CN111192303B - Point cloud data processing method and device - Google Patents
Point cloud data processing method and device Download PDFInfo
- Publication number
- CN111192303B CN111192303B CN202010271385.0A CN202010271385A CN111192303B CN 111192303 B CN111192303 B CN 111192303B CN 202010271385 A CN202010271385 A CN 202010271385A CN 111192303 B CN111192303 B CN 111192303B
- Authority
- CN
- China
- Prior art keywords
- point
- cloud data
- point cloud
- data
- displacement
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The specification discloses a point cloud data processing method and device, which are used for compensating acquired cloud data of each point collected at historical time, so that the acquired cloud data of each point after compensation all correspond to the current time. Specifically, the compensation is performed based on a motion trajectory of an object in an environment corresponding to a point to which the point cloud data belongs, in a specified time period between a historical time when the point is acquired and a current time. Because the point to which the point cloud data belongs is generated by an object in the environment, the position change and/or posture change of the object in the environment in the specified time period can represent the position change of the point generated according to the object in the specified time period in the environment to a certain extent. Therefore, the point cloud data of the point is compensated according to the change condition of the object in the specified time period, and the point cloud data of the point obtained after compensation can be more fit with the actual condition of the current moment.
Description
Technical Field
The application relates to the technical field of unmanned driving, in particular to a point cloud data processing method and device.
Background
At present, the unmanned technology is an important component of the artificial intelligence technology, has increasingly prominent effects in social production and life, and becomes one of the main directions for guiding the development of traffic technology.
With the development of unmanned driving technology, methods for controlling intelligent vehicles (including unmanned vehicles and vehicles with driving assistance functions) to run are more mature. Generally, in the running process of the intelligent vehicle, data acquisition is carried out on each object in the environment through acquisition equipment such as radars and the like, so that the intelligent vehicle can sense the condition of the environment where the intelligent vehicle is located according to the acquired data. However, the radar mostly adopts a time-sharing scanning mode when acquiring data of an environment, so that the actual acquisition time of each acquired data in one frame is different. When the subsequent intelligent vehicle senses the environment according to the data acquired by the radar, the acquired data is inaccurate, so that information with larger error or even wrong error is generated inevitably, and a driving decision made by the intelligent vehicle is influenced, so that the driving safety is difficult to guarantee.
Disclosure of Invention
The embodiment of the specification provides a point cloud data processing method and a point cloud data processing device, which are used for partially solving the problems in the prior art.
The embodiment of the specification adopts the following technical scheme:
the present specification provides a point cloud data processing method, including:
acquiring point cloud data;
determining an object corresponding to each point in the point cloud data;
determining the motion trail of each object in the motion trails of the objects obtained in advance;
determining displacement data of the object in a specified time period according to the motion trail of the object, wherein the displacement data is used as displacement data of the point; the specified time period is a time period from the historical time of the point cloud data collected to the point to the current time;
and according to the determined displacement data of the point, compensating the acquired point cloud data of the point at the historical moment to obtain the point cloud data of the point at the current moment.
Optionally, the acquiring point cloud data specifically includes:
determining the time length for collecting one frame of point cloud data;
and acquiring point cloud data collected within the time length from the specified time according to each preset specified time.
Optionally, determining displacement data of the object in a specified time period according to the motion trajectory of the object specifically includes:
determining first position data of the object at the current moment according to the motion track of the object; and determining second position data of the object at the historical moment;
and determining displacement data of the object in a specified time period according to the difference between the first position data and the second position data.
Optionally, compensating the acquired point cloud data of the point at the historical time according to the determined displacement data of the point, specifically including:
determining the pose change of an acquisition device for acquiring the point cloud data of the point in the specified time period;
and compensating the acquired point cloud data of the point according to the displacement data of the point and the pose change of the acquisition equipment.
Optionally, compensating the acquired point cloud data of the point according to the displacement data of the point and the pose change of the acquisition device, specifically including:
establishing a pose transformation matrix according to the pose change of the acquisition equipment;
adopting the pose conversion matrix to compensate the acquired point cloud data of the point at the historical moment, and obtaining the point cloud data of the point at the historical moment as intermediate data under the condition that the pose of the acquisition equipment is changed;
and adjusting the intermediate data according to the displacement data of the point to obtain the point cloud data of the point at the current moment, wherein the point cloud data is used as the point cloud data of the point compensated at the current moment.
Optionally, compensating the acquired point cloud data of the point according to the displacement data of the point and the pose change of the acquisition device, specifically including:
according to the displacement data of the point, adjusting the acquired point cloud data of the point at the historical moment to obtain the point cloud data of the point at the current moment as intermediate data under the condition that the point has displacement corresponding to the displacement data;
establishing a pose transformation matrix according to the pose change of the acquisition equipment;
and compensating the intermediate data by adopting the pose conversion matrix to obtain point cloud data of the point compensated by the point at the current moment under the condition that the pose of the acquisition equipment is changed.
Optionally, compensating the acquired point cloud data of the point according to the displacement data of the point and the pose change of the acquisition device, specifically including:
converting the coordinates corresponding to the point cloud data of the point at the historical moment into a coordinate system taking the acquisition equipment as a reference to obtain the point cloud data of the point at the historical moment after coordinate conversion;
and compensating the point cloud data of the point at the historical moment after coordinate transformation according to the displacement data of the point and the pose change of the acquisition equipment.
The point cloud data processing apparatus provided by the present specification includes:
the acquisition module is used for acquiring point cloud data;
the object determining module is used for determining an object corresponding to each point in the point cloud data;
the motion track determining module is used for determining the motion track of each object in the motion tracks of the objects obtained in advance;
the displacement data determining module is used for determining displacement data of the object in a specified time period according to the motion track of the object, and the displacement data are used as displacement data of the point; the specified time period is a time period from the historical time of the point cloud data collected to the point to the current time;
and the compensation module is used for compensating the acquired point cloud data of the point at the historical moment according to the determined displacement data of the point to obtain the point cloud data of the point at the current moment.
The present specification provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements a point cloud data processing method as described above.
The unmanned equipment comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the method for processing the point cloud data.
The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects:
in an embodiment of the present specification, a method and an apparatus for processing point cloud data compensate acquired point cloud data collected at a historical time, so that the acquired compensated point cloud data corresponds to a current time. Specifically, the compensation is performed based on a motion trajectory of an object in an environment corresponding to a point to which the point cloud data belongs, in a specified time period between a historical time when the point is acquired and a current time. Since the point to which the point cloud data belongs is generated by an object in the environment, the position change and/or posture change of the object in the environment in the specified time period can be represented to a certain extent. Therefore, the point cloud data of the point is compensated according to the change condition of the object in the specified time period, and the point cloud data of the point obtained after compensation can be more fit with the actual condition of the current moment. Further, the method and apparatus of the present specification can obtain further effects when processing point cloud data generated from a dynamic object in an environment.
Drawings
The accompanying drawings, which are included to provide a further understanding of the specification and are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description serve to explain the specification and not to limit the specification in a non-limiting sense. In the drawings:
FIG. 1a is a process of acquiring point cloud data by an acquisition device;
FIG. 1b shows a point a in the point cloud dataiA relative relationship diagram of the historical time and the current time;
fig. 2 is a process of processing point cloud data according to an embodiment of the present disclosure;
fig. 3a is a process for acquiring point cloud data according to an embodiment of the present disclosure;
FIG. 3b is a point a in the point cloud datajA relative relationship diagram of the historical time and the current time;
FIG. 4 is a process for determining displacement data provided by embodiments of the present description;
fig. 5 is a process of compensating point cloud data according to an embodiment of the present disclosure;
fig. 6 is another process for compensating point cloud data provided by the embodiments of the present disclosure;
fig. 7 is a schematic structural diagram of a point cloud data processing apparatus provided in an embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of a portion of an unmanned aerial vehicle corresponding to fig. 2 provided in an embodiment of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the specification without making any creative effort belong to the protection scope of the specification.
Before describing the process in this specification, an existing point cloud data processing process is described.
In the scenario shown in fig. 1a, taking a laser radar whose scanning mode is a mechanical rotation type as an example, the laser radar (the center of a circle in fig. 1 a) rotates in a counterclockwise direction, and one frame of point cloud data is obtained every rotation (360 degrees). Taking the ith frame of point cloud data as an example, the ith frame of point cloud data includes a plurality of points, such as point a in fig. 1aiTo point fiThe time length (i.e. scanning period) required by the acquired ith frame of point cloud data of the laser radar is CiThe starting time of the scanning time is tiThe end time is ti’. In FIG. 1a, point aiThe line and point b with the laser radariThe included angle of the connecting line between the laser radar and the laser radar is an angle theta, and the time length required by the rotation angle theta of the laser radar is the acquisition point aiFrom the historical time to the collection point biThe time duration between historical times. As can be seen, in this scenario, point a is collectediTo point fiEach history time is different.
For the ith frame, the duration C of the frameiEnd time t ofi’And acquiring the collected point cloud data generated at the historical moment. As can be seen, point a is obtainediTo point fiAre the same.
At point aiFor example, point aiIn this specificationThe order relationship between the various moments involved in (1 b). On the time axis shown in FIG. 1b, point aiThe historical time and acquisition a ofiThere is a certain time difference between the time of the point cloud data.
The existing point cloud data processing method does not consider the historical time of actually acquiring the point cloud data of each point in the ith frame, directly takes the time of acquiring the point cloud data in the ith frame as the historical time of acquiring the point cloud data of each point in the ith frame, and processes the acquired point cloud data on the basis. If the point to which the point cloud data in the ith frame belongs corresponds to a dynamic object in the environment, the accuracy of the point cloud data processing result is seriously affected by the existing point cloud data processing method.
And, in the scenario shown in FIG. 1a, point e is actually capturediFrom the historical time of the point cloud data to the time of acquiring the point cloud data (instant length C)iEnd time t ofi’) The time required for the laser radar to rotate the angle is totally elapsed. And, in fact, if point eiThe corresponding object is a dynamic object at the acquisition point eiAt the point of time eiThe position change and/or posture change of the corresponding object relative to the historical moment in the actual environment, and the acquired point eiThe point cloud data of (a) cannot reflect the point eiThe actual position and/or posture of the corresponding object in the environment at the time of acquiring the point cloud data.
Further, a point a is collectediThe historical time of the point cloud data is earlier than the time of acquiring the point cloud data, so that the acquired point aiThe point cloud data of (a) is more likely to be inaccurate.
In view of the above, the present specification provides a point cloud data processing process to solve at least some problems in the point cloud data processing method in the prior art.
The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.
Fig. 2 is a point cloud data processing process provided in an embodiment of the present specification, which specifically includes the following steps:
s200: and acquiring point cloud data.
The point cloud data in this specification can be acquired by scanning each object in the environment with an acquisition device (e.g., a laser radar).
The collecting device for collecting point cloud data may be a collecting device provided on an intelligent vehicle. When the intelligent vehicle runs in the environment, the intelligent vehicle carries the acquisition equipment to move in the environment.
In an optional implementation scenario of this specification, as shown in fig. 3a, taking the jth frame of point cloud data acquired by the acquisition device as an example, the time for acquiring the point cloud data may be the aforementioned time duration CjEnd time t ofj’(ii) a Or the starting time t of collecting the j-th frame point cloud datajTo the end time tj’At a certain time or times therebetween; it may also be in chronological order at an end time tj’Followed by a certain moment or moments.
S202: and determining objects corresponding to each point in the point cloud data in the environment.
In an optional implementation scenario of the present specification, an object corresponding to at least a part of points in the point cloud data in an environment may be determined according to the acquired point cloud data.
For example, a map may be constructed from the acquired point cloud data. The obtained map based on the point cloud data may be a RangeImage, Elevation Image, or the like. Then, in the figure, objects in the environment are identified. Then, for at least part of points in the point cloud data, an object corresponding to the point is determined in the identified objects.
In another optional implementation scenario of the present specification, objects corresponding to at least some points in the point cloud data in the environment may be determined according to the acquired data in other forms and the acquired point cloud data.
For example, an image of the environment may be captured, and an image that temporally matches the acquired point cloud data may be determined as a target image of the acquired point cloud data among the captured images. Then, according to the characteristics of each pixel of the target image, the target image is processed to identify each object in the target image. And determining corresponding pixels of the points in the target image aiming at least part of the points in the acquired point cloud data. And taking the object corresponding to the pixel in the target image as the object corresponding to the point in the environment.
S204: and determining the motion trail of each object in the pre-obtained motion trail of each object in the environment.
In the present specification, the term "obtained in advance" is a concept having a relative meaning. All times before this step may be the time at which this "pre-acquisition" is achieved. That is, the timing of realizing the "obtaining in advance" in the present specification can be understood in various ways.
For example, the time of "obtaining in advance" may occur before the historical time of acquiring the point cloud data of a certain point, and then the motion trajectory of the object corresponding to the point obtained in advance may be predicted according to the environmental data acquired before the historical time. At this time, the environment data may be at least one of point cloud data acquired before the historical time, acquired image data, and data acquired by the detection device.
For another example, the time of "obtaining in advance" may occur before the time of acquiring the point cloud data, and the motion trajectory of the object corresponding to the point obtained in advance may be obtained according to the environmental data acquired before the time of acquiring the point cloud data. At this time, if the environmental data is point cloud data obtained before the time of acquiring the point cloud data, the motion trajectory of the object may be a predicted trajectory. If the environment data is at least one of image data acquired before the point cloud data is acquired and data acquired by the detection device, the motion trajectory of the object may be a trajectory obtained based on an actual position state and a motion state of the object.
As another example, the "pre-obtained" time may occur after the time point at which the point cloud data is acquired, but before this step. At this time, the motion trajectory may be obtained from each environment data including the point cloud data acquired in step S200.
S206: and determining displacement data of the object in a specified time period according to the motion trail of the object, wherein the displacement data is used as the displacement data of the point. The specified time period is a time period from the historical time of the point cloud data collected to the point to the current time.
Because the point to which the point cloud data belongs is generated according to the object in the environment, the position change and/or posture change of the object in the environment in the specified time period can be represented to a certain extent according to the position change of the point generated according to the object in the specified time period. Since the historical time of the point cloud data of each point is different, the designated time periods of each point are also different.
Alternatively, the motion trajectory of the object in this specification is only obtained by predicting the position of the object at each future time, and the object may be abstracted as a point. The displacement data of the point obtained by the displacement data of the object can reflect at least the position change of the point caused by the movement of the object in the specified time period.
The "future time" herein is a concept of time with respect to the aforementioned historical time. In FIG. 3b, point a is collected on the time axisjThe time after the historical time of the point cloud data may be the point ajFuture time of the historical time.
Alternatively, the motion trajectory of the object in this specification is obtained by predicting/detecting the position and posture (hereinafter, referred to as pose) of the object at each future time. The displacement data of the point obtained by the displacement data of the object can also reflect the position change of the point caused by the posture change of the object in a specified time period.
In this specification, "current" is a concept having a relative meaning with respect to "history". The "current time" may be the aforementioned time at which the point cloud data is acquired or may be a time after the time at which the point cloud data is acquired. E.g. point ajThe historical time of day and the current time of day in chronological order, as shown in fig. 3 b. For convenience of description, the following description will be given by taking the current time as the time for acquiring the point cloud data as an example.
S208: and according to the determined displacement data of the point, compensating the acquired point cloud data of the point at the historical moment to obtain the point cloud data of the point at the current moment.
As can be seen from the foregoing, the displacement data of the point can reflect at least the position change of the point caused by the movement of the object in the specified time period. And compensating the point cloud data of the point at the historical moment according to the displacement data, so that the point cloud data of the point corresponding to the historical moment can be compensated to the point cloud data corresponding to the current moment, and the compensated point cloud data of the point can at least reflect the position condition of the point at the current moment.
In the scenario of a lidar in which the acquisition device is mechanically rotating, as shown in fig. 3a, point a is acquiredjTo point fjThe historical moments are different from each other, through the process in the specification, the moments corresponding to the collected point cloud data can be processed to the same moment, the difference of the point cloud data collected at different moments in one frame of point cloud data in the time dimension is reduced, and the uniformity of the point cloud data obtained through processing in the time dimension is further improved.
In addition, it should be noted that suitable scenarios for the process in this specification include, but are not limited to, the aforementioned scenarios suitable for time-sharing scanning and collecting point cloud data by a mechanically rotating lidar. That is, the process in the present specification is also applicable to other scenes in which the past time and the current time of point cloud data are not the same, for example, scenes in which point cloud data are collected by Flash (Flash) scanning.
In a scenario in which the flash scanning lidar is used as the acquisition device, the time at which the echo generated by the object is received corresponds to the aforementioned historical time. Because the distances from all objects in the environment to the position where the flash scanning type laser radar is located are different, the historical time of all points in the received point cloud data is different. After point cloud data generated at each historical time is received, each point cloud data is obtained as one frame. Because a certain time length exists between each historical time and the time of acquiring the point cloud data, the process in the description can also achieve the technical effect of compensating the point cloud data acquired at the historical time to the current time when being applied to processing the point cloud data acquired by flash scanning.
The point cloud data processing process described in this specification will be described in detail below.
In an actual scene, compared with image data, the point cloud data can provide information of each object in the depth direction in the environment, namely the point cloud data provides more abundant dimensionality for the information provided by a user. Particularly in the field of unmanned driving technology, the intelligent vehicle needs to make decisions according to various data based on the environment, and the point cloud data plays an irreplaceable role in the field due to the specificity of the point cloud data on the data dimension.
However, the intelligent vehicle has certain real-time and continuous requirements on data in the decision making process. Due to the limitation of factors such as the frame rate of the acquisition equipment for acquiring the point cloud data, the problem that the acquired point cloud data cannot meet the use requirement of the intelligent vehicle in the aspects of real-time performance and continuity is caused.
Therefore, in an optional embodiment of the present specification, the limitation of the point cloud data in terms of real-time performance and continuity is improved by increasing the frequency of acquiring the point cloud data.
Specifically, as shown in fig. 3a, a time duration C for acquiring one frame (for example, jth frame) of point cloud data may be first determinedj. Then, according to each predetermined time, e.g. time tj 0To time tj 5And acquiring point cloud data collected within the time length from the specified time. At time tj 0The duration of each historical moment corresponding to the acquired one-frame point cloud data is time tj 0To time tj+1 0The time duration in between.
It can be seen from the figureIn the scene shown in fig. 3a, since the point cloud data acquired each time is a complete point cloud data acquired within the time period, the area s in fig. 3a is0Respectively at a time tj 0Starting duration up to from time tj 5The start time lengths are each acquired once.
Now with the region s0Point f injAt time tj 0Corresponding time duration and time tj 5The corresponding time lengths are each acquired once for example. Collecting a point fjFrom the historical time to the time tj 0In a first designated time period between the end moments of the corresponding durations, the laser radar rotates by an angle; collecting a point fjFrom the historical time to the time tj 5During a second specified time period between the end times of the corresponding durations, the lidar is rotated by an angle β.
Point f is pointed out through the process in the specificationjRespectively at time t during point cloud data compensationj 0Corresponding duration and time tj 5The corresponding time lengths are each compensated once. Specifically, at time tj 0Corresponding time length to point fjWhen the point cloud data is compensated, the point f in the first appointed time period is usedjIs compensated for. At time tj 5To point fjWhen the point cloud data is compensated, the point f in the second designated time period is usedjIs compensated for. At point fjWhen the corresponding object is a dynamic object, the point f in the first designated time periodjThe corresponding displacement of the object and the point f in the second designated time periodjThe displacement amounts of the corresponding objects are different.
It can be seen that, in the process of this specification, although a phenomenon of repeatedly acquiring point cloud data to a certain extent is caused in order to increase the frequency of acquiring data, the repeatedly acquired point cloud data is compensated to a different extent at different specified times, so that the compensated point cloud data obtained by the repeatedly acquired point cloud data through the compensation to a different extent can embody the position change of the point to which the point cloud data belongs over time. Further, the point cloud data having the "static" attribute can be provided with the "dynamic" attribute by the compensation based on the motion state of the object in the environment in the present specification.
Since the point cloud data is obtained from an object in the environment, the position change of the point to which the point cloud data generated by the object belongs can be represented to a large extent according to the displacement data obtained from the position change/pose change of the object occurring within a specified time period. As shown in fig. 4, the process of obtaining displacement data of a point to which point cloud data generated by an object belongs according to the object displacement data may be as follows:
s400: and determining first position data of the object at the current moment according to the motion track of the object.
As can be seen from the foregoing, the data source for determining the motion trajectory of the object in the present specification may be various, and the meaning of the current time is also broad.
In a case where the time point at which the point cloud data is acquired is the current time point, the motion trajectory may be actually detected by the detection device or identified from an image acquired by the image acquisition device, and then the first position data may be actual data of the object. Furthermore, the motion trajectory may be predicted based on each data in the history, and the first position data obtained from the motion trajectory may be predicted data for the object.
S402: second position data of the object at the historical time is determined.
Similarly, the second position data can also be obtained from the motion trajectory of the object. Whether the second position data is the actual data of the object also depends on the source of the motion trajectory of the object, which is not described herein again. Optionally, the second position data is actual position data of the object acquired by the detection device at the historical time.
It should be noted that the information included in the motion trajectory for the object includes not only the position information of the object in the environment at the future time, but also the posture information of the object in the environment at the future time. The first position data and the second position data in this specification may be used to characterize position information or pose information of the object.
The execution order of steps S400 and S402 may be adjusted according to the actual scene.
S404: and determining the displacement data of the object in a specified time period according to the difference between the first position data and the second position data, and taking the displacement data as the displacement data of the point.
As can be seen from the above, the displacement data obtained from the first position data and the second position data in this step can be used to represent the amount of position change or the amount of pose change of the object in the specified time period.
The process in the specification can determine the degree of error of the point cloud data caused by the change of the position or the pose of an object corresponding to each point in the point cloud data in a specified time period, and compensate the point cloud data according to the degree of the error caused by the motion of the object, so that the inaccuracy of the point cloud data caused by the motion of the object is greatly reduced.
On the basis, the process in the specification can also determine the degree of error of the point cloud data caused by the position or pose change of the acquisition equipment in a specified time period, and compensate the point cloud data according to the degree of error caused by the motion of the acquisition equipment.
Specifically, the process of compensation may be: and determining the pose change of the acquisition equipment for acquiring the point cloud data of the point in the specified time period. And then, compensating the acquired point cloud data of the point according to the displacement data of the point and the pose change of the acquisition equipment.
In a scene in which point cloud data of an environment is acquired by an acquisition device arranged on an intelligent vehicle, the intelligent vehicle carries the acquisition device to move in the environment, and the pose change of the acquisition device can be caused by the movement of the intelligent vehicle. In addition, in some implementation scenarios, the acquisition device may also adjust its own acquisition angle in the process of acquiring the point cloud data, and the pose change of the acquisition device may also be caused by its own adjustment. Alternatively, the pose of the acquisition device may be represented by six degrees of freedom of the acquisition device.
Therefore, through the process in the specification, the point cloud data can be compensated according to the error caused by the motion of the object corresponding to the point cloud data; and the point cloud data can be compensated according to errors caused by the motion of the acquisition equipment. The 'dynamic' attribute of the compensated point cloud data obtained through the process in the specification is richer, and the compensated point cloud data can be more accurate and more fit with the actual situation corresponding to the current moment.
Optionally, the process of "compensating the acquired point cloud data of the point according to the displacement data of the point and the pose change of the acquisition device" may include two sub-steps, that is: and compensating the acquired point cloud data of the point according to the displacement data of the point, and compensating the acquired point cloud data of the point according to the pose change of the acquisition equipment. The order of execution of the two substeps may be adjusted according to the actual scenario. Hereinafter, the order of execution of the two substeps will be described separately in two cases.
(1) And compensating according to the displacement data of the point, and then compensating according to the pose change of the acquisition equipment.
As shown in fig. 5, the process of "performing compensation according to the displacement data of the point and then performing compensation according to the pose change of the acquisition device" may include the following steps:
s500: and adjusting the acquired point cloud data of the point at the historical moment according to the displacement data of the point to obtain the point cloud data of the point at the current moment as first intermediate data under the condition that the point has displacement corresponding to the displacement data.
In an optional scenario of this specification, the displacement data of the point and the position data corresponding to the point cloud data of the point may be summed to compensate the position change of the point caused by the motion of the object in the specified time period to the point cloud data of the point, so as to obtain the first intermediate data of the point at the current time.
Point a in the previous embodimentjFor example, the positions of the points in the point cloud data in the environment are referenced to a cartesian three-dimensional coordinate system. If the collected j frame point cloud data is the point ajThe homogeneous coordinate of the position corresponding to the point cloud data is Pa=（xa、ya、za1). At the point ajWithin a corresponding specified time period, the point ajHas a displacement data of Fa=（Δxa、Δya、Δza) Then the obtained point ajThe corresponding first intermediate data is (P)a+Fa）=P’a1=（xa+Δxa、ya+Δya、za+Δza、1）。
The possibility of large displacement of objects in the environment in the vertical direction is small; moreover, the position of the object in the vertical direction is mostly dependent on the road environment, and the benefit of compensating for the displacement in the vertical direction is small, the displacement data corresponding to the part in the vertical direction (for example, the point a) can be correctedjCorresponding Δ za) Neglected.
Further, since the compensation difficulty of the dimension of the reflection intensity in the point cloud data is large, the calculation for the dimension can be omitted in the calculation process. Still at point ajFor example, the point a is obtainedjThe corresponding first intermediate data is P'a1=（xa+Δxa、ya+Δya）。
S502: and establishing a pose transformation matrix according to the pose change of the acquisition equipment.
The collecting device is at this point ajThe corresponding pose change in the designated time period can be realized by the position change matrix delta Ta=（Δxt、Δyt、Δzt) And attitude variance matrix Δ Ra 
And (5) characterizing.
The position variation matrix Δ TaAnd attitude variance matrix Δ RaThe data acquisition method can be obtained according to the data sensed by the sensing equipment of the intelligent vehicle to which the acquisition equipment belongs. The sensing device may be at least one of an inertial navigation system, a vehicle-mounted accelerometer, a gyroscope.
The execution order of steps S500 and S502 may be adjusted according to the actual usage scenario.
S504: and compensating the first intermediate data by adopting the pose conversion matrix to obtain point cloud data of the point compensated by the point at the current moment under the condition that the pose of the acquisition equipment is changed.
To the point a according to the position and posture conversion matrixjOf'a1Compensation is carried out to obtain a point ajThe point cloud data compensated at the current time may be P "a1=
. It can be seen that the step can compensate the position change of the point caused by the motion of the acquisition equipment in the specified time period into the point cloud data of the point
(2) The method comprises the steps of firstly compensating according to the pose change of the acquisition equipment, and then compensating according to the displacement data of the point.
As shown in fig. 6, the process of "performing compensation according to the pose change of the acquisition device and then performing compensation according to the displacement data of the point" may include the following steps:
s600: and establishing a pose transformation matrix according to the pose change of the acquisition equipment.
The pose transformation matrix in this step is the same as the pose transformation matrix in step S502, and is not described herein again.
S602: and compensating the acquired point cloud data of the point at the historical moment by adopting the pose conversion matrix to obtain the point cloud data of the point at the historical moment as second intermediate data under the condition that the pose of the acquisition equipment is changed.
Still at the point a described abovejFor example, based on a similar idea as step S504, point ajThe homogeneous coordinate of the position corresponding to the point cloud data is Pa=（xa、ya、zaAnd 1) of the first intermediate data P 'obtained in this step'a2=
。
S604: and adjusting the second intermediate data according to the displacement data of the point to obtain the point cloud data of the point at the current moment, wherein the point cloud data is used as the point cloud data of the point compensated at the current moment.
Based on similar idea as step S500, the second intermediate data P'a2The point cloud data of the point compensated at the current moment can be obtained as P "a2= P’a2+Fa。
Alternatively, this step may be preceded by the aforementioned pose transformation matrix for the point ajDisplacement data F ofaCompensating to obtain the compensated point ajDisplacement data F'a. Then by second intermediate data P'a2The point cloud data of the point compensated at the current moment can be obtained as P "a2= P’a2+ F’a。
Point cloud data for other points as shown in fig. 3a, point a may also be usedjWhen the point cloud data is compensated, the same or similar steps are used for compensation.
At this point, compensation for the point cloud data is completed. The compensated point cloud data fully refers to the motion state of the object in the environment and the motion state of the acquisition equipment, and can reflect each actual information of the environment at the current moment to a greater extent.
Further, in order to facilitate data processing, the point cloud data and the pose data of the acquisition equipment can be mapped to the same coordinate system, and then the point cloud data after mapping is compensated.
Specifically, the process of performing coordinate transformation by mapping may be: and converting the coordinates corresponding to the point cloud data of the point at the historical moment into a coordinate system taking the acquisition equipment as a reference to obtain the point cloud data of the point at the historical moment after coordinate conversion. And then, compensating the point cloud data of the point at the historical moment after coordinate transformation according to the displacement data of the point and the pose change of the acquisition equipment.
In the scene of "performing compensation according to the displacement data of the point and then performing compensation according to the pose change of the acquisition device", in step S504, the first intermediate data may be subjected to coordinate transformation, and the first intermediate data after the coordinate transformation may be further subjected to compensation.
The process may be: and converting the coordinate corresponding to the first intermediate data of the point at the current moment into a coordinate system taking the acquisition equipment as a reference to obtain the first intermediate of the point after the coordinate conversion at the current moment. Specifically, a translation variation matrix H and a rotation variation matrix G may be collected, and the first intermediate data P'a1Coordinate conversion is carried out, and the obtained first intermediate data after coordinate conversion is
=
P’a1。
And then, compensating the first intermediate data after the coordinate conversion by adopting the pose conversion matrix to obtain point cloud data of the point compensated by the acquisition equipment at the current moment under the condition of the pose change. The point cloud data of the point compensated at the current time can be P'a1=
。
In the aforementioned scenario of "performing compensation according to the pose change of the acquisition device and then performing compensation according to the displacement data of the point", in step S602, the second intermediate data may be subjected to coordinate transformation, and further the second intermediate data after the coordinate transformation may be subjected to compensation.
The process may be: and converting the coordinates corresponding to the point cloud data of the point at the historical time into a coordinate system taking the acquisition equipment as a reference to obtain the point cloud data of the point after the coordinate conversion at the historical time.
Specifically, a translation variation matrix H and a rotation variation matrix G may be collected, and the second intermediate data P'a2Coordinate conversion is carried out, and the obtained second intermediate data after coordinate conversion is
=
。
And then, compensating the point cloud data of the point after coordinate transformation by adopting the pose transformation matrix. The point cloud data of the point compensated at the current time can be P'a2=
+ F’a。
The point cloud data processing process provided by the specification can be particularly applied to the field of distribution by using an unmanned vehicle, for example, in the distribution scene of express delivery, takeaway and the like by using the unmanned vehicle. Specifically, in the above-described scenario, delivery may be performed using an autonomous vehicle fleet configured with a plurality of unmanned vehicles.
Based on the same idea, the embodiments of the present specification further provide a point cloud data processing apparatus corresponding to the process shown in fig. 2, and the point cloud data processing apparatus is shown in fig. 7.
Fig. 7 is a schematic structural diagram of a point cloud data processing apparatus provided in an embodiment of the present specification, where the point cloud data processing apparatus may include:
an obtaining module 700, configured to obtain point cloud data;
an object determining module 702, configured to determine, for each point in the point cloud data, an object corresponding to the point in the environment;
a motion trajectory determination module 704, configured to determine a motion trajectory of each object from motion trajectories of the objects obtained in advance;
a displacement data determining module 706, configured to determine, according to the motion trajectory of the object, displacement data of the object in a specified time period as displacement data of the point; the specified time period is a time period from the historical time of the point cloud data collected to the point to the current time;
and the compensation module 708 is configured to compensate the acquired point cloud data of the point at the historical time according to the determined displacement data of the point, so as to obtain the point cloud data of the point at the current time.
The obtaining module 700, the object determining module 702, the motion trajectory determining module 704, the displacement data determining module 706, and the compensating module 708 are electrically connected in sequence. Optionally, the acquisition module 700 is electrically connected to the compensation module 708.
Optionally, the acquisition module 700 may include an electrically connected duration determination sub-module 7000 and a point cloud data acquisition sub-module 7002.
And the time length determining submodule 7000 is used for determining the time length for acquiring one frame of point cloud data.
And the point cloud data acquisition submodule 7002 is configured to acquire, according to each preset specified time, point cloud data acquired within the time period from the specified time.
Alternatively, the displacement data determination module 706 may include: a first position data determination sub-module 7060, a second position data determination sub-module 7062 and a displacement data determination sub-module 7064. The first position data determining submodule 7060 and the second position data determining submodule 7062 are electrically connected to the displacement data determining submodule 7064, respectively.
The first position data determining sub-module 7060 is configured to determine, according to the motion trajectory of the object, first position data of the object at the current time.
A second position data determining submodule 7062 is configured to determine second position data of the object at the historical time.
And the displacement data determining submodule 7064 is configured to determine, according to a difference between the first position data and the second position data, displacement data of the object in a specified time period.
Optionally, the compensation module 708 may include electrically connected: a collection device pose change determination sub-module 7080 and a first compensation sub-module 7082.
And the acquisition equipment pose change determining sub-module 7080 is configured to determine a pose change of the acquisition equipment that acquires the point cloud data of the point within the specified time period.
And the first compensation submodule 7082 is configured to compensate the acquired point cloud data of the point according to the displacement data of the point and the pose change of the acquisition device.
Optionally, the first compensation sub-module 7082 may include: a pose transformation matrix establishing unit 70822, a first intermediate data determining unit 70820 and a compensating unit 70824. Wherein, the pose transformation matrix establishing unit 70822 and the first intermediate data determining unit 70820 are respectively electrically connected with the compensating unit 70824.
A first intermediate data determining unit 70820, configured to adjust the acquired point cloud data of the point at the historical time according to the displacement data of the point, so as to obtain the point cloud data of the point at the current time as first intermediate data under the condition that the point has a displacement corresponding to the displacement data.
A pose transformation matrix establishing unit 70822, configured to establish a pose transformation matrix according to the pose change of the acquisition device.
A compensating unit 70824, configured to compensate the first intermediate data by using the pose transformation matrix, so as to obtain point cloud data of the point compensated by the point at the current time under the condition that the pose of the acquisition device changes.
Optionally, the compensation module 708 may include electrically connected: and the acquisition equipment pose change determining submodule and the second compensation submodule.
And the acquisition equipment pose change determining submodule is used for determining the pose change of the acquisition equipment for acquiring the point cloud data of the point in the specified time period.
And the second compensation submodule is used for compensating the acquired point cloud data of the point according to the displacement data of the point and the pose change of the acquisition equipment.
The second compensation sub-module may include: the pose transformation matrix establishing unit, the second intermediate data determining unit and the compensating unit. The pose transformation matrix establishing unit and the second intermediate data determining unit are respectively and electrically connected with the compensating unit.
And the pose transformation matrix establishing unit is used for establishing a pose transformation matrix according to the pose change of the acquisition equipment.
A second intermediate data determining unit, configured to compensate the acquired point cloud data of the point at the historical time by using the pose transformation matrix to obtain the point cloud data of the point at the historical time as second intermediate data under the condition that the pose of the acquisition device changes
And the compensation unit is used for adjusting the second intermediate data according to the displacement data of the point to obtain point cloud data of the point at the current moment, and the point cloud data is used as the point cloud data of the point compensated at the current moment.
Optionally, the compensation module may further include: coordinate conversion submodule 7084.
The coordinate conversion sub-module 7084 may be configured to convert the coordinates corresponding to the point cloud data of the point at the historical time into a coordinate system with reference to the collecting apparatus, so as to obtain the point cloud data of the point at the historical time after coordinate conversion. And compensating the point cloud data of the point at the historical moment after coordinate transformation according to the displacement data of the point and the pose change of the acquisition equipment.
Embodiments of the present specification further provide a computer-readable storage medium, where the storage medium stores a computer program, and the computer program is operable to execute the point cloud data processing process provided in fig. 2.
The embodiment of the specification also provides a part of structure schematic structure diagram of the unmanned equipment shown in FIG. 8. As shown in fig. 8, at the hardware level, the drone includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, although it may also include hardware required for other services. The processor reads a corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to implement the point cloud data processing process described above with reference to fig. 2. Of course, besides the software implementation, the present specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.
In the 90 th generation of 20 th century, it is obvious that improvements in Hardware (for example, improvements in Circuit structures such as diodes, transistors and switches) or software (for improvement in method flow) can be distinguished for a technical improvement, however, as technology develops, many of the improvements in method flow today can be regarded as direct improvements in Hardware Circuit structures, designers almost all obtain corresponding Hardware Circuit structures by Programming the improved method flow into Hardware circuits, and therefore, it cannot be said that an improvement in method flow cannot be realized by Hardware entity modules, for example, Programmable logic devices (Programmable logic devices L organic devices, P L D) (for example, Field Programmable Gate Arrays (FPGAs) are integrated circuits whose logic functions are determined by user Programming of devices), and a digital system is "integrated" on a P L D "by self Programming of designers without requiring many kinds of integrated circuits manufactured and manufactured by special chip manufacturers to design and manufacture, and only a Hardware software is written in Hardware programs such as Hardware programs, software programs, such as Hardware programs, software, Hardware programs, software programs, Hardware programs, software, Hardware programs, software, Hardware programs, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software.
A controller may be implemented in any suitable manner, e.g., in the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, Application Specific Integrated Circuits (ASICs), programmable logic controllers (PLC's) and embedded microcontrollers, examples of which include, but are not limited to, microcontrollers 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone L abs C8051F320, which may also be implemented as part of the control logic of a memory.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.
Claims (10)
1. A point cloud data processing method, characterized in that the method comprises:
acquiring point cloud data;
determining an object corresponding to each point in the point cloud data;
determining the motion trail of each object in the motion trails of the objects obtained in advance;
determining displacement data of the object in a specified time period according to the motion trail of the object, wherein the displacement data is used as displacement data of the point; the specified time period is a time period from the historical time of the point cloud data collected to the point to the current time;
and according to the determined displacement data of the point and the pose change of the acquisition equipment for acquiring the point cloud data, compensating the acquired point cloud data of the point at the historical moment to obtain the point cloud data of the point at the current moment.
2. The method of claim 1, wherein acquiring point cloud data specifically comprises:
determining the time length for collecting one frame of point cloud data;
and acquiring point cloud data collected within the time length from the specified time according to each preset specified time.
3. The method according to claim 1 or 2, wherein determining displacement data of the object within a specified time period according to the motion trajectory of the object specifically comprises:
determining first position data of the object at the current moment according to the motion track of the object; and determining second position data of the object at the historical moment;
and determining displacement data of the object in a specified time period according to the difference between the first position data and the second position data.
4. The method of claim 3, wherein compensating the acquired point cloud data of the point at the historical time according to the determined displacement data of the point and the pose change of the acquisition device acquiring the point cloud data comprises:
determining the pose change of an acquisition device for acquiring the point cloud data of the point in the specified time period;
and compensating the acquired point cloud data of the point according to the displacement data of the point and the pose change of the acquisition equipment.
5. The method of claim 4, wherein compensating the acquired point cloud data of the point according to the displacement data of the point and the pose change of the acquisition device comprises:
establishing a pose transformation matrix according to the pose change of the acquisition equipment;
adopting the pose conversion matrix to compensate the acquired point cloud data of the point at the historical moment, and obtaining the point cloud data of the point at the historical moment as intermediate data under the condition that the pose of the acquisition equipment is changed;
and adjusting the intermediate data according to the displacement data of the point to obtain the point cloud data of the point at the current moment, wherein the point cloud data is used as the point cloud data of the point compensated at the current moment.
6. The method of claim 4, wherein compensating the acquired point cloud data of the point according to the displacement data of the point and the pose change of the acquisition device comprises:
according to the displacement data of the point, adjusting the acquired point cloud data of the point at the historical moment to obtain the point cloud data of the point at the current moment as intermediate data under the condition that the point has displacement corresponding to the displacement data;
establishing a pose transformation matrix according to the pose change of the acquisition equipment;
and compensating the intermediate data by adopting the pose conversion matrix to obtain point cloud data of the point compensated by the point at the current moment under the condition that the pose of the acquisition equipment is changed.
7. The method of claim 4, wherein compensating the acquired point cloud data of the point according to the displacement data of the point and the pose change of the acquisition device comprises:
converting the coordinates corresponding to the point cloud data of the point at the historical moment into a coordinate system taking the acquisition equipment as a reference to obtain the point cloud data of the point at the historical moment after coordinate conversion;
and compensating the point cloud data of the point at the historical moment after coordinate transformation according to the displacement data of the point and the pose change of the acquisition equipment.
8. A point cloud data processing apparatus, comprising:
the acquisition module is used for acquiring point cloud data;
the object determining module is used for determining an object corresponding to each point in the point cloud data;
the motion track determining module is used for determining the motion track of each object in the motion tracks of the objects obtained in advance;
the displacement data determining module is used for determining displacement data of the object in a specified time period according to the motion track of the object, and the displacement data are used as displacement data of the point; the specified time period is a time period from the historical time of the point cloud data collected to the point to the current time;
and the compensation module is used for compensating the acquired point cloud data of the point at the historical moment according to the determined displacement data of the point and the pose change of the acquisition equipment for acquiring the point cloud data to obtain the point cloud data of the point at the current moment.
9. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1-7.
10. An unmanned aerial device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010271385.0A CN111192303B (en) | 2020-04-09 | 2020-04-09 | Point cloud data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010271385.0A CN111192303B (en) | 2020-04-09 | 2020-04-09 | Point cloud data processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111192303A CN111192303A (en) | 2020-05-22 |
| CN111192303B true CN111192303B (en) | 2020-08-07 |
Family
ID=70710956
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010271385.0A Active CN111192303B (en) | 2020-04-09 | 2020-04-09 | Point cloud data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111192303B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112329547A (en) * | 2020-10-15 | 2021-02-05 | 北京三快在线科技有限公司 | Data processing method and device |
| CN112819861B (en) * | 2021-02-26 | 2024-06-04 | 广州小马慧行科技有限公司 | Point cloud motion compensation method, device and computer readable storage medium |
| CN113763560B (en) * | 2021-08-02 | 2024-02-09 | 纵目科技（上海）股份有限公司 | Method, system, equipment and computer readable storage medium for generating point cloud data |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014202258A1 (en) * | 2013-06-21 | 2014-12-24 | National University Of Ireland, Maynooth | A method for mapping an environment |
| CN107817503B (en) * | 2016-09-14 | 2018-12-21 | 北京百度网讯科技有限公司 | Motion compensation process and device applied to laser point cloud data |
| CN109613543B (en) * | 2018-12-06 | 2020-09-25 | 深圳前海达闼云端智能科技有限公司 | Method and device for correcting laser point cloud data, storage medium and electronic equipment |
| CN110243358B (en) * | 2019-04-29 | 2023-01-03 | 武汉理工大学 | Multi-source fusion unmanned vehicle indoor and outdoor positioning method and system |
| CN110942477B (en) * | 2019-11-21 | 2021-11-19 | 大连理工大学 | Method for depth map fusion by using binocular camera and laser radar |
-
2020
- 2020-04-09 CN CN202010271385.0A patent/CN111192303B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111192303A (en) | 2020-05-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111192303B (en) | Point cloud data processing method and device | |
| US20220371602A1 (en) | Vehicle positioning method, apparatus, and controller, intelligent vehicle, and system | |
| CN111522026B (en) | Data fusion method and device | |
| CN111077555B (en) | Positioning method and device | |
| JP2018526641A (en) | System and method for laser depth map sampling | |
| JP2021140822A (en) | Vehicle control method, vehicle control device, and vehicle | |
| CN111238450B (en) | Visual positioning method and device | |
| CN111127551B (en) | Target detection method and device | |
| CN111288971B (en) | Visual positioning method and device | |
| CN111126362B (en) | Method and device for predicting obstacle track | |
| CN117218628A (en) | Multi-target detection method, system and server | |
| CN111798489B (en) | Feature point tracking method, device, medium and unmanned equipment | |
| JP6815935B2 (en) | Position estimator | |
| CN113643321A (en) | Sensor data acquisition method and device for unmanned equipment | |
| CN115979262A (en) | Aircraft positioning method, device, equipment and storage medium | |
| CN116164763A (en) | Target course angle determining method and device, electronic equipment and storage medium | |
| CN112393723B (en) | Positioning method, positioning device, medium and unmanned equipment | |
| CN116558545A (en) | Calibration method and device for sensor data | |
| CN115014332A (en) | Laser SLAM mapping method and device, electronic equipment and computer readable storage medium | |
| CN117095371A (en) | Target detection method and detection device | |
| CN113554711B (en) | Camera online calibration method and device, computer equipment and storage medium | |
| CN110244710B (en) | Automatic tracing method, device, storage medium and electronic equipment | |
| CN112556702A (en) | Height correction method for vehicle moving track and related device | |
| CN112712561A (en) | Picture construction method and device, storage medium and electronic equipment | |
| CN114173058B (en) | Video image stabilization processing method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |