CN114185476A - Stereo frame interaction method and system - Google Patents

Stereo frame interaction method and system Download PDF

Info

Publication number
CN114185476A
CN114185476A CN202111366127.1A CN202111366127A CN114185476A CN 114185476 A CN114185476 A CN 114185476A CN 202111366127 A CN202111366127 A CN 202111366127A CN 114185476 A CN114185476 A CN 114185476A
Authority
CN
China
Prior art keywords
vertex
coordinate
frame
dimensional
mouse button
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
Application number
CN202111366127.1A
Other languages
Chinese (zh)
Inventor
祁智恒
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Lumi Technology Jiangsu Co ltd
Original Assignee
Lumi Technology Jiangsu Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Lumi Technology Jiangsu Co ltd filed Critical Lumi Technology Jiangsu Co ltd
Priority to CN202111366127.1A priority Critical patent/CN114185476A/en
Publication of CN114185476A publication Critical patent/CN114185476A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
    • G06F3/0486—Drag-and-drop
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/06—Topological mapping of higher dimensional structures onto lower dimensional surfaces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10032—Satellite or aerial image; Remote sensing
    • G06T2207/10044—Radar image
    • 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
    • G06T2207/30204—Marker

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Processing Or Creating Images (AREA)

Abstract

The invention provides a three-dimensional frame interaction method and system, and relates to the technical field of data annotation. The stereo frame interaction method comprises the following steps: pressing a left mouse button, dragging and lifting the left mouse button, wherein the pressed point is a starting first vertex, and the lifted point is an ending third vertex of the starting vertex; moving the mouse to search for a seventh vertex, and clicking again after the position of the seventh vertex is determined to obtain the seventh vertex; and automatically calculating and filling the rest vertexes of the three-dimensional frame to generate a cuboid three-dimensional frame. The stereo frame can be constructed and the position, the size and the direction of the stereo frame can be adjusted. In addition, the invention also provides a stereo frame interaction system, which comprises: the device comprises a reference plane determining module, an extension plane determining module and a three-dimensional frame generating module.

Description

Stereo frame interaction method and system
Technical Field
The invention relates to the technical field of data annotation, in particular to a three-dimensional frame interaction method and system.
Background
Point cloud annotation is a fundamental and important topic in three-dimensional computer vision. The method is widely applied to three-dimensional reconstruction, instant positioning and mapping, automatic driving and the like. However, there are many obstacles in practical use. Scholars have done a lot of work on obstacles such as point cloud sparse change, occlusion and partial overlap.
With the continuous development of computer networks, artificial intelligence related technologies are becoming more common in daily life. For example, in many living scenarios, machine learning in artificial intelligence is involved, and the machine learning can be understood as training a model, and the training of the model requires that sample data for training the model be acquired first.
The position detection model can be trained by adopting sample data labeled in a two-dimensional-three-dimensional correlation manner, and the trained position detection model can be used for identifying the spatial position of an obstacle object in a driving road of the unmanned automobile. The sample data labeled in the two-dimensional-three-dimensional correlation manner is the sample data labeled with the position frame of the detection object in the two-dimensional image and the position frame of the detection object in the three-dimensional image.
In the prior art, when sample data of a plurality of two-dimensional-three-dimensional associated labels is acquired, by identifying the position of a detection object in each sample data, the two-dimensional-three-dimensional associated labels can be performed on the detection object in each sample data according to the detected object position of the detection object in each sample data. In this way, when the position of the detection object in a certain sample data fails to be identified, and the two-dimensional-three-dimensional association labeling of the detection object in the sample data fails, the two-dimensional-three-dimensional association labeling information of the detection object in the sample data is lost.
In the prior art, a 3D frame can also be applied to labeling of a 2D image, and can be mapped from 3D to 2D, so as to determine the edge of an object. The 2D/3D fusion labeling simultaneously labels the acquired 2D image data and establishes the association, and the method can label the position and the size of an object in a plane and a solid.
The object of interest may be enclosed by drawing a box and placing a vertex at each edge of the object. If an edge of an object is not visible or occluded by another object in the 2D image, the annotator estimates the position of the edge based on the size, height and angle of the object.
Disclosure of Invention
The invention aims to provide a stereo frame interaction method which can construct a stereo frame and adjust the position, size and direction of the stereo frame.
Another object of the present invention is to provide a stereoscopic frame interaction system, which is capable of operating a stereoscopic frame interaction method.
The embodiment of the invention is realized by the following steps:
in a first aspect, an embodiment of the present application provides a stereoscopic frame interaction method, which includes actions of pressing, dragging, and lifting a left mouse button, where the pressed point is a starting first vertex, and the lifted point is an ending third vertex of the starting vertex; moving the mouse to search for a seventh vertex, and clicking again after the position of the seventh vertex is determined to obtain the seventh vertex; and automatically calculating and filling the rest vertexes of the three-dimensional frame to generate a cuboid three-dimensional frame.
In some embodiments of the present invention, the automatically computing and filling the remaining vertices of the solid frame to generate a rectangular solid frame includes: generating a coordinate of a second vertex according to the X coordinate of the third vertex and the Y coordinate of the first vertex; and generating the coordinate of the fourth vertex according to the X coordinate of the first vertex and the Y coordinate of the third vertex.
In some embodiments of the present invention, the above further includes: and calculating the difference value DltX of the seventh vertex relative to the third vertex and the difference value DltY of the Y axis respectively.
In some embodiments of the present invention, the above further includes: generating a coordinate of a fifth vertex according to the X coordinate plus DltX of the first vertex and the Y coordinate plus DltY of the first vertex; generating a coordinate of a fourth vertex according to the X coordinate plus DltX of the second vertex and the Y coordinate plus DltY of the second vertex; and generating the coordinate of the eighth vertex according to the X coordinate plus DltX of the fourth vertex and the Y coordinate plus DltY of the fourth vertex.
In some embodiments of the present invention, the above further includes: and dragging points except the vertex and the middle point on any surface of the three-dimensional frame through a left mouse button to adjust the position of the three-dimensional frame.
In some embodiments of the present invention, the above further includes: and dragging any vertex of the vertices of the rear rectangular plane through the left mouse button to adjust the direction of the three-dimensional frame.
In some embodiments of the present invention, the above further includes: dragging any vertex in the front vertex through a left mouse button, and adjusting the sizes of the front rectangular plane and the rear rectangular plane at the same time; dragging any one of the front middle points through a left mouse button to adjust the size of the front rectangular plane; and dragging any one of the rear middle points through the left mouse button to adjust the size of the rear rectangular plane.
In a second aspect, an embodiment of the present application provides a stereoscopic frame interaction system, which includes a reference plane determining module, configured to perform actions of pressing, dragging, and lifting a left mouse button, where a pressed point is a starting first vertex, and a lifted point is an ending third vertex of the starting vertex;
the extended surface determining module is used for moving the mouse to search for a seventh vertex, and when the position of the seventh vertex is determined, clicking again to obtain the seventh vertex;
and the three-dimensional frame generation module is used for automatically calculating and filling the residual vertexes of the three-dimensional frame to generate a cuboid three-dimensional frame.
In some embodiments of the invention, the above includes: at least one memory for storing computer instructions; at least one processor in communication with the memory, wherein the at least one processor, when executing the computer instructions, causes the system to: the device comprises a reference plane determining module, an extension plane determining module and a three-dimensional frame generating module.
In a third aspect, embodiments of the present application provide a computer-readable storage medium on which a computer program is stored, where the computer program, when executed by a processor, implements a method as any one of stereoscopic frame interaction methods.
Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects:
a three-dimensional frame (also called a 3D frame) may be often used in the field of data annotation to annotate various objects in picture, video or point cloud data, and the three-dimensional frame may also be constructed and the position, size and direction of the three-dimensional frame may be adjusted. The point cloud data can be acquired to obtain target point cloud data, and a three-dimensional block diagram of the labeled object is generated based on projections of the target point cloud data on planes of a first coordinate axis and a second coordinate axis in a three-dimensional coordinate system and a coordinate set of the target point cloud data on a third coordinate axis of the three-dimensional coordinate system. Therefore, when point cloud labeling is carried out, point cloud labeling can be carried out on the labeled object very conveniently according to the three-dimensional block diagram, and therefore labeling efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic diagram of a three-dimensional frame construction process provided in an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating a method for adjusting a stereo frame according to an embodiment of the present invention;
fig. 3 is a schematic block diagram of a stereoscopic frame interactive system according to an embodiment of the present invention;
fig. 4 is an electronic device according to an embodiment of the present invention;
fig. 5 is a schematic perspective view of a frame according to an embodiment of the present invention.
Icon: 10-determining a datum plane module; 20-determining an extension plane module; 30-generating a stereoscopic frame module; 101-a memory; 102-a processor; 103-communication interface.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
It is to be noted that the term "comprises," "comprising," or any other variation thereof is 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 identical elements in a process, method, article, or apparatus that comprises the element.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the individual features of the embodiments can be combined with one another without conflict.
Example 1
Referring to fig. 1 and 5, fig. 1 is a schematic diagram illustrating a three-dimensional frame construction procedure according to an embodiment of the present invention, which is as follows:
step S100, pressing a left mouse button, dragging and lifting, wherein the pressed point is a starting first vertex, and the lifted point is an ending third vertex of the starting vertex;
step S110, the mouse moves to search for a seventh vertex, and the seventh vertex is obtained by clicking again after the position of the seventh vertex is determined;
and step S120, automatically calculating and filling the residual vertexes of the three-dimensional frame to generate a cuboid three-dimensional frame.
In some embodiments, the left mouse button is pressed, dragged, and lifted.
The point of pressing the left button of the mouse is the initial first vertex, and the lifting point is the front ending third vertex.
And moving the mouse, searching the seventh vertex, and clicking the mouse again to obtain the seventh vertex.
And automatically calculating and filling the other 5 vertexes (the second vertex, the fourth vertex, the fifth vertex, the sixth vertex and the eighth vertex), so that a cuboid three-dimensional frame is drawn. Vertex calculation rules:
the second vertex is: and taking the X coordinate of the third vertex and taking the Y coordinate of the first vertex.
The fourth vertex: and taking the X coordinate of the first vertex and taking the Y coordinate of the third vertex.
And calculating the difference value DltX of the seventh vertex relative to the third vertex and the difference value DltY of the Y axis respectively.
The fifth vertex: and taking the X coordinate of the first vertex plus DltX, and taking the Y coordinate of the first vertex plus DltY.
The fourth vertex: and taking the X coordinate plus DltX of the second vertex, and taking the Y coordinate plus DltY of the second vertex.
The eighth vertex: and taking the X coordinate of the fourth vertex plus DltX, and taking the Y coordinate of the fourth vertex plus DltY.
Defining:
the method comprises the following steps: and the rectangular plane is composed of a first vertex, a second vertex, a third vertex and a fourth vertex.
The following: and the rectangular plane consists of a fifth vertex, a sixth vertex, a seventh vertex and an eighth vertex.
Side surface: the remaining 4 planes of the solid frame.
Front vertex: a first vertex, a second vertex, a third vertex, and a fourth vertex.
Rear vertex: a fifth vertex, a sixth vertex, a seventh vertex, and an eighth vertex.
Front middle point: a ninth vertex, a tenth vertex, an eleventh vertex, and a first second vertex.
Rear middle point: a first third vertex, a first fourth vertex, a first fifth vertex, and a first sixth vertex.
Example 2
Referring to fig. 2, fig. 2 is a schematic diagram of a method for adjusting a stereo frame according to an embodiment of the present invention, which includes the following steps:
and S200, dragging points except the vertex and the middle point on any surface of the three-dimensional frame through a left mouse button to adjust the position of the three-dimensional frame.
And step S210, dragging any vertex of the vertices of the rear rectangular plane through the left mouse button to adjust the direction of the three-dimensional frame.
Step S220, dragging any vertex in the front vertex through a left mouse button, and adjusting the sizes of the front rectangular plane and the rear rectangular plane at the same time;
step S230, dragging any one of the front middle points through a left mouse button to adjust the size of the front rectangular plane;
and step S240, dragging any one of the rear middle points through the left mouse button to adjust the size of the rear rectangular plane.
In some embodiments, adjusting the position of the stereo frame:
and dragging the points except the vertex and the middle point on any surface of the stereo frame by the left mouse button.
Adjusting the direction of the three-dimensional frame:
and dragging any vertex in the rear vertexes by the left mouse button.
Adjusting the size of the three-dimensional frame:
the size of the front and back of the stereo frame can be different.
Adjusting the size of the front and back simultaneously:
and dragging any vertex in the front vertices by the left mouse button.
Adjusting the size of the front face:
and dragging any one middle point in the front middle points by the left mouse button.
The size of the back is adjusted:
and dragging any one of the rear middle points by the left mouse button.
The front and the back of the stereo frame are kept the same size.
Adjusting the size of the front and back simultaneously:
and dragging any one vertex or middle point of the front vertex, the front middle point or the rear middle point by the left mouse button.
Example 3
Referring to fig. 3, fig. 3 is a schematic diagram of a stereo frame interactive system module according to an embodiment of the present invention, which is shown as follows:
a reference plane determining module 10, configured to perform actions of pressing, dragging, and lifting a left mouse button, where a pressed point is a first starting vertex, and a lifted point is a third ending vertex of the first starting vertex;
the extended surface determining module 20 is used for moving the mouse to search for a seventh vertex, and when the position of the seventh vertex is determined, clicking again to obtain the seventh vertex;
and a stereo frame generation module 30, configured to automatically calculate and complement the remaining vertices of the stereo frame to generate a rectangular stereo frame.
In some embodiments, the point cloud data: in the field of unmanned driving, point cloud data may be a data set of points in a certain coordinate, and each data in the point cloud data includes a coordinate in a three-dimensional coordinate system, and may further include information such as color, classification value, intensity value, time, and the like.
Point cloud labeling: and 3DBox is performed on the three-dimensional object corresponding to the point cloud data, and data such as vehicle, pedestrian, obstacle and the like are added to the object, so that training data are provided for the deep learning algorithm.
The method for generating the stereoscopic block diagram of the annotated object provided by the embodiment of the application can be applied to a user side, and the user side can be, but is not limited to, a personal computer, a smart phone, a tablet computer, a laptop portable computer, a vehicle-mounted computer, a personal digital assistant and the like.
And acquiring initial point cloud data in the selected area. In the embodiment of the application, the selected area can be selected manually by a marking person after point cloud data acquired by a three-dimensional laser radar is subjected to point cloud rendering in a three-dimensional coordinate system. The marking object is located in the selected area, and the marking object refers to point cloud data needing point cloud marking, such as point cloud data of pedestrians, vehicles or obstacles.
Specifically, the rendering area may be subjected to coarse-grained 2DBox frame selection by a labeling person, and at this time, in the three-dimensional coordinate system, as long as the area where the coordinates on the frame selection plane are located in the frame selection area is the selected area, the coordinate set of the points in the selected area is the initial point cloud data. The plane in which the 2DBox frame is selected may be an xy plane, a yz plane, or an xz plane in a three-dimensional space coordinate, which is not specifically limited in this embodiment of the application.
For convenience of explanation, the embodiment of the present application will be described by taking an example of 2DBox frame selection in the xy plane. After the rectangular area is framed, traversing all points (x, y, z) in the point cloud data according to the maximum point (xmax, ymax) and the minimum point (xmin, ymin) of the rectangular frame coordinate, finding out the points which satisfy xmin < x < xmax and ymin < y < ymax, and using the coordinate set of the found points as the initial point cloud data in the selected area.
In the embodiment of the application, the selected area is a rectangular area. It will be appreciated that in other embodiments, the outlined region may be of other shapes, for example, circular or elliptical, etc.
And filtering the ground point cloud data in the initial point cloud data to obtain target point cloud data. For the field of unmanned driving, the three-dimensional laser radar can acquire ground point cloud data corresponding to the ground besides point cloud data of marked objects such as vehicles, pedestrians, obstacles and the like on the road surface. After the initial point cloud data in the selected area is obtained, the ground point cloud data in the initial point cloud data can be filtered to obtain target point cloud data.
Specifically, ground point cloud data in the initial point cloud data is filtered, and the filtered initial point cloud data is obtained.
In the embodiment of the application, ground point cloud data can be filtered from the initial point cloud data by adopting a ground segmentation algorithm and the like, so that the filtered initial point cloud data is obtained. Fig. 2 is a schematic diagram of initial point cloud data before filtering, and a schematic diagram of initial point cloud data after filtering point cloud data corresponding to the ground from the initial point cloud data to obtain filtered initial point cloud data is shown in fig. 3.
In the point cloud data acquisition process, due to the influence of the three-dimensional laser radar and the environment, some noise points may exist in the acquired point cloud data, the noise points are generally very sparse, and the points of the labeled object are relatively dense, so that after the ground point cloud data in the initial point cloud data are filtered to obtain the filtered initial point cloud data, the filtered initial point cloud data can be denoised, the noise point data in the filtered initial point cloud data are removed to obtain target point cloud data, and the target point cloud data is the point cloud data of the object to be subjected to point cloud labeling, namely the labeled object. In the embodiment of the present application, denoising processing on the initial point cloud data may adopt, but is not limited to, methods such as radius filtering, statistical filtering, voxel filtering, and the like.
And generating a three-dimensional block diagram of the marked object based on the projections of the target point cloud data on the planes of the first coordinate axis and the second coordinate axis in the three-dimensional coordinate system and the coordinate set of the target point cloud data on the third coordinate axis in the three-dimensional coordinate system.
The projection height represents the height (z-axis height) of target point cloud data projected on a third coordinate axis, the first center coordinate represents the coordinate center value (center coordinate on the z-axis) of the target point cloud data on the third axis, the second center coordinate represents the center coordinate (center coordinate of xy plane) of the target point cloud data projected on the planes of the first coordinate axis and the second coordinate axis, the length represents the length of an image formed by the target point cloud data projected on the planes of the first coordinate axis and the second coordinate axis, the broadband represents the broadband of the image formed by the target point cloud data projected on the planes of the first coordinate axis and the second coordinate axis, and the rotation angle represents the rotation angle of the image formed by the target point cloud data projected on the planes of the first coordinate axis and the second coordinate axis. Therefore, a stereoscopic block diagram can be directly generated in the three-dimensional coordinate system according to the projection height, the first center coordinate, the length, the width, the rotation angle and the second center coordinate, and the stereoscopic block diagram can be used as a stereoscopic block diagram of the labeling object.
As shown in fig. 4, an embodiment of the present application provides an electronic device, which includes a memory 101 for storing one or more programs; a processor 102. The one or more programs, when executed by the processor 102, implement the method of any of the first aspects as described above.
Also included is a communication interface 103, and the memory 101, processor 102 and communication interface 103 are electrically connected to each other, directly or indirectly, to enable transfer or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 101 may be used to store software programs and modules, and the processor 102 executes the software programs and modules stored in the memory 101 to thereby execute various functional applications and data processing. The communication interface 103 may be used for communicating signaling or data with other node devices.
The Memory 101 may be, but is not limited to, a Random Access Memory 101 (RAM), a Read Only Memory 101 (ROM), a Programmable Read Only Memory 101 (PROM), an Erasable Read Only Memory 101 (EPROM), an electrically Erasable Read Only Memory 101 (EEPROM), and the like.
The processor 102 may be an integrated circuit chip having signal processing capabilities. The Processor 102 may be a general-purpose Processor 102, including a Central Processing Unit (CPU) 102, a Network Processor 102 (NP), and the like; but may also be a Digital Signal processor 102 (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware components.
In the embodiments provided in the present application, it should be understood that the disclosed method and system and method can be implemented in other ways. The method and system embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
In another aspect, embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, which, when executed by the processor 102, implements the method according to any one of the first aspect described above. The functions, if implemented in the form of software functional modules 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 or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) 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 101 (ROM), a Random Access Memory 101 (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In summary, the stereoscopic frame interaction method and system provided by the embodiment of the present application can often use a stereoscopic frame (also called a 3D frame) to mark various targets in picture, video or point cloud data in the field of data marking, and can also construct the stereoscopic frame and adjust the position, size and direction of the stereoscopic frame. The point cloud data can be acquired to obtain target point cloud data, and a three-dimensional block diagram of the labeled object is generated based on projections of the target point cloud data on planes of a first coordinate axis and a second coordinate axis in a three-dimensional coordinate system and a coordinate set of the target point cloud data on a third coordinate axis of the three-dimensional coordinate system. Therefore, when point cloud labeling is carried out, point cloud labeling can be carried out on the labeled object very conveniently according to the three-dimensional block diagram, and therefore labeling efficiency is improved.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.

Claims (10)

1. A stereoscopic frame interaction method is characterized by comprising the following steps:
pressing a left mouse button, dragging and lifting the left mouse button, wherein the pressed point is a starting first vertex, and the lifted point is an ending third vertex of the starting vertex;
moving the mouse to search for a seventh vertex, and clicking again after the position of the seventh vertex is determined to obtain the seventh vertex;
and automatically calculating and filling the rest vertexes of the three-dimensional frame to generate a cuboid three-dimensional frame.
2. A method as claimed in claim 1, wherein automatically computing the complement of the remaining vertices of the bounding box, generating a rectangular bounding box comprises:
generating a coordinate of a second vertex according to the X coordinate of the third vertex and the Y coordinate of the first vertex;
and generating the coordinate of the fourth vertex according to the X coordinate of the first vertex and the Y coordinate of the third vertex.
3. The method of claim 2, further comprising:
and calculating the difference value DltX of the seventh vertex relative to the third vertex and the difference value DltY of the Y axis respectively.
4. A stereoscopic frame interaction method as claimed in claim 3, further comprising:
generating a coordinate of a fifth vertex according to the X coordinate plus DltX of the first vertex and the Y coordinate plus DltY of the first vertex;
generating a coordinate of a fourth vertex according to the X coordinate plus DltX of the second vertex and the Y coordinate plus DltY of the second vertex;
and generating the coordinate of the eighth vertex according to the X coordinate plus DltX of the fourth vertex and the Y coordinate plus DltY of the fourth vertex.
5. The method of claim 1, further comprising:
and dragging points except the vertex and the middle point on any surface of the three-dimensional frame through a left mouse button to adjust the position of the three-dimensional frame.
6. The method of claim 1, further comprising:
and dragging any vertex of the vertices of the rear rectangular plane through the left mouse button to adjust the direction of the three-dimensional frame.
7. The method of claim 1, further comprising:
dragging any vertex in the front vertex through a left mouse button, and adjusting the sizes of the front rectangular plane and the rear rectangular plane at the same time;
dragging any one of the front middle points through a left mouse button to adjust the size of the front rectangular plane;
and dragging any one of the rear middle points through the left mouse button to adjust the size of the rear rectangular plane.
8. A stereoscopic frame interaction system, comprising:
the reference surface determining module is used for performing actions of pressing, dragging and lifting a left mouse button, wherein a pressed point is a starting first vertex, and a lifted point is an ending third vertex of the starting vertex;
the extended surface determining module is used for moving the mouse to search for a seventh vertex, and when the position of the seventh vertex is determined, clicking again to obtain the seventh vertex;
and the three-dimensional frame generation module is used for automatically calculating and filling the residual vertexes of the three-dimensional frame to generate a cuboid three-dimensional frame.
9. A stereoscopic frame interaction system as claimed in claim 8, comprising:
at least one memory for storing computer instructions;
at least one processor in communication with the memory, wherein the at least one processor, when executing the computer instructions, causes the system to perform: the device comprises a reference plane determining module, an extension plane determining module and a three-dimensional frame generating module.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.
CN202111366127.1A 2021-11-18 2021-11-18 Stereo frame interaction method and system Pending CN114185476A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111366127.1A CN114185476A (en) 2021-11-18 2021-11-18 Stereo frame interaction method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111366127.1A CN114185476A (en) 2021-11-18 2021-11-18 Stereo frame interaction method and system

Publications (1)

Publication Number Publication Date
CN114185476A true CN114185476A (en) 2022-03-15

Family

ID=80540318

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111366127.1A Pending CN114185476A (en) 2021-11-18 2021-11-18 Stereo frame interaction method and system

Country Status (1)

Country Link
CN (1) CN114185476A (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160117795A1 (en) * 2014-10-27 2016-04-28 Fu Tai Hua Industry (Shenzhen) Co., Ltd. Point cloud data processing system and method thereof and computer readable storage medium
CN110598743A (en) * 2019-08-12 2019-12-20 北京三快在线科技有限公司 Target object labeling method and device
CN110929612A (en) * 2019-11-13 2020-03-27 北京云聚智慧科技有限公司 Target object labeling method, device and equipment
CN111080805A (en) * 2019-11-26 2020-04-28 北京云聚智慧科技有限公司 Method and device for generating three-dimensional block diagram of marked object, electronic equipment and storage medium
CN111724402A (en) * 2020-06-18 2020-09-29 北京小白世纪网络科技有限公司 Medical image labeling method, system and device
CN112419233A (en) * 2020-10-20 2021-02-26 腾讯科技（深圳）有限公司 Data annotation method, device, equipment and computer readable storage medium
WO2021114884A1 (en) * 2019-12-11 2021-06-17 杭州海康威视数字技术股份有限公司 Point cloud labeling method, apparatus, and system, device, and storage medium
CN113160349A (en) * 2020-01-07 2021-07-23 北京地平线机器人技术研发有限公司 Point cloud marking method and device, storage medium and electronic equipment

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160117795A1 (en) * 2014-10-27 2016-04-28 Fu Tai Hua Industry (Shenzhen) Co., Ltd. Point cloud data processing system and method thereof and computer readable storage medium
CN110598743A (en) * 2019-08-12 2019-12-20 北京三快在线科技有限公司 Target object labeling method and device
CN110929612A (en) * 2019-11-13 2020-03-27 北京云聚智慧科技有限公司 Target object labeling method, device and equipment
CN111080805A (en) * 2019-11-26 2020-04-28 北京云聚智慧科技有限公司 Method and device for generating three-dimensional block diagram of marked object, electronic equipment and storage medium
WO2021114884A1 (en) * 2019-12-11 2021-06-17 杭州海康威视数字技术股份有限公司 Point cloud labeling method, apparatus, and system, device, and storage medium
CN113160349A (en) * 2020-01-07 2021-07-23 北京地平线机器人技术研发有限公司 Point cloud marking method and device, storage medium and electronic equipment
CN111724402A (en) * 2020-06-18 2020-09-29 北京小白世纪网络科技有限公司 Medical image labeling method, system and device
CN112419233A (en) * 2020-10-20 2021-02-26 腾讯科技（深圳）有限公司 Data annotation method, device, equipment and computer readable storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
陌蓠_47B3: "手把手教你用原生js实现按住鼠标拖动画框", pages 1 - 7, Retrieved from the Internet <URL:https://www.jianshu.com/p/04dc66653182> *

Similar Documents

Publication Publication Date Title
Wang et al. Real‐Time Vehicle Detection Algorithm Based on Vision and Lidar Point Cloud Fusion
Balali et al. Multi-class US traffic signs 3D recognition and localization via image-based point cloud model using color candidate extraction and texture-based recognition
Takimoto et al. 3D reconstruction and multiple point cloud registration using a low precision RGB-D sensor
Ulusoy et al. Semantic multi-view stereo: Jointly estimating objects and voxels
CN111080805A (en) Method and device for generating three-dimensional block diagram of marked object, electronic equipment and storage medium
US11209277B2 (en) Systems and methods for electronic mapping and localization within a facility
WO2023024443A1 (en) Data matching method and apparatus, and electronic device, storage medium and program product
Bullinger et al. 3d vehicle trajectory reconstruction in monocular video data using environment structure constraints
Wang et al. Fusion Algorithm of Laser-Point Clouds and Optical Images
CN117911656A (en) Three-dimensional lane marking method and device, electronic equipment and storage medium
CN111695497B (en) Pedestrian recognition method, medium, terminal and device based on motion information
CN116091751B (en) Point cloud classification method and device, computer equipment and storage medium
CN114185476A (en) Stereo frame interaction method and system
US20220245860A1 (en) Annotation of two-dimensional images
CN114170267A (en) Target tracking method, device, equipment and computer readable storage medium
Bullinger et al. Monocular 3d vehicle trajectory reconstruction using terrain shape constraints
CN116309943B (en) Parking lot semantic map road network construction method and device and electronic equipment
CN111899277B (en) Moving object detection method and device, storage medium and electronic device
Prakash et al. A semi-supervised approach to space carving
Kim et al. 3D Object Detection Method Using LiDAR Information in Multiple Frames
CN117935206A (en) Data preprocessing method, device, equipment and storage medium
Bullinger et al. 3D Trajectory Reconstruction of Dynamic Objects Using Planarity Constraints
CN115147803A (en) Object detection method and device
Chu et al. Removing past data of dynamic objects using static Velodyne LiDAR sensor
Nuger et al. Multicamera fusion for shape estimation and visibility analysis of unknown deforming objects

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