CN113984068A - Positioning method, positioning apparatus, and computer-readable storage medium - Google Patents
Positioning method, positioning apparatus, and computer-readable storage medium Download PDFInfo
- Publication number
- CN113984068A CN113984068A CN202111357725.2A CN202111357725A CN113984068A CN 113984068 A CN113984068 A CN 113984068A CN 202111357725 A CN202111357725 A CN 202111357725A CN 113984068 A CN113984068 A CN 113984068A
- Authority
- CN
- China
- Prior art keywords
- cloud
- positioning
- transformation relation
- decentralized
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
Abstract
The application discloses a positioning method, a positioning device and a computer readable storage medium, wherein the positioning method comprises the following steps: comparing the uncertainty of the decentralized transformation relation between the cloud end and the equipment end with a first preset threshold value; the de-centralization transformation relation is used for representing a coordinate transformation relation between a global coordinate system of the cloud end and a local coordinate system of the equipment end; in response to the uncertainty of the decentralization transformation relation being greater than the first preset threshold, updating the decentralization transformation relation according to current cloud positioning information and current equipment end tracking information matched with the current cloud positioning information; and performing fusion positioning on the subsequent cloud positioning information and the equipment end tracking information by adopting the updated decentralized transformation relation. By the scheme, the obtained end cloud fusion result has better consistency and efficiency.
Description
Technical Field
The present application relates to the field of positioning technologies, and in particular, to a positioning method, a positioning apparatus, and a computer-readable storage medium.
Background
Positioning and navigation based on a pre-built map are important underlying technologies in the fields of computer vision, robots, unmanned vehicles, augmented reality and the like. The terminal cloud fusion navigation scheme with low communication cost, low power consumption load, high stability and high coupling degree has important practical value in the fields of unmanned vehicles, robots, augmented reality and the like.
The difficulty of the device side tracking and cloud positioning fusion technology lies in that: 1) the cloud positioning is influenced by factors such as dynamic scenes, environmental changes and the like, the positioning success rate is low, and the positioning pose has high uncertainty; 2) due to the limitation of communication time delay and server computing power, the cloud positioning is delayed to return to the equipment end; 3) in order to reduce the inconsistency between the cloud map and the device-side tracking map building information, high-frequency rich data exchange needs to be carried out between the cloud side and the device side, and therefore communication load and computational load on two sides of the cloud side are increased.
Disclosure of Invention
The application provides at least one positioning method, a positioning device and a computer readable storage medium.
A first aspect of the present application provides a positioning method, including: comparing the uncertainty of the decentralized transformation relation between the cloud end and the equipment end with a first preset threshold value; the de-centralization transformation relation is used for representing a coordinate transformation relation between a global coordinate system of the cloud end and a local coordinate system of the equipment end; in response to that the uncertainty of the decentralization transformation relation is larger than the first preset threshold value, updating the decentralization transformation relation according to current cloud positioning information and current equipment end tracking information matched with the current cloud positioning information; and performing fusion positioning on the subsequent cloud positioning information and the equipment end tracking information by adopting the updated decentralized transformation relation.
Therefore, the cloud positioning information and the equipment tracking information are fused and positioned through the decentralized transformation relation between the cloud and the equipment, the requirements on the computing capacity and the data communication of the equipment are low, efficient end cloud fusion is achieved, and the obtained end cloud fusion result has good consistency; in addition, when the uncertainty of the decentralization transformation relation is larger than a first preset threshold value, the decentralization transformation relation is updated, and the updated decentralization transformation relation is adopted to perform fusion positioning on subsequent cloud positioning information and subsequent equipment side tracking information, so that the accuracy of the end cloud fusion result is high.
Before the step of comparing the uncertainty of the decentralized transformation relationship between the cloud and the device side with a first preset threshold, the method includes: acquiring initial cloud positioning information; initializing the decentralized transformation relation according to the initial cloud positioning information and initial equipment tracking information matched with the initial cloud positioning information.
Therefore, the decentralized transformation relationship is initialized according to the initial cloud positioning information and the initial equipment tracking information matched with the initial cloud positioning information, the initialized decentralized transformation relationship can be obtained, and fusion positioning of the cloud positioning information and the equipment tracking information can be achieved through the decentralized transformation relationship between the cloud and the equipment.
Wherein the method further comprises: and obtaining the initialized uncertainty of the decentralized transformation relation based on the mapping error of the cloud end and the observation error when the initial cloud end positioning information is matched with the initial equipment end tracking information.
Therefore, by integrating the mapping error of the cloud and the observation error when the initial cloud positioning information is matched with the initial equipment tracking information, the uncertainty of the decentralized transformation relation can be initialized, so that the decentralized transformation relation can be updated when the uncertainty of the decentralized transformation relation is greater than a first preset threshold value, and the accuracy of the end cloud fusion result is high.
Wherein the method comprises the following steps: and updating the uncertainty of the decentralized transformation relation according to the accumulated error of the equipment end in the operation process.
Therefore, the uncertainty of the decentralization transformation relation is updated according to the accumulated error of the equipment terminal in the operation process, so that the uncertainty of the decentralization transformation relation caused by the accumulated error can be reflected through the uncertainty of the decentralization transformation relation, the decentralization transformation relation can be updated when the uncertainty of the decentralization transformation relation is larger than a first preset threshold value, and the accuracy of the end cloud fusion result is high.
Wherein, the updating the uncertainty of the decentralization transformation relation according to the accumulated error of the equipment end in the operation process comprises the following steps: and updating the uncertainty of the de-centralization transformation relation by using a covariance matrix of pose information detected by the equipment terminal in the operation process.
Therefore, the decentralized transformation relation is used for representing the coordinate transformation relation between the global coordinate system of the cloud and the local coordinate system of the equipment end, and for an autonomously developed equipment end tracking and positioning algorithm, namely an equipment end white box tracking and positioning algorithm, not only can the output result of each state quantity be obtained, but also the corresponding information such as confidence coefficient, covariance matrix and the like can be obtained, so that the uncertainty of the decentralized transformation relation can be directly updated through the covariance matrix of pose information, the decentralized transformation relation is updated when the uncertainty of the decentralized transformation relation is greater than a first preset threshold, and the accuracy of the end cloud fusion result is high.
Wherein, the updating the uncertainty of the decentralization transformation relation according to the accumulated error of the equipment end in the operation process comprises the following steps: and updating the uncertainty of the decentralization transformation relation at a preset error accumulation rate.
Therefore, as the de-centering transformation relation is used for representing the coordinate transformation relation between the global coordinate system of the cloud and the local coordinate system of the equipment end, for a general equipment end tracking and positioning algorithm, namely an equipment end black box tracking and positioning algorithm, the uncertainty of the de-centering transformation relation can be updated through a preset error accumulation rate, so that the de-centering transformation relation is updated when the uncertainty of the de-centering transformation relation is greater than a first preset threshold, and the accuracy of an end cloud fusion result is high.
Wherein the preset error accumulation rate is positively correlated with the tracking duration or the tracking distance of the device side.
Therefore, by setting a preset error accumulation rate positively correlated with the tracking duration or the tracking distance of the equipment end and updating the uncertainty of the decentralized transformation relation at the preset error accumulation rate, the accumulated error generated by the black box system of the equipment end in the motion process can be brought into the positioning method, and the accuracy of the end cloud fusion result is high.
The map used by the cloud comprises a plurality of sub-maps, a preset map association relationship is formed between any two sub-maps, the decentralized transformation relationship comprises a first transformation relationship between a global coordinate system of the observed sub-map and a local coordinate system of the equipment end during initialization, and a second transformation relationship between the global coordinate system of the unobserved sub-map and the local coordinate system of the equipment end, which is obtained through calculation of the first transformation relationship and the preset map association relationship.
Therefore, under the condition that the map used by the cloud comprises a plurality of sub-maps, a second transformation relation between the global coordinate system of the sub-map which is not observed and the local coordinate system of the equipment end can be obtained through a first transformation relation between the global coordinate system of the observed sub-map and the local coordinate system of the equipment end and a preset map association relation between any two sub-maps, and therefore the decentralized transformation relation can comprise the first association relation and the second association relation, so that even if a certain sub-map is not observed within a certain time, a real-time fusion positioning result of the tracking and positioning algorithm of the equipment end under the global coordinate system of the sub-map which is not observed can be still obtained stably.
Before the step of performing fusion positioning on the subsequent cloud positioning information and the subsequent device tracking information by using the updated decentralized-transformation relationship, the method further includes: projecting subsequent cloud positioning information of the cloud to a local coordinate system of the equipment end through the decentralized transformation relation before updating and the decentralized transformation relation after updating respectively to obtain a first reprojection value and a second reprojection value; comparing the error between the first and second reprojected values to a second preset threshold; in response to that the error between the first reprojection value and the second reprojection value is greater than the second preset threshold, executing the step of performing fusion positioning on the subsequent cloud positioning information and the device side tracking information by using the updated decentralized-transformation relationship; and in response to that the error between the first reprojection value and the second reprojection value is not greater than the second preset threshold value, performing fusion positioning on subsequent cloud positioning information and equipment end tracking information by using the decentralized transformation relation before updating.
Therefore, the subsequent cloud positioning information of the cloud is projected to a local coordinate system of the equipment end through the decentralized transformation relation before updating and the decentralized transformation relation after updating respectively to obtain a first reprojected value and a second reprojected value, whether the error between the first reprojected value and the second reprojected value is larger than a second preset threshold value or not is judged, if yes, the subsequent cloud positioning information and the subsequent equipment tracking information are subjected to fusion positioning by adopting the decentralized transformation relation after updating, if not, the subsequent cloud positioning information and the subsequent equipment tracking information are subjected to fusion positioning by adopting the decentralized transformation relation before updating, so that when the error between the first reprojected value and the second reprojected value is small, the decentralized transformation relation is selected not to be adjusted, and frequent jumping of a fusion positioning result is avoided, the user has better use experience.
Before the step of performing fusion positioning on the subsequent cloud positioning information and the device tracking information by using the updated decentralized-transformation relationship, the method further includes: comparing the error between the first reprojection value and the second reprojection value corresponding to the subsequent cloud positioning information of a plurality of continuous frames of the cloud with a second preset threshold; in response to that errors between the first reprojection value and the second reprojection value corresponding to the subsequent cloud positioning information of the plurality of continuous frames of the cloud are larger than the second preset threshold, reinitializing the de-centralization transformation relationship according to the latest subsequent cloud positioning information of the cloud and equipment tracking information matched with the latest subsequent cloud positioning information of the cloud, and fusing and positioning the subsequent cloud positioning information and the equipment tracking information by adopting the reinitialized de-centralization transformation relationship; and in response to that the errors between the first reprojection value and the second reprojection value corresponding to the subsequent cloud positioning information of the cloud of a plurality of continuous frames are not larger than the second preset threshold, executing the step of performing fusion positioning on the subsequent cloud positioning information and the equipment tracking information by adopting the updated decentralized transformation relation.
Therefore, whether errors between first reprojection values and second reprojection values corresponding to subsequent cloud positioning information of a plurality of continuous frames of cloud are larger than a second preset threshold value or not is judged, if yes, the decentralized transformation relation is reinitialized according to the latest cloud subsequent positioning information and equipment tracking information matched with the latest cloud subsequent positioning information, the reinitialized decentralized transformation relation is adopted to perform fusion positioning on the subsequent cloud positioning information and the subsequent equipment tracking information, if not, the updated decentralized transformation relation is adopted to perform fusion positioning on the subsequent cloud positioning information and the subsequent equipment tracking information, the decentralized transformation relation can be reestablished when the system errors are too large, and the accuracy of the end cloud fusion result is high.
The device end is provided with at least two different operation stages, wherein the second preset thresholds of the different operation stages are different.
Therefore, the user has great difference on the requirements of stability and precision of the fusion positioning result in different operation stages, and the requirements of the user in different operation stages can be met by setting different second preset thresholds in different operation stages, so that the user experience can be improved.
In order to solve the above problem, a second aspect of the present application provides a positioning apparatus, comprising: the judging module is used for judging whether the uncertainty of a decentralized transformation relation between the cloud end and the equipment end is larger than a first preset threshold value or not, wherein the decentralized transformation relation is used for representing a coordinate transformation relation between a global coordinate system of the cloud end and a local coordinate system of the equipment end; the updating module is used for updating the decentralized transformation relation according to current cloud positioning information and current equipment end tracking information matched with the current cloud positioning information when the uncertainty of the decentralized transformation relation between the cloud end and the equipment end is judged to be larger than a first preset threshold value; and the positioning module is used for fusing and positioning subsequent cloud positioning information and equipment end tracking information by adopting the updated decentralized transformation relation.
In order to solve the above problem, a third aspect of the present application provides a positioning apparatus, which includes a memory and a processor coupled to each other, and the processor is configured to execute program instructions stored in the memory to implement the positioning method in the first aspect.
In order to solve the above problem, a fourth aspect of the present application provides a computer-readable storage medium having stored thereon program instructions, which when executed by a processor, implement the positioning method in the first aspect described above.
According to the scheme, whether the uncertainty of the decentralized transformation relation between the cloud end and the equipment end is larger than a first preset threshold value or not is judged, wherein the decentralized transformation relation is used for representing the coordinate transformation relation between a global coordinate system of the cloud end and a local coordinate system of the equipment end, when the uncertainty of the decentralized transformation relation between the cloud end and the equipment end is judged to be larger than the first preset threshold value, the decentralized transformation relation is updated according to the current cloud end positioning information and the current equipment end tracking information matched with the current cloud end positioning information, and then the updated decentralized transformation relation is adopted to perform fusion positioning on subsequent cloud end positioning information and subsequent equipment end tracking information. Therefore, the cloud positioning information and the equipment tracking information are fused and positioned through the decentralized transformation relation between the cloud and the equipment, the requirements on the computing capacity and the data communication of the equipment are low, efficient end cloud fusion is achieved, and the obtained end cloud fusion result has good consistency; in addition, when the uncertainty of the decentralization transformation relation is larger than a first preset threshold value, the decentralization transformation relation is updated, and the updated decentralization transformation relation is adopted to perform fusion positioning on subsequent cloud positioning information and subsequent equipment side tracking information, so that the accuracy of the end cloud fusion result is high.
Drawings
FIG. 1 is a schematic flow chart diagram illustrating an embodiment of a positioning method of the present application;
FIG. 2 is a schematic flow chart diagram illustrating another embodiment of a positioning method of the present application;
FIG. 3 is a schematic flow chart diagram of a positioning method according to another embodiment of the present application;
FIG. 4 is a schematic flow chart diagram illustrating a positioning method according to another embodiment of the present application;
FIG. 5 is a block diagram of an embodiment of a positioning device of the present application;
FIG. 6 is a schematic diagram of a frame of another embodiment of the positioning device of the present application;
FIG. 7 is a block diagram of an embodiment of a computer-readable storage medium of the present application.
Detailed Description
The following describes in detail the embodiments of the present application with reference to the drawings attached hereto.
In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, interfaces, techniques, etc. in order to provide a thorough understanding of the present application.
The terms "system" and "network" are often used interchangeably herein. The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship. Further, the term "plurality" herein means two or more than two.
Referring to fig. 1, fig. 1 is a schematic flow chart of an embodiment of a positioning method according to the present application. Specifically, the method may include the steps of:
step S11: comparing the uncertainty of the decentralized transformation relation between the cloud end and the equipment end with a first preset threshold value; the decentralized transformation relation is used for representing the coordinate transformation relation between the global coordinate system of the cloud end and the local coordinate system of the equipment end. It is to be understood that, in response to the uncertainty of the decentralised transform relationship being greater than the first preset threshold, step S12 is executed; and responding to that the uncertainty of the decentralization transformation relation is not greater than a first preset threshold value, indicating that the decentralization transformation relation is relatively accurate at present, and in order to avoid frequent jumping of the fusion positioning result, temporarily not updating the decentralization transformation relation, and ending the process.
In the process of fusion positioning of the tracking system of the device end and the positioning system of the cloud end, the device end and the cloud end do not share the same coordinate system, so that a decentralized transformation relation needs to be established to realize coordinate transformation between the global coordinate system of the cloud end and the local coordinate system of the device end, the decentralized transformation relation can transform a frame of cloud end positioning pose information and a corresponding frame of device end tracking pose information, and the relative relation between the cloud end positioning information and the device end tracking information matched with the cloud end positioning information can be maintained through the decentralized transformation relation.
In an embodiment, an expression form of the decentralized transformation relation can be selected according to information of the cloud map and information tracked by the device side. When the cloud map is consistent with the scale tracked by the equipment end, the de-centering transformation relation can be rigid transformation with six degrees of freedom; when the scales tracked by the cloud map and the equipment end are inconsistent, the de-centralization transformation relation can be a seven-degree-of-freedom similarity transformation; when the scales tracked by the cloud map and the equipment end are consistent and the gravity directions of the cloud map and the equipment end are both observable, the de-centralization transformation relation can be position of four degrees of freedom plus yaw angle transformation; when the scales tracked by the cloud map and the equipment end are consistent, and the gravity direction and the yaw angle of the cloud map and the equipment end are observable, the decentralized transformation relation can be position transformation of three degrees of freedom.
It can be appreciated that in tracking the location, the accuracy of the decentralised transform relationship is indicated by adding an uncertainty to the decentralised transform relationship; when the uncertainty of the decentralization transformation relation between the cloud end and the equipment end is larger than a first preset threshold value, the accuracy of the decentralization transformation relation is poor, and the decentralization transformation relation needs to be updated; when the uncertainty of the decentralization transformation relation between the cloud and the equipment end is not larger than a first preset threshold, the decentralization transformation relation is relatively accurate at present, and therefore the decentralization transformation relation can not be updated.
Step S12: and updating the decentralized transformation relation according to the current cloud positioning information and the current equipment tracking information matched with the current cloud positioning information.
It can be understood that after the current cloud positioning information is acquired, the current cloud positioning information can be compared with all tracking information of the current device side, then the current device side tracking information matched with the current cloud positioning information is acquired, and at this time, according to the current cloud positioning information and the current device side tracking information matched with the current cloud positioning information, the decentralized transformation relationship between the cloud side and the device side can be determined, that is, the decentralized transformation relationship can be optimized and updated. In this embodiment, the decentralized transformation relationship may be optimized and updated by using methods such as an extended kalman filter, an unscented kalman filter, a root mean square filter, and nonlinear optimization.
In an embodiment, because the positioning information of a single frame has randomness and a large amount of noise, the decentralized transformation relationship can be updated according to the current cloud positioning information of multiple frames and the tracking information of the current equipment end of the multiple frames matched with the current cloud positioning information of the multiple frames, so that the accuracy of the end cloud fusion result is high.
Step S13: and performing fusion positioning on subsequent cloud positioning information and equipment tracking information by adopting the updated decentralized transformation relation.
After the decentralized transformation relation is updated, in the subsequent fusion positioning process, the equipment terminal initiates a receiving request, receives subsequent cloud positioning information sent by the cloud, compares the subsequent cloud positioning information with all tracking information of the equipment terminal to obtain subsequent equipment terminal tracking information matched with the subsequent cloud positioning information, and then adopts the updated decentralized transformation relation to perform fusion positioning on the subsequent cloud positioning information and the subsequent equipment terminal tracking information.
The execution main body of the positioning method can be a positioning device, for example, the positioning method can be executed by a terminal device or a cloud device or a server or other processing devices, wherein the terminal device can be a mobile device such as a robot, an unmanned vehicle, an unmanned aerial vehicle, or the like, or a User Equipment (UE), a User terminal, a cordless telephone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, or the like. In some possible implementations, the location method may be implemented by a processor calling computer readable instructions stored in a memory. The tracking and positioning algorithm of the equipment end can use preset tracking and positioning algorithms of the equipment ends such as ARKit, ARCore and the like, and also can use a visual inertial tracking and positioning algorithm for tracking and positioning based on images and inertial navigation information of the equipment end or a pure visual tracking and positioning algorithm based on single/double/multi-view image information.
According to the scheme, the cloud positioning information and the equipment tracking information are fused and positioned through the decentralized transformation relation between the cloud and the equipment, the requirements on the computing capacity and the data communication of the equipment are low, so that efficient end cloud fusion is realized, and the obtained end cloud fusion result has good consistency; in addition, when the uncertainty of the decentralization transformation relation is larger than a first preset threshold value, the decentralization transformation relation is optimized and updated, and the updated decentralization transformation relation is adopted to perform fusion positioning on subsequent cloud positioning information and subsequent equipment side tracking information, so that the accuracy of a side cloud fusion result is high.
Referring to fig. 2, fig. 2 is a schematic flowchart illustrating a positioning method according to another embodiment of the present application. Specifically, the method may include the steps of:
step S21: and acquiring initial cloud positioning information.
Step S22: initializing the decentralized transformation relation according to the initial cloud positioning information and initial equipment tracking information matched with the initial cloud positioning information.
It can be understood that, because data communication and cloud location between the cloud and the device end all have great delay, therefore can preserve device end tracking information in advance, after obtaining initial cloud location information, can compare with all tracking information of the device end, then obtain initial device end tracking information with initial cloud location information assorted, according to initial cloud location information and initial device end tracking information with initial cloud location information assorted at this moment, can confirm the decentralization transform relation between the cloud and the device end, can initialize the decentralization transform relation. Specifically, after the first frame image successfully positioned at the cloud end is obtained, the first frame image is compared with all key frames of the tracking information of the equipment end, if the first frame image successfully positioned at the cloud end is matched with a certain key frame of the tracking information of the equipment end, the pose information of the first frame image successfully positioned at the cloud end and the pose information corresponding to the key frame of the tracking information of the equipment end can be obtained, so that the initialized decentralized transformation relation between the cloud end and the equipment end can be determined, and the cloud end positioning information and the equipment end tracking information can be fused and positioned through the decentralized transformation relation between the cloud end and the equipment end.
Further, the positioning method of the present application may further include: and obtaining uncertainty of the initialized decentralized transformation relation based on the image building error of the cloud end and the observation error when the initial cloud end positioning information is matched with the initial equipment end tracking information. It can be appreciated that, since the cloud location results are relatively noisy, the uncertainty of the initialized decentralized transform relationship needs to be derived from the uncertainty of the cloud location. Specifically, the uncertainty of cloud positioning at least comprises uncertainty of two aspects, the uncertainty of the first aspect is that a map of a cloud has a mapping error when mapping, the uncertainty of the second aspect is that when positioning, an observation error exists when matching between a three-dimensional point in initial cloud positioning information and a two-dimensional point of initial equipment end tracking information, the uncertainty of the two aspects is integrated, an initialized decentralization transformation relation can be obtained, so that the decentralization transformation relation can be updated when the uncertainty of the decentralization transformation relation is greater than a first preset threshold value, and the accuracy of an end cloud fusion result is high.
Step S23: comparing the uncertainty of the decentralized transformation relation between the cloud end and the equipment end with a first preset threshold value; the decentralized transformation relation is used for representing the coordinate transformation relation between the global coordinate system of the cloud end and the local coordinate system of the equipment end. In response to the uncertainty of the decentralization transform relationship being greater than the first preset threshold, performing step S24; and responding to the uncertainty of the decentralized conversion relation not being larger than the first preset threshold value, and ending the process.
Step S24: and updating the decentralized transformation relation according to the current cloud positioning information and the current equipment end tracking information matched with the current cloud positioning information.
Step S25: and updating the uncertainty of the decentralized transformation relation according to the accumulated error of the equipment end in the operation process.
The tracking and positioning system at the equipment end can generate error accumulation in the tracking process, and the error accumulation process needs to be incorporated into the fusion positioning method, and it can be understood that the confidence coefficient of the covariance matrix of the visual inertial system is lower and lower due to the error accumulation, that is, the decentralized transformation relation is more and more inaccurate due to the accumulated error generated by the visual inertial system, so that the uncertainty of the decentralized transformation relation needs to be updated according to the accumulated error of the equipment end in the operation process, the inaccuracy degree of the decentralized transformation relation caused by the accumulated error can be reflected by the uncertainty of the decentralized transformation relation, and therefore, the decentralized transformation relation can be updated when the uncertainty of the decentralized transformation relation is greater than a first preset threshold value, and the accuracy of the end cloud fusion result is high.
In an embodiment, the step S25 specifically includes: and updating the uncertainty of the decentralized transformation relation by using the covariance matrix of the pose information detected by the equipment end in the operation process. It can be understood that, since the decentralized transformation relationship is used for representing the coordinate transformation relationship between the global coordinate system of the cloud and the local coordinate system of the device side, and for an autonomously developed device side tracking and positioning algorithm, that is, a device side white box tracking and positioning algorithm, not only can the output result of each state quantity be obtained, but also information such as a corresponding confidence coefficient and a covariance matrix can be obtained, so that the uncertainty of the decentralized transformation relationship can be directly updated through the covariance matrix of the pose information of the device side, and thus, when the uncertainty of the decentralized transformation relationship is greater than a first preset threshold, the decentralized transformation relationship is updated, and further, the accuracy of the end cloud fusion result is high.
In an embodiment, the step S25 specifically includes: and updating the uncertainty of the decentralization transformation relation at a preset error accumulation rate. It can be understood that, since the de-centering transformation relation is used for representing the coordinate transformation relation between the global coordinate system of the cloud and the local coordinate system of the device, for the existing device tracking and positioning algorithm, that is, the device black box tracking and positioning algorithm, since the output result of each state quantity can only be obtained, and the corresponding information such as confidence coefficient and covariance matrix cannot be obtained, the uncertainty of the de-centering transformation relation can be updated through the preset error accumulation rate, so that when the uncertainty of the de-centering transformation relation is greater than the first preset threshold, the de-centering transformation relation is updated, and further, the accuracy of the end cloud fusion result is high.
Further, the preset error accumulation rate is positively correlated with the tracking duration or the tracking distance of the device side. It can be understood that the longer the tracking time of the device side is, or the longer the tracking distance of the device side is, the more the error is accumulated, so that by setting a preset error accumulation rate positively correlated to the tracking time or the tracking distance of the device side, and updating the uncertainty of the decentralized transformation relationship at the preset error accumulation rate, the accumulated error generated by the device side black box system in the motion process can be incorporated into the positioning method, and the accuracy of the end cloud fusion result is high.
Step S26: and adopting the updated decentralized transformation relation to perform fusion positioning on subsequent cloud positioning information and equipment tracking information.
In this embodiment, steps S23, S24, and S26 are substantially similar to steps S11-S13 in the above embodiments of the present application, and are not described herein again.
In an embodiment, the map used by the cloud includes a plurality of sub-maps, a preset map association relationship exists between any two sub-maps, and the decentralized transformation relationship includes a first transformation relationship between a global coordinate system of the observed sub-map and a local coordinate system of the device side during initialization, and a second transformation relationship between the global coordinate system of the unobserved sub-map and the local coordinate system of the device side, which is calculated through the first transformation relationship and the preset map association relationship. It can be understood that, under the condition that the map used by the cloud includes a plurality of sub-maps, a second transformation relation between the global coordinate system of the sub-map which is not observed and the local coordinate system of the device end can be obtained through a first transformation relation between the global coordinate system of the observed sub-map and the local coordinate system of the device end and a preset map association relation between any two sub-maps, so that the transformation relation between the global coordinate systems of the plurality of sub-maps and the local coordinate system of the device end can be maintained simultaneously, that is, the decentralized transformation relation can include the first association relation and the second association relation. The device tracking and positioning algorithm has better consistency in a short period, so that even if a certain sub-map is not observed in a certain time, the real-time fusion positioning result of the device tracking information under the global coordinate system of the sub-map which is not observed can be stably obtained by utilizing the device tracking information and the decentralized transformation relation.
Referring to fig. 3, fig. 3 is a schematic flowchart illustrating a positioning method according to another embodiment of the present application. Specifically, the method may include the steps of:
step S31: comparing the uncertainty of the decentralized transformation relation between the cloud end and the equipment end with a first preset threshold value; the decentralized transformation relation is used for representing the coordinate transformation relation between the global coordinate system of the cloud end and the local coordinate system of the equipment end. In response to the uncertainty of the decentralization transform relationship being greater than the first preset threshold, performing step S32; and responding to the uncertainty of the decentralized conversion relation not being larger than the first preset threshold value, and ending the process.
Step S32: and updating the decentralized transformation relation according to the current cloud positioning information and the current equipment tracking information matched with the current cloud positioning information.
Step S33: and projecting subsequent cloud positioning information of the cloud to a local coordinate system of the equipment end through the decentralized transformation relation before updating and the decentralized transformation relation after updating respectively to obtain a first reprojection value and a second reprojection value.
Step S34: the error between the first and second reprojected values is compared to a second preset threshold. In response to the error between the first and second reprojected values not being greater than the second preset threshold, performing step S35; in response to the error between the first and second reprojected values being greater than the second preset threshold, step S36 is performed.
Step S35: and performing fusion positioning on subsequent cloud positioning information and equipment tracking information by adopting a decentralized transformation relation before updating.
After the decentralized transformation relationship is updated and adjusted, if the updated decentralized transformation relationship is directly adopted to perform fusion positioning on subsequent cloud positioning information and subsequent equipment tracking information, frequent jitter of a fusion positioning result may be caused by frequent updating of the decentralized transformation relationship, and user experience is further influenced; therefore, in this embodiment, the subsequent cloud positioning information of the cloud is projected onto the local coordinate system of the device end through the pre-update decentralization transformation relationship and the post-update decentralization transformation relationship respectively to obtain a first reprojected value and a second reprojected value, and whether the error between the first reprojected value and the second reprojected value is greater than a second preset threshold is determined, if yes, the subsequent cloud positioning information and the subsequent device tracking information are fusion-positioned by using the post-update decentralization transformation relationship, and if not, the subsequent cloud positioning information and the subsequent device tracking information are fusion-positioned by using the pre-update decentralization transformation relationship, so that when the error between the first reprojected value and the second reprojected value is small, the decentralization transformation relationship is selected not to be adjusted, and frequent jitter of a fusion-positioning result is not caused, the user has better use experience.
Step S36: and performing fusion positioning on subsequent cloud positioning information and equipment tracking information by adopting the updated decentralized transformation relation.
In this embodiment, steps S31, S32, and S36 are substantially similar to steps S11-S13 in the above embodiments of the present application, and are not described herein again.
Referring to fig. 4, fig. 4 is a schematic flowchart illustrating a positioning method according to another embodiment of the present application. Specifically, the method may include the steps of:
step S41: comparing the uncertainty of the decentralized transformation relation between the cloud end and the equipment end with a first preset threshold value; the decentralized transformation relation is used for representing the coordinate transformation relation between the global coordinate system of the cloud end and the local coordinate system of the equipment end. In response to the uncertainty of the decentralization transform relationship being greater than the first preset threshold, performing step S42; and responding to the uncertainty of the decentralized conversion relation not being larger than the first preset threshold value, and ending the process.
Step S42: and updating the decentralized transformation relation according to the current cloud positioning information and the current equipment tracking information matched with the current cloud positioning information.
Step S43: and projecting subsequent cloud positioning information of the cloud to a local coordinate system of the equipment end through the decentralized transformation relation before updating and the decentralized transformation relation after updating respectively to obtain a first reprojection value and a second reprojection value.
Step S44: the error between the first and second reprojected values is compared to a second preset threshold. In response to the error between the first and second reprojected values not being greater than the second preset threshold, performing step S45; in response to the error between the first and second reprojected values being greater than the second preset threshold, step S46 is performed.
Step S45: and performing fusion positioning on subsequent cloud positioning information and equipment tracking information by adopting a decentralized transformation relation before updating.
Step S46: and comparing the error between the first reprojection value and the second reprojection value corresponding to the subsequent cloud positioning information of the plurality of continuous frames of the clouds with a second preset threshold. In response to that the errors between the first reprojection value and the second reprojection value corresponding to the subsequent cloud positioning information of the plurality of continuous frames of cloud terminals are greater than a second preset threshold, executing step S47; in response to that the error between the first reprojection value and the second reprojection value corresponding to the subsequent cloud positioning information of the plurality of continuous frames of cloud is not greater than the second preset threshold, step S48 is executed.
Step S47: and according to the latest subsequent cloud positioning information of the cloud and the equipment tracking information matched with the latest subsequent cloud positioning information of the cloud, re-initializing the de-centralization transformation relation, and performing fusion positioning on the subsequent cloud positioning information and the equipment tracking information by adopting the re-initialized de-centralization transformation relation.
It can be understood that, when the subsequent cloud positioning information of a plurality of continuous frames of the cloud is projected onto the local coordinate system of the device end through the pre-update decentralization transformation relation and the post-update decentralization transformation relation, and the obtained error between the first reprojection value and the second reprojection value is greater than the second preset threshold, the error of the visual inertial system may be too large, and at this time, the decentralization transformation relation needs to be adjusted once, that is, the decentralization transformation relation needs to be reinitialized; the method comprises the steps of calculating a new decentralization transformation relation by using pose information of a latest frame of image positioned by a cloud and pose information of a key frame of equipment end tracking information matched with the latest frame of image positioned by the cloud, completing reinitialization of the decentralization transformation relation if a reprojection error of a certain frame in the historical cloud positioning information under the new decentralization transformation relation is smaller than a second preset threshold value, and performing fusion positioning on subsequent cloud positioning information and subsequent equipment end tracking information by adopting the reinitialized decentralization transformation relation, so that the decentralization transformation relation can be reestablished when a system error is too large, and the accuracy of an end cloud fusion result is high.
Step S48: and adopting the updated decentralized transformation relation to perform fusion positioning on subsequent cloud positioning information and equipment tracking information.
In this embodiment, steps S41-S45 and S48 are substantially similar to steps S31-S36 in the above embodiments of the present application, and are not described herein again.
In one implementation scenario, the device side has at least two different operating phases, wherein the second preset thresholds of the different operating phases are different. Specifically, the operation process of the device-side tracking and positioning system may be divided into different stages, such as an initialization stage, a traveling navigation stage, and a stationary observation stage, where in each stage, the requirements of the user on the stability and accuracy of the fusion positioning are greatly different, so that a different second preset threshold needs to be adopted in each stage to improve the user experience. It can be understood that, because in different operation stages, the user has a greater difference to the stability and accuracy requirements of the fusion positioning result, and different second preset thresholds are set in different operation stages, the requirements of the user in different operation stages can be met, and therefore the user experience can be improved.
Referring to fig. 5, fig. 5 is a schematic diagram of a frame of an embodiment of the positioning device of the present application. The positioning device 50 includes: a determining module 500, configured to determine whether an uncertainty of a de-centering transformation relationship between the cloud and the device side is greater than a first preset threshold, where the de-centering transformation relationship is used to represent a coordinate transformation relationship between a global coordinate system of the cloud and a local coordinate system of the device side; an updating module 502, configured to update the decentralized transformation relationship according to current cloud location information and current device tracking information matched with the current cloud location information when it is determined whether uncertainty of the decentralized transformation relationship between the cloud and the device is greater than a first preset threshold; and the positioning module 504 is configured to perform fusion positioning on subsequent cloud positioning information and device tracking information by using the updated decentralized transformation relationship.
In the scheme, the positioning module 504 performs fusion positioning on the cloud positioning information and the equipment tracking information through the decentralized transformation relationship between the cloud and the equipment, and has low requirements on the computing capacity and data communication of the equipment, so that efficient end cloud fusion is realized, and the obtained end cloud fusion result has better consistency; in addition, when the uncertainty of the decentralized transformation relationship is greater than a first preset threshold, the determining module 500 updates the decentralized transformation relationship through the updating module 502, and performs fusion positioning on subsequent cloud positioning information and subsequent equipment tracking information by using the updated decentralized transformation relationship, so that the accuracy of the end cloud fusion result is high.
In some embodiments, the positioning apparatus 50 further includes an initialization module (not shown), which is specifically configured to obtain initial cloud positioning information, and initialize the decentralized transformation relationship according to the initial cloud positioning information and initial device tracking information matched with the initial cloud positioning information.
In some embodiments, the updating module 502 is further configured to update the uncertainty of the de-centering transformation relation according to an accumulated error of the device during operation.
In some embodiments, the step of the updating module 502 performing the updating of the uncertainty of the de-centering transformation relation according to the accumulated error of the device side during the operation process includes: updating the uncertainty of the de-centralization transformation relation by using a covariance matrix of pose information detected by the equipment end in the operation process; or updating the uncertainty of the decentralization transformation relation at a preset error accumulation rate.
In some embodiments, the determining module 500 is further configured to project the subsequent cloud positioning information of the cloud to the local coordinate system of the device end through the decentralized transformation relationship before the updating and the decentralized transformation relationship after the updating, so as to obtain a first reprojection value and a second reprojection value, and determine whether an error between the first reprojection value and the second reprojection value is greater than a second preset threshold. If the determining module 500 determines that the error between the first reprojection value and the second reprojection value is greater than a second preset threshold, the positioning module 504 performs the step of performing fusion positioning on the subsequent cloud positioning information and the device tracking information by using the updated decentralized transformation relationship; if the determining module 500 determines that the error between the first reprojection value and the second reprojection value is not greater than the second preset threshold, the positioning module 504 is configured to perform fusion positioning on the subsequent cloud positioning information and the device tracking information by using the decentralized transformation relationship before updating.
In some embodiments, the determining module 500 is further configured to determine whether errors between the first reprojection value and the second reprojection value corresponding to the subsequent cloud positioning information of the plurality of consecutive frames of the cloud are both greater than a second preset threshold. If the determining module 500 determines that the errors between the first reprojection value and the second reprojection value corresponding to the subsequent cloud positioning information of the plurality of continuous frames of the cloud are greater than a second preset threshold, the initializing module is configured to reinitialize the decentralized transformation relationship according to the latest subsequent cloud positioning information of the cloud and the device tracking information matched with the latest subsequent cloud positioning information of the cloud, and the positioning module 504 performs fusion positioning on the subsequent cloud positioning information and the device tracking information by using the reinitialized decentralized transformation relationship; if the determining module 500 determines that the errors between the first reprojection value and the second reprojection value corresponding to the subsequent cloud positioning information of the cloud of a plurality of consecutive frames are not both greater than the second preset threshold, the positioning module 504 executes the step of performing fusion positioning on the subsequent cloud positioning information and the device tracking information by using the updated decentralized-to-center transformation relationship.
Referring to fig. 6, fig. 6 is a schematic diagram of a frame of a positioning device according to another embodiment of the present application. The positioning apparatus 60 includes a memory 61 and a processor 62 coupled to each other, and the processor 62 is configured to execute program instructions stored in the memory 61 to implement the steps of any of the above-described embodiments of the positioning method. In one particular implementation scenario, the positioning device 60 may include, but is not limited to: microcomputer, server.
In particular, the processor 62 is used to control itself and the memory 61 to implement the steps in the positioning embodiment of cloud fusion at either end described above. The processor 62 may also be referred to as a CPU (Central Processing Unit). The processor 62 may be an integrated circuit chip having signal processing capabilities. The Processor 62 may also be a general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. In addition, the processor 62 may be collectively implemented by an integrated circuit chip.
In the above scheme, the processor 62 performs fusion positioning on the cloud positioning information and the equipment tracking information through the decentralized transformation relationship between the cloud and the equipment, and has low requirements on the computing capacity and data communication of the equipment, so that efficient end cloud fusion is realized, and the obtained end cloud fusion result has good consistency; in addition, when the uncertainty of the decentralization transformation relation is larger than a first preset threshold value, the decentralization transformation relation is updated, and the updated decentralization transformation relation is adopted to perform fusion positioning on subsequent cloud positioning information and subsequent equipment side tracking information, so that the accuracy of the end cloud fusion result is high.
Referring to fig. 7, fig. 7 is a block diagram illustrating an embodiment of a computer-readable storage medium according to the present application. The computer readable storage medium 70 stores program instructions 700 capable of being executed by a processor, the program instructions 700 for implementing the steps in the positioning embodiments of either end cloud convergence described above.
The disclosure relates to the field of augmented reality, and aims to detect or identify relevant features, states and attributes of a target object by means of various visual correlation algorithms by acquiring image information of the target object in a real environment, so as to obtain an AR effect combining virtual and reality matched with specific applications. For example, the target object may relate to a face, a limb, a gesture, an action, etc. associated with a human body, or a marker, a marker associated with an object, or a sand table, a display area, a display item, etc. associated with a venue or a place. The vision-related algorithms may involve visual localization, SLAM, three-dimensional reconstruction, image registration, background segmentation, key point extraction and tracking of objects, pose or depth detection of objects, and the like. The specific application can not only relate to interactive scenes such as navigation, explanation, reconstruction, virtual effect superposition display and the like related to real scenes or articles, but also relate to special effect treatment related to people, such as interactive scenes such as makeup beautification, limb beautification, special effect display, virtual model display and the like.
The detection or identification processing of the relevant characteristics, states and attributes of the target object can be realized through the convolutional neural network. The convolutional neural network is a network model obtained by performing model training based on a deep learning framework.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a module or a unit is merely one type of logical division, and an actual implementation may have another division, for example, a unit or a component may be combined or integrated with another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some interfaces, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on network elements. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Claims (14)
1. A method of positioning, the method comprising:
comparing the uncertainty of the decentralized transformation relation between the cloud end and the equipment end with a first preset threshold value; the de-centralization transformation relation is used for representing a coordinate transformation relation between a global coordinate system of the cloud end and a local coordinate system of the equipment end;
in response to that the uncertainty of the decentralization transformation relation is larger than the first preset threshold value, updating the decentralization transformation relation according to current cloud positioning information and current equipment end tracking information matched with the current cloud positioning information;
and performing fusion positioning on the subsequent cloud positioning information and the equipment end tracking information by adopting the updated decentralized transformation relation.
2. The method according to claim 1, wherein the step of comparing the uncertainty of the de-centering transformation relationship between the cloud and the device side with a first preset threshold is preceded by the method comprising:
acquiring initial cloud positioning information;
initializing the decentralized transformation relation according to the initial cloud positioning information and initial equipment tracking information matched with the initial cloud positioning information.
3. The method of claim 2, further comprising:
and obtaining the initialized uncertainty of the decentralized transformation relation based on the mapping error of the cloud end and the observation error when the initial cloud end positioning information is matched with the initial equipment end tracking information.
4. The method according to claim 1, characterized in that it comprises:
and updating the uncertainty of the decentralized transformation relation according to the accumulated error of the equipment end in the operation process.
5. The method according to claim 4, wherein the updating the uncertainty of the de-centering transformation relation according to the accumulated error of the device side in the operation process comprises:
and updating the uncertainty of the de-centralization transformation relation by using a covariance matrix of pose information detected by the equipment terminal in the operation process.
6. The method according to claim 4, wherein the updating the uncertainty of the de-centering transformation relation according to the accumulated error of the device side in the operation process comprises:
and updating the uncertainty of the decentralization transformation relation at a preset error accumulation rate.
7. The method according to claim 6, wherein the preset error accumulation rate is positively correlated with the tracking duration or the tracking distance of the device side.
8. The method according to claim 3, wherein the map used by the cloud includes a plurality of sub-maps, any two sub-maps have a predetermined map association relationship therebetween, and the decentralized transformation relationship includes a first transformation relationship between a global coordinate system of the observed sub-map and a local coordinate system of the device side at initialization, and a second transformation relationship between a global coordinate system of the unobserved sub-map and a local coordinate system of the device side calculated from the first transformation relationship and the predetermined map association relationship.
9. The method according to claim 1, wherein before the step of performing the fusion positioning on the subsequent cloud positioning information and the device tracking information by using the updated decentralized transformation relationship, the method further comprises:
projecting subsequent cloud positioning information of the cloud to a local coordinate system of the equipment end through the decentralized transformation relation before updating and the decentralized transformation relation after updating respectively to obtain a first reprojection value and a second reprojection value;
comparing the error between the first and second reprojected values to a second preset threshold;
in response to that the error between the first reprojection value and the second reprojection value is greater than the second preset threshold, executing the step of performing fusion positioning on the subsequent cloud positioning information and the device side tracking information by using the updated decentralized-transformation relationship;
and in response to that the error between the first reprojection value and the second reprojection value is not greater than the second preset threshold value, performing fusion positioning on subsequent cloud positioning information and equipment end tracking information by using the decentralized transformation relation before updating.
10. The method of claim 9, wherein before performing the step of performing the fused positioning of the subsequent cloud positioning information and the device-side tracking information by using the updated decentralized-transformation relationship, the method further comprises:
comparing the error between the first reprojection value and the second reprojection value corresponding to the subsequent cloud positioning information of a plurality of continuous frames of the cloud with a second preset threshold;
in response to that errors between the first reprojection value and the second reprojection value corresponding to the subsequent cloud positioning information of the plurality of continuous frames of the cloud are larger than the second preset threshold, reinitializing the de-centralization transformation relationship according to the latest subsequent cloud positioning information of the cloud and equipment tracking information matched with the latest subsequent cloud positioning information of the cloud, and fusing and positioning the subsequent cloud positioning information and the equipment tracking information by adopting the reinitialized de-centralization transformation relationship;
and in response to that the errors between the first reprojection value and the second reprojection value corresponding to the subsequent cloud positioning information of the cloud of a plurality of continuous frames are not larger than the second preset threshold, executing the step of performing fusion positioning on the subsequent cloud positioning information and the equipment tracking information by adopting the updated decentralized transformation relation.
11. Method according to claim 9 or 10, characterized in that the equipment side has at least two different operating phases, wherein the second preset threshold values of the different operating phases are different.
12. A positioning device, comprising:
the judging module is used for comparing the uncertainty of the decentralized transformation relation between the cloud end and the equipment end with a first preset threshold value; the de-centralization transformation relation is used for representing a coordinate transformation relation between a global coordinate system of the cloud end and a local coordinate system of the equipment end;
the updating module is used for responding that the uncertainty of the decentralized transformation relation is larger than the first preset threshold value, and updating the decentralized transformation relation according to current cloud positioning information and current equipment tracking information matched with the current cloud positioning information;
and the positioning module is used for fusing and positioning subsequent cloud positioning information and equipment end tracking information by adopting the updated decentralized transformation relation.
13. A positioning apparatus, comprising a memory and a processor coupled to each other, wherein the processor is configured to execute program instructions stored in the memory to implement the positioning method according to any one of claims 1 to 11.
14. A computer readable storage medium having stored thereon program instructions which, when executed by a processor, implement the localization of end cloud fusion of any of claims 1 to 11.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111357725.2A CN113984068A (en) | 2021-11-16 | 2021-11-16 | Positioning method, positioning apparatus, and computer-readable storage medium |
| PCT/CN2022/106560 WO2023087758A1 (en) | 2021-11-16 | 2022-07-19 | Positioning method, positioning apparatus, computer-readable storage medium, and computer program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111357725.2A CN113984068A (en) | 2021-11-16 | 2021-11-16 | Positioning method, positioning apparatus, and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113984068A true CN113984068A (en) | 2022-01-28 |
Family
ID=79748886
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111357725.2A Pending CN113984068A (en) | 2021-11-16 | 2021-11-16 | Positioning method, positioning apparatus, and computer-readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113984068A (en) |
| WO (1) | WO2023087758A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115601034A (en) * | 2022-09-30 | 2023-01-13 | 北京交通大学（Cn） | Attack detection method for decentralized finance |
| WO2023087758A1 (en) * | 2021-11-16 | 2023-05-25 | 上海商汤智能科技有限公司 | Positioning method, positioning apparatus, computer-readable storage medium, and computer program product |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019126957A1 (en) * | 2017-12-25 | 2019-07-04 | 深圳前海达闼云端智能科技有限公司 | Terminal-cloud combined positioning method and apparatus, electronic device and computer program product |
| CN108717710B (en) * | 2018-05-18 | 2022-04-22 | 京东方科技集团股份有限公司 | Positioning method, device and system in indoor environment |
| CN112146645B (en) * | 2019-06-28 | 2022-07-22 | 浙江商汤科技开发有限公司 | Method and device for aligning coordinate system, electronic equipment and storage medium |
| CN112115874B (en) * | 2020-09-21 | 2022-07-15 | 武汉大学 | Cloud-fused visual SLAM system and method |
| CN113295159B (en) * | 2021-05-14 | 2023-03-03 | 浙江商汤科技开发有限公司 | Positioning method and device for end cloud integration and computer readable storage medium |
| CN113984068A (en) * | 2021-11-16 | 2022-01-28 | 浙江商汤科技开发有限公司 | Positioning method, positioning apparatus, and computer-readable storage medium |
-
2021
- 2021-11-16 CN CN202111357725.2A patent/CN113984068A/en active Pending
-
2022
- 2022-07-19 WO PCT/CN2022/106560 patent/WO2023087758A1/en unknown
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023087758A1 (en) * | 2021-11-16 | 2023-05-25 | 上海商汤智能科技有限公司 | Positioning method, positioning apparatus, computer-readable storage medium, and computer program product |
| CN115601034A (en) * | 2022-09-30 | 2023-01-13 | 北京交通大学（Cn） | Attack detection method for decentralized finance |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023087758A1 (en) | 2023-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110582798B (en) | System and method for virtual enhanced vision simultaneous localization and mapping | |
| CN107990899B (en) | Positioning method and system based on SLAM | |
| CN109544636A (en) | A kind of quick monocular vision odometer navigation locating method of fusion feature point method and direct method | |
| WO2019157925A1 (en) | Visual-inertial odometry implementation method and system | |
| CN106940704B (en) | Positioning method and device based on grid map | |
| US20150243035A1 (en) | Method and device for determining a transformation between an image coordinate system and an object coordinate system associated with an object of interest | |
| CN109816696A (en) | A kind of robot localization and build drawing method, computer installation and computer readable storage medium | |
| RU2662913C2 (en) | Method of robot localization in localization plane | |
| CN112219087A (en) | Pose prediction method, map construction method, movable platform and storage medium | |
| US20210183100A1 (en) | Data processing method and apparatus | |
| US10636190B2 (en) | Methods and systems for exploiting per-pixel motion conflicts to extract primary and secondary motions in augmented reality systems | |
| CN110726406A (en) | Improved nonlinear optimization monocular inertial navigation SLAM method | |
| CN111127524A (en) | Method, system and device for tracking trajectory and reconstructing three-dimensional image | |
| CN113984068A (en) | Positioning method, positioning apparatus, and computer-readable storage medium | |
| TWI795885B (en) | Visual positioning method, device and computer-readable storage medium | |
| CN110390685B (en) | Feature point tracking method based on event camera | |
| Droeschel et al. | 3D body pose estimation using an adaptive person model for articulated ICP | |
| KR20210058686A (en) | Device and method of implementing simultaneous localization and mapping | |
| CN111415417A (en) | Mobile robot topology experience map construction method integrating sparse point cloud | |
| CN111998862A (en) | Dense binocular SLAM method based on BNN | |
| CN110749308B (en) | SLAM-oriented outdoor positioning method using consumer-grade GPS and 2.5D building models | |
| CN112967340A (en) | Simultaneous positioning and map construction method and device, electronic equipment and storage medium | |
| Mehralian et al. | EKFPnP: extended Kalman filter for camera pose estimation in a sequence of images | |
| CN113063412B (en) | Multi-robot cooperative positioning and mapping method based on reliability analysis | |
| US10977810B2 (en) | Camera motion estimation |
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 |