attitude information of key points in the multi-source sensor data to obtain the current forward direction and / or change in direction of the moving object.

[0014] Optionally, in some embodiments of this disclosure, the motion direction detection method further includes: acquiring the current ambient air pressure value collected by the wearable device; calculating the altitude corresponding to the current ambient air pressure value based on the current ambient air pressure value and the relationship between the air pressure value and altitude; and determining the current forward direction and / or change in direction of the moving object in three-dimensional space based on the current forward direction and / or change in direction and the altitude corresponding to the current ambient air pressure value.

[0015] Optionally, in some embodiments of this disclosure, the motion direction detection method further includes: in response to the moving object being in a specific scene, acquiring the current satellite navigation position information of the moving object; and correcting the satellite navigation position information based on the current forward direction and / or the amount of direction change of the moving object.

[0016] According to a second aspect of the present disclosure, a motion direction detection device is provided, comprising:

[0017] The first acquisition module is used to acquire multi-source sensor data collected by the wearable device, and to perform fusion processing on the multi-source sensor data to obtain the attitude information of the wearable device; wherein the wearable device is worn on a moving object;

[0018] The attitude calculation module is used to calculate the attitude information of key points in the multi-source sensor data using various attitude calculation methods, and to obtain the current forward direction and / or the change in direction of the moving object.

[0019] Optionally, in some embodiments of this disclosure, the attitude calculation module includes a first analysis unit, configured to perform motion cycle feature analysis on the multi-source sensor data and the attitude information in response to detecting that the motion of the moving object is periodic motion based on the multi-source sensor data and the attitude information, and obtain motion cycle feature information; an acquisition unit, configured to acquire the attitude information of key points within the current motion cycle from the attitude information based on the motion cycle feature information; and an attitude calculation unit, configured to perform attitude calculation on the attitude information of key points within the current motion cycle using multiple attitude calculation methods, and obtain the current forward direction and / or change in direction of the moving object.

[0020] Optionally, in some embodiments of this disclosure, the attitude calculation unit is specifically used to: determine the Euler angle rotation order corresponding to each of the multiple attitude calculation methods; perform attitude calculation on the attitude information of key points in the current motion cycle based on the corresponding Euler angle rotation order to obtain multiple Euler angles of key points in the current motion cycle; and determine the current forward direction and / or direction change of the moving object based on the multiple Euler angles of key points in the current motion cycle.

[0021] Optionally, in some embodiments of this disclosure, the attitude calculation unit is further configured to: obtain the heading angle of each of the plurality of Euler angles; optimize the heading angle of each of the plurality of Euler angles according to a preset algorithm to obtain the target heading angle of the key point in the current motion cycle; determine the current forward direction and / or direction change of the moving object based on the target heading angle of the key point in the current motion cycle; wherein the preset algorithm includes at least any one of the following: clustering algorithm, extreme value removal and averaging algorithm, and averaging algorithm.

[0022] Optionally, in some embodiments of this disclosure, the attitude calculation unit is further configured to: obtain the target heading angle of the key point in the previous motion cycle, and determine the change in heading angle of the current motion cycle compared to the previous motion cycle based on the target heading angle of the key point in the current motion cycle and the target heading angle of the key point in the previous motion cycle; determine the current direction change of the moving object based on the change in heading angle; and determine the current forward direction of the moving object based on the current direction change of the moving object and the forward direction of the moving object in the previous motion cycle.

[0023] Optionally, in some embodiments of this disclosure, the device further includes: an analysis module, configured to, in response to detecting that the motion of the moving object is a non-periodic motion based on the multi-source sensor data and the attitude information, perform attitude change analysis on the multi-source sensor data and the attitude information to obtain attitude information within a target time period; wherein the target time period is the time period during which the attitude of the wearable device changes; and a first determination module, configured to, based on the attitude information within the target time period, determine the current forward direction and / or the amount of direction change of the moving object.

[0024] Optionally, in some embodiments of this disclosure, the first determining module is specifically used to: perform attitude calculation on the attitude information within the target time period using multiple attitude calculation methods to obtain the current forward direction of the moving object.

[0025] Optionally, in some embodiments of this disclosure, the attitude calculation module is specifically used to: input the multi-source sensor data into a pre-trained motion type switching recognition model to determine whether the moving object is currently undergoing a motion type switch; wherein, the motion type switching recognition model has learned the mapping relationship between motion type switching and multi-source sensor data; when the moving object is currently undergoing a motion type switch, various attitude calculation methods are used to perform attitude calculation on the attitude information of key points in the multi-source sensor data to obtain the current forward direction and / or direction change of the moving object.

[0026] Optionally, in some embodiments of this disclosure, the device further includes: a second acquisition module, configured to acquire the current ambient air pressure value collected by the wearable device; a calculation module, configured to calculate the altitude corresponding to the current ambient air pressure value based on the current ambient air pressure value and the relationship between air pressure value and altitude; and a second determination module, configured to determine the current forward direction and / or change in direction of the moving object in three-dimensional space based on the current forward direction and / or change in direction and the altitude corresponding to the current ambient air pressure value.

[0027] Optionally, in some embodiments of this disclosure, the device further includes: a navigation assistance module, configured to, in response to the moving object being in a specific scene, acquire the current satellite navigation position information of the moving object, and correct the satellite navigation position information based on the current forward direction and / or the change in direction of the moving object.

[0028] According to a third aspect of the present disclosure, a wearable device is provided, comprising:

[0029] At least one processor; and

[0030] A memory communicatively connected to the at least one processor; wherein,

[0031] The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the motion direction detection method described in the first aspect above.

[0032] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium is provided that stores computer instructions for causing the computer to perform the motion direction detection method described in the first aspect above.

[0033] The technical solutions provided by the embodiments of this disclosure can include the following beneficial effects: Multiple attitude calculation methods are used to calculate the attitude information of key points within the current motion cycle of the wearable device, thereby obtaining the current forward direction and / or change in direction of the moving object. The motion direction detection method of this disclosure allows the wearable device to be unaffected by its wearing position, improving the accuracy of motion direction estimation results when the attitude of the wearable device undergoes complex changes with the moving object.

[0034] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0035] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0036] Figure 1 This is a flowchart illustrating a motion direction detection method according to an exemplary embodiment.

[0037] Figure 2 This is a flowchart illustrating a motion direction detection method according to an exemplary embodiment.

[0038] Figure 3 This is a schematic diagram illustrating an embodiment of the present disclosure of obtaining key point attitude information within the current motion cycle.

[0039] Figure 4 This is a flowchart illustrating a motion direction detection method according to an exemplary embodiment.

[0040] Figure 5 This is a schematic diagram illustrating the current forward direction and the amount of change in direction of a moving object according to an embodiment of this disclosure.

[0041] Figure 6 This is a flowchart illustrating a motion direction detection method according to an exemplary embodiment.

[0042] Figure 7 This is a flowchart illustrating a motion direction detection method according to an exemplary embodiment.

[0043] Figure 8 This is a schematic diagram of a target time period for a non-periodic motion of a moving object, as shown in an embodiment of this disclosure.

[0044] Figure 9 This is a schematic diagram of a motion direction detection device according to an exemplary embodiment.

[0045] Figure 10 This is a schematic diagram of a motion direction detection device according to an exemplary embodiment.

[0046] Figure 11 This is a schematic diagram of a motion direction detection device according to an exemplary embodiment.

[0047] Figure 12 This is a block diagram illustrating a wearable device according to an exemplary embodiment. Detailed Implementation

[0048] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0049] This disclosure provides a motion direction detection method, apparatus, electronic device, and storage medium, which can improve the accuracy of motion direction estimation results for moving objects when the posture of wearable devices undergoes complex changes with the moving object. Figure 1 This is a flowchart illustrating a motion direction detection method according to an exemplary embodiment, such as... Figure 1 As shown, this motion direction detection method is used in wearable devices and includes the following steps.

[0050] In step 101, multi-source sensor data collected by the wearable device is acquired, and the multi-source sensor data is fused to obtain the attitude information of the wearable device; wherein, the wearable device is worn on a moving object.

[0051] Optionally, in some embodiments of this disclosure, the multi-source sensor data may include at least two of accelerometer data, gyroscope data, and geomagnetic sensor data. For example, the multi-source sensor data may include accelerometer data, and also include at least one of gyroscope data and geomagnetic sensor data. Furthermore, the higher the accuracy of the multi-source sensors, the higher the accuracy of motion direction recognition, and the more accurately the motion direction of the moving object can be detected even if the motion direction of the moving object changes slowly and uniformly.

[0052] It should be noted that the posture information of wearable devices can be represented using quaternions.

[0053] To improve the accuracy of posture information of wearable devices, in the embodiments of this disclosure, filtering and noise reduction algorithms can be used to process multi-source sensor data collected by the wearable device. The processed multi-source sensor data can then be fused to eliminate noise and reduce the impact of signal noise. As an example, filtering methods may include, but are not limited to, moving average window filtering, exponential weighted averaging, and median filtering.

[0054] In step 102, various attitude calculation methods are used to calculate the attitude information of key points in the multi-source sensor data to obtain the current forward direction and / or change in direction of the moving object.

[0055] It should be noted that the Euler angle rotation order corresponding to different attitude calculation methods is different. Based on the Euler angle rotation order corresponding to each of the various attitude calculation methods, attitude calculation can be performed on the attitude information of key points in the current motion cycle to obtain multiple Euler angles of key points in the current motion cycle, thereby determining the current forward direction and / or change in direction of the moving object.

[0056] To identify the current direction of movement of an object in three-dimensional space during activities such as mountain climbing, diving, and rock climbing, in one implementation, the motion direction detection method proposed in this disclosure can also acquire the current ambient air pressure value collected by a wearable device. Based on the current ambient air pressure value and the relationship between air pressure value and altitude, the altitude corresponding to the current ambient air pressure value is calculated. Based on the current direction of movement and / or change in direction of the moving object, and the altitude corresponding to the current ambient air pressure value, the current direction of movement and / or change in direction of the moving object in three-dimensional space is determined.

[0057] It should also be noted that the current direction of movement of a moving object can be either a relative direction or an absolute direction. If the direction of movement is absolute, the absolute direction of the moving object within the current motion cycle needs to be determined based on the absolute direction of the previous motion cycle and the change in direction of the current motion cycle compared to the previous motion cycle. Specifically, the initial absolute direction of the moving object needs to be obtained at the beginning of the first motion cycle (e.g., by obtaining the initial absolute direction of the moving object through the Global Positioning System (GPS)). Based on the initial absolute direction of the moving object within the first motion cycle and the change in direction within adjacent motion cycles, the current absolute direction of the moving object can be determined.

[0058] According to the motion direction detection method of this disclosure, multiple attitude calculation methods are used to calculate the attitude information of key points in the current motion cycle of a wearable device, thereby obtaining the current forward direction and / or the change in direction of the moving object. The motion direction detection method of this disclosure allows the wearable device to be unaffected by its wearing position, and improves the accuracy of motion direction estimation results when the attitude of the wearable device changes complexly with the moving object.

[0059] Figure 2 This is a flowchart illustrating a motion direction detection method according to an exemplary embodiment, such as... Figure 2 As shown, the motion direction detection method includes the following steps.

[0060] In step 201, multi-source sensor data collected by the wearable device is acquired, and the multi-source sensor data is fused to obtain the attitude information of the wearable device; wherein, the wearable device is worn on a moving object.

[0061] In step 202, in response to the detection that the motion of the moving object is periodic based on the multi-source sensor data and attitude information, motion periodic feature analysis is performed on the multi-source sensor data and attitude information to obtain motion periodic feature information.

[0062] It should be noted that the motion of a moving object, such as walking, running, or swimming, can be determined based on multi-source sensor data and attitude information. When the motion of the moving object is periodic, motion period feature analysis is performed on the multi-source sensor data and attitude information to obtain motion period feature information. As an example, motion period feature information may include features within a motion cycle, the range of attitude changes, and key postures during attitude transitions.

[0063] In step 203, the attitude information of key points within the current motion cycle is obtained from the attitude information based on the motion cycle feature information.

[0064] Key points can be crucial moments in the object's motion. For objects undergoing periodic motion, when selecting key points within the current motion cycle, moments in two consecutive cycles where the posture is the same should be chosen. For example, in running, the forward arm swing posture within each running cycle would be selected as the key point. As an example... Figure 3 This is a schematic diagram illustrating an embodiment of the present disclosure of obtaining key point attitude information within the current motion cycle. For example... Figure 3 As shown, 301 and 302 are two motion cycles, and point A in motion cycle 301 and point A' in motion cycle 302 are the moments when the postures are the same in the two motion cycles.

[0065] To enhance anti-interference capabilities and improve the accuracy of estimating the current direction of movement and / or change in direction of a moving object, multiple key points can be used within the current motion cycle. This means that the attitude information of each of these key points can be obtained from the attitude information of the wearable device based on the motion cycle feature information. For example, ... Figure 3 In the illustrated embodiment, key points A, B, and C can be selected within motion cycle 301. By comprehensively estimating the orientation of the moving object based on the pose information of multiple key points, the accuracy of the orientation estimation result can be improved.

[0066] In step 204, various attitude calculation methods are used to calculate the attitude information of key points within the current motion cycle to obtain the current forward direction and / or change in direction of the moving object.

[0067] It should also be noted that the current direction of movement of a moving object can be either a relative direction or an absolute direction. If the direction of movement is absolute, the absolute direction of the moving object within the current motion cycle needs to be determined based on the absolute direction of the previous motion cycle and the change in direction of the current motion cycle compared to the previous motion cycle. Specifically, the initial absolute direction of the moving object needs to be obtained at the beginning of the first motion cycle (e.g., by obtaining the initial absolute direction of the moving object through the Global Positioning System (GPS)). Based on the initial absolute direction of the moving object within the first motion cycle and the change in direction within adjacent motion cycles, the current absolute direction of the moving object can be determined.

[0068] To accurately detect the direction of motion even when a moving object is switching motion types (e.g., from running to cycling), in one implementation, the motion direction detection method proposed in this disclosure can further input the acquired multi-source sensor data into a pre-trained motion type switching recognition model to determine whether the moving object is currently switching motion types. When the moving object is currently switching motion types, multiple attitude calculation methods are used to calculate the attitude information of key points in the multi-source sensor data to obtain the current forward direction and / or the change in direction of the moving object. For example, using multi-source sensor data and the motion type switching recognition model, it is determined that the moving object is currently switching from running to cycling. At this time, multiple attitude calculation methods can be used to calculate the attitude information of key points in the multi-source sensor data. For example, if it is determined that the attitude characteristics of the key points have not changed, such as when the moving object switches from running to cycling and the heading angle has not changed, it can be determined that the moving object has not changed its direction.

[0069] It should be noted that, in the embodiments of this disclosure, the motion type switching recognition model has learned the mapping relationship between motion type switching and multi-source sensor data. For example, in a scenario where motion type switching occurs, multi-source sensor data of the wearable device worn by the moving object sample is acquired. This multi-source sensor data is used to train a preset neural network model, and the trained neural network model is determined as the motion type switching recognition model, so that the motion type switching recognition model learns the mapping relationship between motion type switching and multi-source sensor data.

[0070] In some embodiments of this disclosure, the current forward direction and / or change in direction of a moving object obtained by the motion direction detection method proposed in this disclosure can also be used to correct satellite navigation position information in environments with weak satellite navigation position signals. As an example, when a moving object is in a specific scenario, such as a desert or tunnel where satellite navigation signals are weak, the current satellite navigation position information of the moving object can be obtained, and based on the current forward direction and / or change in direction of the moving object, the satellite navigation position information can be corrected to assist satellite navigation, thereby improving the accuracy of the satellite navigation position information.

[0071] According to the motion direction detection method of this disclosure, when the motion of the moving object is periodic, motion cycle feature analysis is performed on multi-source sensor data and attitude information to obtain motion cycle feature information, and the attitude information of key points within the current motion cycle is obtained from the attitude information. Multiple attitude calculation methods are used to calculate the attitude information of key points within the current motion cycle of the wearable device to obtain the current forward direction and / or direction change of the moving object. The motion direction detection method of this disclosure allows the wearable device to be unaffected by its wearing position, and further improves the accuracy of motion direction estimation results when the attitude of the wearable device changes complexly with the moving object.

[0072] Figure 4 This is a flowchart illustrating a motion direction detection method according to an exemplary embodiment, such as... Figure 4 As shown, the motion direction detection method includes the following steps.

[0073] In step 401, multi-source sensor data collected by the wearable device is acquired, and the multi-source sensor data is fused to obtain the attitude information of the wearable device; wherein, the wearable device is worn on a moving object.

[0074] In step 402, in response to the detection that the motion of the moving object is periodic based on the multi-source sensor data and attitude information, motion periodic feature analysis is performed on the multi-source sensor data and attitude information to obtain motion periodic feature information.

[0075] In step 403, the attitude information of key points within the current motion cycle is obtained from the attitude information based on the motion cycle feature information.

[0076] The key point could be the moment when multi-source sensor data undergoes a sudden change, for example... Figure 3 In the illustrated embodiment, points B and C represent the moments when the multi-source sensor data reaches its extreme value within period 301. Alternatively, the key point could be the moment of reaching zero, allowing us to determine which part of the current motion cycle the posture corresponds to based on the zero-crossing moment. Based on the posture information of the key points, the current motion type of the moving object is determined. Taking an accelerometer as an example, accelerometer data is obtained, and the posture information of the key points within this data is used to determine the current acceleration of the moving object. Based on this acceleration, the current motion type of the moving object is determined, such as whether the object is currently running or walking.

[0077] In step 404, the Euler angle rotation order corresponding to each of the various attitude calculation methods is determined.

[0078] In step 405, based on their respective Euler angle rotation order, the attitude information of the key points in the current motion cycle is calculated to obtain multiple Euler angles of the key points in the current motion cycle.

[0079] In step 406, the current forward direction and / or change in direction of the moving object are determined based on multiple Euler angles of key points within the current motion cycle.

[0080] In one implementation, the heading angles of multiple Euler angles can be obtained; these heading angles are then optimized using a preset algorithm to obtain the target heading angle of a key point within the current motion cycle; based on the target heading angle of the key point within the current motion cycle, the current forward direction and / or change in direction of the moving object are determined. As an example, Figure 5 This is a schematic diagram illustrating the current forward direction and the amount of change in direction of a moving object according to an embodiment of this disclosure. Figure 5 It can be seen that the direction of the moving object has changed, which could be a scenario where the object turns around while swimming.

[0081] It should be noted that, in the embodiments of this disclosure, steps 401-403 can be implemented in any of the ways described in the embodiments of this disclosure. This disclosure does not limit this and will not elaborate further.

[0082] According to the motion direction detection method of this disclosure, when the motion of the moving object is periodic, multiple attitude calculation methods are used to calculate the attitude information of key points within the current motion cycle of the wearable device, obtaining multiple Euler angles of the key points within the current motion cycle, thereby more accurately determining the current forward direction and / or change in direction of the moving object. The motion direction detection method of this disclosure allows the wearable device to be unaffected by its wearing position, and further improves the accuracy of motion direction estimation results when the attitude of the wearable device changes complexly with the moving object.

[0083] Figure 6 This is a flowchart illustrating a motion direction detection method according to an exemplary embodiment, such as... Figure 6 As shown, the motion direction detection method includes the following steps.

[0084] In step 601, multi-source sensor data collected by the wearable device is acquired, and the multi-source sensor data is fused to obtain the attitude information of the wearable device; wherein, the wearable device is worn on a moving object.

[0085] In step 602, in response to the detection that the motion of the moving object is periodic based on the multi-source sensor data and attitude information, motion periodic feature analysis is performed on the multi-source sensor data and attitude information to obtain motion periodic feature information.

[0086] In step 603, the attitude information of key points within the current motion cycle is obtained from the attitude information based on the motion cycle feature information.

[0087] In step 604, the Euler angle rotation order corresponding to each of the various attitude calculation methods is determined.

[0088] In step 605, based on their respective Euler angle rotation order, the attitude information of the key points in the current motion cycle is calculated to obtain multiple Euler angles of the key points in the current motion cycle.

[0089] In step 606, the heading angle of each of the multiple Euler angles is obtained.

[0090] In step 607, the heading angles of each of the multiple Euler angles are optimized according to a preset algorithm to obtain the target heading angles of the key points in the current motion cycle.

[0091] It should be noted that the preset algorithm includes at least one of the following: clustering algorithm, extreme value removal and averaging algorithm, and averaging algorithm. As an example, let's take... Figure 3 Taking the illustrated embodiment as an example, assuming the current motion cycle is motion cycle 302, three key points are selected within the current motion cycle 302, namely key point A', key point B', and key point C'. Each of key points A', B', and C' corresponds to multiple heading angles. Based on the multiple heading angles corresponding to each of the three key points, a clustering algorithm is used to obtain the target heading angles corresponding to key points A', B', and C' within the current motion cycle 302.

[0092] In step 608, the current forward direction and / or change in direction of the moving object are determined based on the target heading angle of the key point within the current motion cycle.

[0093] In one implementation, the target heading angle of a key point in the previous motion cycle can be obtained. Based on the target heading angles of the key points in the current motion cycle and the target heading angles of the key points in the previous motion cycle, the change in heading angle between the current and previous motion cycles is determined. The change in direction of the moving object is then determined based on this change in heading angle. Finally, based on the change in direction of the moving object and its forward direction in the previous motion cycle, the current forward direction of the moving object is further determined.

[0094] As an example, with Figure 3Taking the illustrated embodiment as an example, assuming the current motion cycle is motion cycle 302, the target heading angles corresponding to key points A', B', and C' within the current motion cycle 302 are compared with the target heading angles corresponding to key points A, B, and C within the previous motion cycle 301. This allows us to determine the change in heading angle between the current motion cycle and the previous cycle, and thus determine the change in the current direction of the moving object.

[0095] It should be noted that, in the embodiments of this disclosure, steps 601-605 can be implemented in any of the ways described in the various embodiments of this disclosure. This disclosure does not limit this and will not elaborate further.

[0096] According to the motion direction detection method of this disclosure, when the motion of the moving object is periodic, multiple attitude calculation methods are used to calculate the attitude information of key points within the current motion cycle of the wearable device, obtaining multiple Euler angles and their corresponding heading angles for the key points within the current motion cycle. The heading angles of each Euler angle are optimized to obtain the target heading angle of the key point within the current motion cycle, thereby more accurately determining the current forward direction and / or change in direction of the moving object. The motion direction detection method of this disclosure allows the wearable device to be unaffected by its wearing position, and further improves the accuracy of motion direction estimation results when the attitude of the wearable device changes complexly with the moving object.

[0097] Figure 7 This is a flowchart illustrating a motion direction detection method according to an exemplary embodiment, such as... Figure 7 As shown, the motion direction detection method includes the following steps.

[0098] In step 701, multi-source sensor data collected by the wearable device is acquired, and the multi-source sensor data is fused to obtain the attitude information of the wearable device; wherein, the wearable device is worn on a moving object.

[0099] In step 702, it is determined whether the motion of the moving object detected based on multi-source sensor data and attitude information is periodic motion. If the motion of the moving object is detected as periodic motion based on multi-source sensor data and attitude information, step 703 is executed; if the motion of the moving object is detected as non-periodic motion based on multi-source sensor data and attitude information, step 706 is executed.

[0100] In step 703, motion cycle feature analysis is performed on the multi-source sensor data and attitude information to obtain motion cycle feature information.

[0101] In step 704, the attitude information of key points within the current motion cycle is obtained from the attitude information based on the motion cycle feature information.

[0102] In step 705, various attitude calculation methods are used to calculate the attitude information of key points within the current motion cycle to obtain the current forward direction and / or change in direction of the moving object.

[0103] In step 706, attitude change analysis is performed on the multi-source sensor data and attitude information to obtain attitude information within the target time period; wherein, the target time period is the time period during which the attitude of the wearable device changes.

[0104] As an example, Figure 8 This is a schematic diagram illustrating a target time period for a non-periodic motion of a moving object, as shown in an embodiment of this disclosure. It can be seen that the posture of the wearable device changes during time periods 801 and 802; therefore, time periods 801 and 802 are considered as the target time periods.

[0105] In step 707, the current forward direction and / or change in direction of the moving object are determined based on the attitude information within the target time period.

[0106] In one implementation, multiple attitude calculation methods can be used to calculate the attitude information within the target time period to obtain the current forward direction of the moving object.

[0107] It should be noted that the current direction of movement of a moving object can be either a relative direction or an absolute direction. If the direction of movement is absolute, the absolute direction of the moving object within the current motion cycle needs to be determined based on the absolute direction of the previous motion cycle and the change in direction of the current motion cycle compared to the previous motion cycle. Specifically, the initial absolute direction of the moving object needs to be obtained at the beginning of the first motion cycle (e.g., by obtaining the initial absolute direction of the moving object through the Global Positioning System (GPS)). Based on the initial absolute direction of the moving object within the first motion cycle and the change in direction within adjacent motion cycles, the current absolute direction of the moving object can be determined.

[0108] It should be noted that, in the embodiments of this disclosure, steps 701-705 can be implemented in any of the ways described in the various embodiments of this disclosure. This disclosure does not limit this and will not elaborate further.

[0109] According to the motion direction detection method of this disclosure, when the motion of the moving object is periodic, multiple attitude calculation methods are used to calculate the attitude information of key points within the current motion cycle of the wearable device to obtain the current forward direction and / or the change in direction of the moving object. When the motion of the moving object is non-periodic, the attitude information within the time period during which the attitude of the wearable device changes is obtained, thereby determining the current forward direction and / or the change in direction of the moving object. The motion direction detection method of this disclosure allows the wearable device to be unaffected by its wearing position, and further improves the accuracy of the motion direction estimation results when the attitude of the wearable device changes complexly with the moving object.

[0110] Figure 9 This is a schematic diagram illustrating the structure of a motion direction detection device according to an exemplary embodiment. Figure 9 As shown, the motion direction detection device includes a first acquisition module 901 and an attitude calculation module 902.

[0111] Specifically, the first acquisition module 901 is used to acquire multi-source sensor data collected by the wearable device and perform fusion processing on the multi-source sensor data to obtain the attitude information of the wearable device; wherein, the wearable device is worn on a moving object.

[0112] The attitude calculation module 902 is used to calculate the attitude information of key points in multi-source sensor data using various attitude calculation methods to obtain the current forward direction and / or change of direction of the moving object.

[0113] In some embodiments of this disclosure, the attitude calculation module 902 includes: a first analysis unit 903, an acquisition unit 904, and an attitude calculation unit 905. The first analysis unit 903 is used to perform motion cycle feature analysis on the multi-source sensor data and attitude information in response to detecting that the motion of a moving object is periodic motion based on multi-source sensor data and attitude information, thereby obtaining motion cycle feature information. The acquisition unit 904 is used to obtain the attitude information of key points within the current motion cycle from the attitude information based on the motion cycle feature information. The attitude calculation unit 905 is used to perform attitude calculation on the attitude information of key points within the current motion cycle using various attitude calculation methods to obtain the current forward direction and / or change in direction of the moving object.

[0114] In some embodiments of this disclosure, the attitude calculation unit 905 is specifically used to: determine the Euler angle rotation order corresponding to each of the multiple attitude calculation methods; perform attitude calculation on the attitude information of key points in the current motion cycle based on the corresponding Euler angle rotation order, and obtain multiple Euler angles of key points in the current motion cycle; and determine the current forward direction and / or direction change of the moving object based on the multiple Euler angles of key points in the current motion cycle.

[0115] In some embodiments of this disclosure, the attitude calculation unit 905 is further configured to: obtain the heading angle of each of the multiple Euler angles; optimize the heading angle of each of the multiple Euler angles according to a preset algorithm to obtain the target heading angle of the key point in the current motion cycle; determine the current forward direction and / or direction change of the moving object based on the target heading angle of the key point in the current motion cycle; wherein the preset algorithm includes at least any one of the following: clustering algorithm, extreme value removal and averaging algorithm, averaging algorithm.

[0116] In some embodiments of this disclosure, the attitude calculation unit 905 is further configured to: obtain the target heading angle of the key point in the previous motion cycle, and determine the change in heading angle of the current motion cycle compared to the previous motion cycle based on the target heading angle of the key point in the current motion cycle and the target heading angle of the key point in the previous motion cycle; determine the current change in direction of the moving object based on the change in heading angle; and determine the current forward direction of the moving object based on the current change in direction of the moving object and the forward direction of the moving object in the previous motion cycle.

[0117] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments of the motion direction detection method, and will not be elaborated here.

[0118] According to the motion direction detection device of this disclosure, when the motion of the moving object is periodic, multiple attitude calculation methods are used to calculate the attitude information of key points within the current motion cycle of the wearable device, thereby obtaining the current forward direction and / or the change in direction of the moving object. The motion direction detection method of this disclosure allows the wearable device to be unaffected by its wearing position, and improves the accuracy of the motion direction estimation results when the attitude of the wearable device changes complexly with the moving object.

[0119] Figure 10 This is a schematic diagram illustrating the structure of a motion direction detection device according to an exemplary embodiment. Figure 10 As shown, the motion direction detection device may further include an analysis module 1006 and a first determination module 1007.

[0120] Specifically, the analysis module 1006 is used to respond to the detection that the motion of the moving object is non-periodic based on multi-source sensor data and attitude information, and to perform attitude change analysis on the multi-source sensor data and attitude information to obtain attitude information within a target time period; wherein, the target time period is the time period during which the attitude of the wearable device changes.

[0121] The first determining module 1007 is used to determine the current forward direction and / or change in direction of the moving object based on the attitude information within the target time period.

[0122] In some embodiments of this disclosure, the first determining module 1007 is specifically used to: perform attitude calculation on the attitude information within the target time period using multiple attitude calculation methods to obtain the current forward direction of the moving object.

[0123] In some embodiments of this disclosure, the attitude calculation module 1002 is specifically used to: input multi-source sensor data into a pre-trained motion type switching recognition model to determine whether the moving object is currently undergoing a motion type switch; wherein, the motion type switching recognition model has learned the mapping relationship between the motion type switch and the multi-source sensor data; when the moving object is currently undergoing a motion type switch, various attitude calculation methods are used to perform attitude calculation on the attitude information of key points in the multi-source sensor data to obtain the current forward direction and / or the change in direction of the moving object.

[0124] in, Figure 10 Middle 1001-1005 and Figure 9 The Chinese 901-905 have the same function and structure.

[0125] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments of the motion direction detection method, and will not be elaborated here.

[0126] According to the motion direction detection device of this disclosure, when the motion of the moving object is periodic, multiple attitude calculation methods are used to calculate the attitude information of key points within the current motion cycle of the wearable device to obtain the current forward direction and / or the change in direction of the moving object. When the motion of the moving object is non-periodic, the attitude information within the time period during which the attitude of the wearable device changes is obtained, thereby determining the current forward direction and / or the change in direction of the moving object. The motion direction detection method of this disclosure allows the wearable device to be unaffected by its wearing position, and further improves the accuracy of the motion direction estimation results when the attitude of the wearable device changes complexly with the moving object.

[0127] Figure 11This is a schematic diagram illustrating the structure of a motion direction detection device according to an exemplary embodiment. Figure 11 As shown, the motion direction detection device may further include: a second acquisition module 1108, a calculation module 1109, a second determination module 1110, and a navigation assistance module 1111.

[0128] The second acquisition module 1108 is used to acquire the current ambient air pressure value collected by the wearable device.

[0129] The calculation module 1109 is used to calculate the altitude corresponding to the current ambient air pressure value based on the current ambient air pressure value and the relationship between air pressure value and altitude.

[0130] The second determining module 1110 is used to determine the current forward direction and / or change in direction of a moving object in three-dimensional space based on the current forward direction and / or change in direction, and the altitude corresponding to the current ambient air pressure value.

[0131] The navigation assistance module 1111 is used to obtain the current satellite navigation position information of the moving object in response to the moving object being in a specific scene, and to correct the satellite navigation position information based on the moving object's current forward direction and / or the amount of change in direction.

[0132] in, Figure 11 1101-1107 and Figure 10 The 1001-1007 series have the same function and structure.

[0133] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments of the motion direction detection method, and will not be elaborated here.

[0134] According to the motion direction detection device of this disclosure, when the motion of the moving object is periodic, it employs multiple attitude calculation methods to calculate the attitude information of key points within the current motion cycle of the wearable device, thereby obtaining the current forward direction and / or change in direction of the moving object. When the motion of the moving object is non-periodic, it acquires the attitude information within the time period during which the attitude of the wearable device changes, thereby determining the current forward direction and / or change in direction of the moving object. Furthermore, based on the current forward direction and / or change in direction of the moving object, the satellite navigation position information can be corrected, thereby improving the accuracy of the satellite navigation position information. In addition, by combining the altitude corresponding to the current ambient air pressure value detected by the wearable device, the current forward direction and / or change in direction of the moving object in three-dimensional space can be determined. The motion direction detection method of this disclosure allows the wearable device to be unaffected by its wearing position, further improving the accuracy of the motion direction estimation results when the attitude of the wearable device undergoes complex changes with the moving object.

[0135] Figure 12 This is a block diagram illustrating a wearable device 1200 according to an exemplary embodiment. (Refer to...) Figure 12 The wearable device 1200 includes one or more of the following components: a processing component 1202, a memory 1204, a power supply component 1206, a multimedia component 1208, an audio component 1210, an input / output (I / O) interface 1212, a sensor component 1214, and a communication component 1216.

[0136] Processing component 1202 typically controls the overall operation of wearable device 1200, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 1202 may include one or more processors 1220 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 1202 may include one or more modules to facilitate interaction between processing component 1202 and other components. For example, processing component 1202 may include a multimedia module to facilitate interaction between multimedia component 1208 and processing component 1202.

[0137] Memory 1204 is configured to store various types of data to support the operation of wearable device 1200. Examples of this data include instructions for any application or method operating on wearable device 1200, contact data, phonebook data, messages, pictures, videos, etc. Memory 1204 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0138] The power component 1206 provides power to various components of the wearable device 1200. The power component 1206 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to the wearable device 1200.

[0139] The multimedia component 1208 includes a screen that provides an output interface between the wearable device 1200 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, the multimedia component 1208 includes a front-facing camera and / or a rear-facing camera. When the device 1200 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0140] Audio component 1210 is configured to output and / or input audio signals. For example, audio component 1210 includes a microphone (MIC) configured to receive external audio signals when wearable device 1200 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 1204 or transmitted via communication component 1216. In some embodiments, audio component 1210 also includes a speaker for outputting audio signals.

[0141] I / O interface 1212 provides an interface between processing component 1202 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0142] Sensor assembly 1214 includes one or more sensors for providing status assessments of various aspects of wearable device 1200. For example, sensor assembly 1214 may detect the on / off state of device 1200, the relative positioning of components such as the display and keypad of wearable device 1200, changes in position of wearable device 1200 or a component of wearable device 1200, the presence or absence of user contact with wearable device 1200, orientation or acceleration / deceleration of wearable device 1200, and temperature changes of wearable device 1200. Sensor assembly 1214 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 1214 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 1214 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0143] Communication component 1216 is configured to facilitate wired or wireless communication between wearable device 1200 and other devices. Wearable device 1200 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 1216 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 1216 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0144] In an exemplary embodiment, the wearable device 1200 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0145] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1204 including instructions, which can be executed by a processor 1220 of the wearable device 1200 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0146] In an exemplary embodiment, a computer program product is also provided, including a computer program that is executed by the processor 1220 of the wearable device 1200 to perform the above-described method.

[0147] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0148] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0149] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for detecting motion direction, characterized in that, include: The wearable device acquires multi-source sensor data collected by the wearable device and performs fusion processing on the multi-source sensor data to obtain the attitude information of the wearable device; wherein the wearable device is worn on a moving object. The attitude calculation of key points in the multi-source sensor data is performed using multiple attitude calculation methods to obtain the current forward direction and / or change in direction of the moving object, including: In response to detecting that the motion of the moving object is periodic motion based on the multi-source sensor data and the attitude information, motion periodic feature analysis is performed on the multi-source sensor data and the attitude information to obtain motion periodic feature information; Based on the motion cycle feature information, the posture information of key points within the current motion cycle is obtained from the posture information; Determine the Euler angle rotation order corresponding to each of the various attitude calculation methods; Based on the corresponding Euler angle rotation order, the attitude information of the key points in the current motion cycle is calculated to obtain multiple Euler angles of the key points in the current motion cycle. Obtain the heading angle of each of the plurality of Euler angles; The heading angles of each of the multiple Euler angles are optimized according to a preset algorithm to obtain the target heading angles of the key points in the current motion cycle. Based on the target heading angle of the key point within the current motion cycle, determine the current forward direction and / or change in direction of the moving object.

2. The method as described in claim 1, characterized in that, The preset algorithm includes: Clustering algorithm or averaging algorithm.

3. The method as described in claim 1, characterized in that, Determining the current direction of travel and / or change of direction of the moving object based on the target heading angle of the key points within the current motion cycle includes: Obtain the target heading angle of the key point in the previous motion cycle, and determine the change in heading angle of the current motion cycle compared to the previous motion cycle based on the target heading angle of the key point in the current motion cycle and the target heading angle of the key point in the previous motion cycle. Then determine the change in the current direction of the moving object based on the change in heading angle. The current direction of motion of the moving object is determined based on the current change in direction of the moving object and the direction of motion of the moving object in the previous motion cycle.

4. The method as described in claim 1, characterized in that, Also includes: In response to detecting that the motion of the moving object is non-periodic based on the multi-source sensor data and the attitude information, attitude change analysis is performed on the multi-source sensor data and the attitude information to obtain attitude information within a target time period; wherein, the target time period is the time period during which the attitude of the wearable device changes; Based on the posture information within the target time period, determine the current forward direction and / or the amount of change in direction of the moving object.

5. The method as described in claim 4, characterized in that, Determining the current direction of motion of the moving object based on the posture information within the target time period includes: Multiple attitude calculation methods are used to calculate the attitude information within the target time period to obtain the current forward direction of the moving object.

6. The method as described in claim 1, characterized in that, The process of using multiple attitude calculation methods to calculate the attitude information of key points in the multi-source sensor data to obtain the current forward direction and / or change in direction of the moving object includes: The multi-source sensor data is input into a pre-trained motion type switching recognition model to determine whether the moving object is currently switching motion types; wherein, the motion type switching recognition model has learned the mapping relationship between motion type switching and multi-source sensor data; When the moving object changes its motion type, multiple attitude calculation methods are used to calculate the attitude information of key points in the multi-source sensor data to obtain the current forward direction and / or the change in direction of the moving object.

7. The method as described in claim 1, characterized in that, Also includes: Obtain the current ambient air pressure value collected by the wearable device; Based on the current ambient air pressure value and the relationship between air pressure value and altitude, calculate the altitude corresponding to the current ambient air pressure value; Based on the current direction of travel and / or the change in direction, and the altitude corresponding to the current ambient air pressure value, determine the current direction of travel and / or the change in direction of the moving object in three-dimensional space.

8. The method as described in claim 1, characterized in that, Also includes: In response to the moving object being in a specific scene, the current satellite navigation position information of the moving object is obtained; The satellite navigation position information is corrected based on the current direction of movement and / or the amount of change in direction of the moving object.

9. A motion direction detection device, characterized in that, include: The first acquisition module is used to acquire multi-source sensor data collected by the wearable device, and to perform fusion processing on the multi-source sensor data to obtain the attitude information of the wearable device; wherein the wearable device is worn on a moving object; The attitude calculation module is used to perform attitude calculation on the attitude information of key points in the multi-source sensor data using multiple attitude calculation methods, and to obtain the current forward direction and / or the change in direction of the moving object. The attitude calculation module includes: The first analysis unit is configured to, in response to detecting that the motion of the moving object is periodic motion based on the multi-source sensor data and the attitude information, perform motion periodic feature analysis on the multi-source sensor data and the attitude information to obtain motion periodic feature information. The acquisition unit is used to acquire the posture information of key points within the current motion cycle from the posture information based on the motion cycle feature information. An attitude calculation unit is used to determine the Euler angle rotation order corresponding to each of the various attitude calculation methods. Based on the corresponding Euler angle rotation order, the attitude information of the key points in the current motion cycle is calculated to obtain multiple Euler angles of the key points in the current motion cycle. Obtain the heading angle of each of the plurality of Euler angles; The heading angles of each of the multiple Euler angles are optimized according to a preset algorithm to obtain the target heading angles of the key points in the current motion cycle. Based on the target heading angle of the key point within the current motion cycle, determine the current forward direction and / or change in direction of the moving object.

10. The apparatus as claimed in claim 9, characterized in that, The preset algorithm includes: Clustering algorithm or averaging algorithm.

11. The apparatus as claimed in claim 9, characterized in that, The attitude calculation unit is also used for: Obtain the target heading angle of the key point in the previous motion cycle, and determine the change in heading angle of the current motion cycle compared to the previous motion cycle based on the target heading angle of the key point in the current motion cycle and the target heading angle of the key point in the previous motion cycle. Then determine the change in the current direction of the moving object based on the change in heading angle. The current direction of motion of the moving object is determined based on the current change in direction of the moving object and the direction of motion of the moving object in the previous motion cycle.

12. The apparatus as claimed in claim 9, characterized in that, The device further includes: An analysis module is configured to, in response to detecting that the motion of the moving object is a non-periodic motion based on the multi-source sensor data and the attitude information, perform attitude change analysis on the multi-source sensor data and the attitude information to obtain attitude information within a target time period; wherein, the target time period is the time period during which the attitude of the wearable device changes; The first determining module is used to determine the current forward direction and / or the change in direction of the moving object based on the posture information within the target time period.

13. The apparatus as claimed in claim 12, characterized in that, The first determining module is specifically used for: Multiple attitude calculation methods are used to calculate the attitude information within the target time period to obtain the current forward direction of the moving object.

14. The apparatus as claimed in claim 9, characterized in that, The attitude calculation module is specifically used for: The multi-source sensor data is input into a pre-trained motion type switching recognition model to determine whether the moving object is currently switching motion types; wherein, the motion type switching recognition model has learned the mapping relationship between motion type switching and multi-source sensor data; When the moving object changes its motion type, multiple attitude calculation methods are used to calculate the attitude information of key points in the multi-source sensor data to obtain the current forward direction and / or the change in direction of the moving object.

15. The apparatus as claimed in claim 9, characterized in that, Also includes: The second acquisition module is used to acquire the current ambient air pressure value collected by the wearable device; The calculation module is used to calculate the altitude corresponding to the current ambient air pressure value based on the current ambient air pressure value and the relationship between air pressure value and altitude. The second determining module is used to determine the current forward direction and / or change in direction of the moving object in three-dimensional space based on the current forward direction and / or change in direction, and the altitude corresponding to the current ambient air pressure value.

16. The apparatus as claimed in claim 9, characterized in that, Also includes: The navigation assistance module is used to, in response to the moving object being in a specific scene, acquire the current satellite navigation position information of the moving object, and correct the satellite navigation position information based on the moving object's current direction of travel and / or the amount of change in direction.

17. A wearable device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method as described in any one of claims 1 to 8.

18. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method as described in any one of claims 1 to 8.

Images