CN111046698B - Visual positioning method and system for visual editing - Google Patents
Visual positioning method and system for visual editing Download PDFInfo
- Publication number
- CN111046698B CN111046698B CN201811189739.6A CN201811189739A CN111046698B CN 111046698 B CN111046698 B CN 111046698B CN 201811189739 A CN201811189739 A CN 201811189739A CN 111046698 B CN111046698 B CN 111046698B
- Authority
- CN
- China
- Prior art keywords
- key frame
- key
- visual
- frames
- list
- 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
- 230000000007 visual effect Effects 0.000 title claims abstract description 170
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000002159 abnormal effect Effects 0.000 claims abstract description 133
- 238000010276 construction Methods 0.000 claims abstract description 20
- 238000006073 displacement reaction Methods 0.000 claims description 32
- 238000001514 detection method Methods 0.000 claims description 23
- 230000004807 localization Effects 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 11
- 238000012216 screening Methods 0.000 description 21
- 230000005856 abnormality Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 9
- 230000002547 anomalous effect Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000009471 action Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
- G01C21/3833—Creation or updating of map data characterised by the source of data
- G01C21/3837—Data obtained from a single source
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/02—Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Television Signal Processing For Recording (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention provides a visual positioning method and a visual positioning system for visual editing, which are characterized in that after key frames of scene images and characteristic information of the key frames are acquired, a visual editing interface is created and the key frames or the characteristic information thereof are displayed, so that a user who is not proficient in programming language can intervene in the scene construction and positioning process, the accuracy of scene construction and positioning is improved, and meanwhile, the construction efficiency is improved, so that the visual positioning method and the visual positioning system are suitable for complex and changeable environments. In addition, the abnormal frames and abnormal connecting lines are further screened out, and the abnormal frames and abnormal connecting lines can be conveniently checked and edited.
Description
Technical Field
The application relates to the technical field of computer images, in particular to a visual positioning method and a visual positioning system for visual editing.
Background
With computer vision becoming an increasingly important technology development point in the robot field, real-time positioning and mapping (Simultaneous Localization and Mapping, abbreviated as "SLAM") technology is a key technology in the industry due to its full autonomy. However, the inventor of the present invention found that the existing SLAM technology has poor adaptability when dealing with complex and changeable environments, has high error rate for environment identification, is not in compliance with the real environment, and still has a large number of error frames in the map construction process to affect the accuracy of map construction and positioning.
Disclosure of Invention
The invention aims to provide a visual positioning method and a visual positioning system for visual editing, which improve the accuracy and efficiency of visual positioning and scene map construction.
In order to achieve the technical purpose, certain embodiments of the present invention disclose a visual positioning method for visual editing, comprising the following steps:
acquiring a key frame of a scene image and feature information of the key frame, wherein the feature information comprises position information of the key frame;
creating a visual editing interface, and displaying icons representing the key frames on the visual editing interface according to the position information of the key frames;
after detecting selection of an icon representing a key frame, displaying the key frame and/or feature information of the key frame for editing; and
and constructing a visual positioning map through the edited key frames and/or the characteristic information of the key frames.
Certain embodiments of the present invention also disclose a visual positioning system for visual editing, comprising:
the first acquisition module is used for acquiring key frames of the scene image and characteristic information of the key frames, wherein the characteristic information comprises position information of the key frames;
the creation module is used for creating a visual editing interface and displaying icons representing the key frames on the visual editing interface according to the position information of the key frames acquired by the first acquisition module;
The detection module is used for detecting selection of icons representing the key frames;
the display module is used for displaying the key frames and/or the characteristic information of the key frames for editing after the detection module detects the selection of the icons representing the key frames; and
and the construction module is used for constructing the visual positioning map through the edited key frames and/or the characteristic information of the key frames.
In one embodiment, when the position information of a plurality of key frames is the same, the plurality of key frames may be formed into a key frame list and an icon representing the key frame list may be displayed on the visual editing interface. Upon detecting selection of an icon representing a key frame list, a plurality of key frames in the key frame list and/or feature information of the plurality of key frames are displayed for editing. And forming a key frame list by a plurality of key frames with the same position information, so that batch processing is convenient.
In one embodiment, the feature information of each key frame in the key frame list may be compared with the feature information of other neighboring key frames in the key frame list to obtain the key frame with the highest feature information similarity with each key frame. And then judging whether the similarity difference between each key frame and the key frame with the highest similarity exceeds a first preset threshold value, and marking the key frame with the similarity difference exceeding the first preset threshold value as an abnormal frame, so that suspicious frames can be screened out from a plurality of key frames with the same position information.
In one embodiment, an anomaly frame list including one or more anomaly frames screened out may be provided on a visual editing interface. After the selection of the abnormal frame list is detected, icons representing the key frame list containing the abnormal frames are displayed on the visual editing interface in a mode different from the key frame list not containing the abnormal frames, so that the icons can be conveniently checked and edited.
In one embodiment, the characteristic information may further include displacement and deflection information of the key frame and the neighboring key frame. And displaying a connecting line for connecting the icon representing the key frame and the icon representing the adjacent key frame on the visual editing interface, and displaying displacement and deflection information of the key frame and the adjacent key frame for editing after detecting the selection of the connecting line. And the adjacent two key frames are linked, so that the relation between the adjacent key frames can be conveniently adjusted.
In one embodiment, it may be determined whether the number of feature point matching pairs of the key frame and the neighboring key frame exceeds a second preset threshold, and the connection line between the key frame and the neighboring key frame, for which the number of feature point matching pairs does not exceed the second preset threshold, is marked as an abnormal connection line, so as to screen out a suspicious connection line.
In one embodiment, an abnormal wire list including one or more abnormal wires screened out may be provided on the visual editing interface. After the selection of the abnormal connection list is detected, one or more abnormal connection lines are displayed on the visual editing interface in a mode different from the non-abnormal connection lines, so that the abnormal connection lines can be conveniently checked and edited.
In one embodiment, a key frame is linked with an adjacent key frame through a connecting line, and when characteristic information of the key frame is edited, the characteristic information of the adjacent key frame is correspondingly edited according to displacement and deflection information of the key frame and the adjacent key frame, so that linkage modification is carried out on the two adjacent key frames.
In one embodiment, the visual localization method described above is a SLAM method. In one embodiment, the visual positioning system is a SLAM system. The flexible implementation of the visual editing interface is provided in the SLAM method and system, so that the recognition accuracy can be ensured to adapt to complex and changeable environments while the mobile robot has certain autonomy.
In one embodiment, editing the key frames and/or feature information of the key frames includes adding, moving, and/or removing the key frames, and/or modifying the feature information of the key frames, wherein the feature information includes coordinates of feature points, descriptors of the feature points, and/or bag of words values of the feature points.
In one embodiment, editing of the key frames and/or feature information of the key frames includes adding, moving, and/or removing lines of the key frames to neighboring key frames, and/or modifying displacement and deflection information of the key frames to neighboring key frames.
Compared with the prior art, the embodiments of the invention have the main differences and effects that:
in the invention, after the key frames of the scene images and the characteristic information of the key frames are acquired, a visual editing interface is created and the key frames or the characteristic information thereof are displayed, so that a user who is not proficient in programming language can also intervene in the scene construction and positioning process, the accuracy of scene construction and positioning is improved, and meanwhile, the construction efficiency is improved so as to adapt to complex and changeable environments.
It is understood that within the scope of the present invention, the above-described technical features of the present invention and technical features specifically described below (in the embodiments and examples) may be combined with each other to constitute new or preferred technical solutions. And are limited to a space, and are not described in detail herein.
Drawings
Fig. 1 is a flow diagram of a visual positioning method for visual editing according to an example embodiment of the present application.
Fig. 2 is a flow chart of screening for anomalous frames according to an example embodiment of the application.
Fig. 3 is a flow chart illustrating displaying an exception frame according to an example embodiment of the present application.
FIG. 4 is a flow diagram of linking key frames with neighboring key frames according to an example embodiment of the present application.
FIG. 5 is a flow diagram of screening abnormal links according to an example embodiment of the present application.
FIG. 6 is a flow chart illustrating abnormal wiring according to an example embodiment of the present application.
FIG. 7 is a block diagram of a visual positioning system for visual editing according to an example embodiment of the present application.
Fig. 8 is a block diagram of an anomaly frame screening subsystem according to an example embodiment of the present application.
Fig. 9 is a block diagram of an anomaly link screening subsystem according to an example embodiment of the present application.
FIG. 10 is a schematic diagram of a visual editing interface according to an example embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
With the development of mobile robot technology, SLAM technology, which is an important technical component of autonomous navigation of mobile robots, has been improved in a variety of complex scenes. At present, the identification error rate of the existing SLAM technology is very high in a logistics transportation environment, and the identification error rate of video frames reaches more than 40%. The large number of error frames has a great influence on the accuracy of map construction and visual positioning, and meanwhile, the accuracy and the efficiency of visual navigation of the mobile robot are reduced.
The inventors of the present invention found that although the total autonomy is in a large direction, the accuracy of current SLAM technology is still not high enough. Aiming at the situation, the invention provides a visual positioning method and a visual positioning system for visual editing, wherein the key frames or characteristic information thereof can be checked, selected and edited on the visual editing interface by creating the visual editing interface and displaying the key frames, so that a user not proficient in programming language can also intervene in the scene construction and positioning process, and the operation threshold is low; and when the environment changes, small key frames which cannot be identified by SLAM technology can be timely adjusted on a visual editing interface, so that the construction efficiency is improved while the accuracy of scene construction and positioning is greatly improved, and the method is suitable for complex and changeable environments.
FIG. 1 illustrates a visual positioning method for visual editing according to an example embodiment of the present application. As shown in fig. 1, the visual positioning method includes the steps of:
in step 101, key frames of a scene image and feature information of the key frames are acquired, the feature information including location information of the key frames. In this step, it is understood that the mobile robot may employ the two-dimensional image provided by the vision sensor as a key frame of the scene image and transmit key frame information to the map processor. The position information of the key frame can be obtained by matching the feature points of the adjacent key frames stored previously or directly obtained by the motion trail. The key frames and the feature information of the key frames may be obtained in various known manners, which will not be described herein.
Thereafter, step 102 is entered, a visual editing interface is created, and an icon representing a key frame is displayed on the visual editing interface according to the location information of the key frame. The visual editing interface may be associated with the location of the entire scene in any suitable manner and the corresponding key frames displayed on the visual editing interface. In one embodiment, the visual editing interface is in one-to-one correspondence with the location of the entire scene. In one embodiment, the visual editing interface may be divided into a plurality of regions, each region corresponding to a different portion of the entire scene, e.g., a first region of the visual editing interface corresponds to the aisle portion and a second region corresponds to the shelf placement portion … …. The visual editing interface is flexibly set and the key frames are displayed, so that the operation can be convenient. In other embodiments, the visual editing interface may also be associated with the location of the entire scene in other ways.
Icons representing key frames may be arranged in any form according to specific situations (e.g., visual editing interface size, scene layout situation), such as icons that may be arranged in a square, circular, or other shape, for ease of viewing and manipulation by an operator. In one embodiment, when the visual editing interface is divided into a plurality of different areas, different forms of icons may be provided for key frames in the different areas.
Thereafter, step 103 is entered, and after detecting selection of an icon representing a key frame, the key frame and/or feature information of the key frame is displayed for editing. In one embodiment, editing the key frames and/or feature information of the key frames includes adding, moving, and/or removing key frames, and/or modifying feature information of the key frames, wherein the feature information includes coordinates of feature points, descriptors of feature points, bag of words values of feature points, and/or other information. The key frames and/or feature information of the key frames may be selected and edited by any known input means.
Thereafter, step 104 is entered to construct a visual positioning map from the edited key frames and/or the feature information of the key frames.
In the case that the visual positioning method is a SLAM method, by providing flexible implementation of the visual editing interface, the mobile robot can have certain autonomy and ensure the recognition accuracy to adapt to complex and changeable environments.
In various embodiments of the present application, the key frames may be analyzed for ease of viewing and editing.
In one embodiment, in step 102, when certain information (e.g., location information) of the plurality of key frames is the same, the plurality of key frames may be combined to form a key frame list and an icon representing the key frame list may be displayed on the visual editing interface. The icons representing the keyframe list may be a list graphic, a stack of keyframe icons, or other form.
In this embodiment, accordingly, in step 103, after detecting selection of an icon representing a key frame list, a plurality of key frames in the key frame list and/or feature information of the plurality of key frames are displayed for editing. In one embodiment, the key frames and/or feature information of the key frames may be displayed directly for editing after clicking on the key frame list. In one embodiment, after clicking on the list of key frames, icons for a plurality of key frames may be displayed for further clicking and then displaying that key frame and/or its characteristic information that was clicked. In other embodiments, the plurality of key frames in the key frame list and the feature information of the plurality of key frames may also be displayed in other manners.
And forming a plurality of key frames with the same information into a key frame list, so that batch processing can be conveniently carried out. In one embodiment, in the case of displaying an icon representing a key frame according to the position information, a plurality of key frames having the same position information are combined to form a key frame list. However, it will be understood by those skilled in the art that in other embodiments of the present application, other key frames with the same information may be combined to form a list, so as to facilitate batch processing.
And further comparing the plurality of key frames, and screening suspicious frames from the plurality of key frames. FIG. 2 illustrates a flowchart for screening for outlier frames according to an example embodiment of the present application. As shown in fig. 2, the above visual positioning method may further include the steps of:
in step 201, feature information of each key frame in the key frame list is compared with feature information of other neighboring key frames in the key frame list in similarity. Phase contrast may be performed in any known manner.
Thereafter, step 202 is performed to obtain, according to the comparison result, the key frame with the highest similarity to the feature information of each key frame.
Thereafter, step 203 is performed to determine whether the similarity difference between each key frame and the key frame with the highest similarity exceeds a first preset threshold. If so, go to step 204; if not, go back to step 201 to continue processing the next key frame until all key frames in the key frame list have been processed. The first preset threshold may be set as needed.
In step 204, the keyframes with similarity differences exceeding the first preset threshold value with the keyframes with highest similarity are marked as abnormal frames. If the key frame is not sufficiently similar to all other key frames, the key frame may not belong to the location or the environment may change.
For example, key frame a, key frame B, and key frame C are included in the key frame list. The similarity difference between the key frame a and the key frame B is S1, the similarity difference between the key frame B and the key frame C is S2, and S2< S1, the key frame C can be considered as the key frame with the highest similarity with the key frame B. Then, comparing S2 with a first preset threshold T1, if S2> T1, the similarity between the key frame B and the key frame C is not high enough, and if attention needs to be paid, the key frame B is marked as an abnormal frame. In other embodiments, other feature information besides similarity may be used to perform screening or auxiliary screening, and may be set according to specific situations.
After the abnormal frames are screened, they can be summarized to form a list and displayed when they need to be checked. FIG. 3 illustrates a flowchart of displaying an exception frame according to an example embodiment of the present application. As shown in fig. 3, the above visual positioning method may further include the steps of:
In step 301, an abnormal frame list is provided on a visual editing interface, the abnormal frame list comprising one or more abnormal frames. When an abnormal frame exists, an abnormal frame list including the abnormal frame may be displayed on either side of the visual editing interface. In one embodiment, the anomaly information of each anomaly frame, such as how much the similarity exceeds, may also be displayed in the anomaly frame list for reference.
Thereafter, step 302 is entered, after the selection of the list of abnormal frames is detected, an icon representing the list of key frames containing abnormal frames is displayed on the visual editing interface in a different manner from the list of key frames not containing abnormal frames. In one embodiment, icons representing a list of keyframes containing an abnormal frame and icons representing a list of keyframes not containing an abnormal frame are displayed in different colors on a visual editing interface. Further, after detecting selection of the key frame list icon representing the frame containing the abnormality, the icon representing the frame containing the abnormality may be displayed in a different manner from the non-abnormal frame. In one embodiment, icons representing a list of keyframes containing an outlier frame and icons representing a list of keyframes not containing an outlier frame are displayed in different lines or graphics on the visual editing interface. In another embodiment, when an anomalous frame is otherwise determined and the determined anomalous frame is not in a certain key frame list, then an icon representing the anomalous frame is displayed directly in a different manner than the non-anomalous frame. In other embodiments, icons representing a list of keyframes containing an outlier frame and icons representing a list of keyframes not containing an outlier frame may also be displayed in other different manners.
Icons representing the frames containing the abnormality and icons representing the frames not containing the abnormality are displayed in different manners, so that the icons can be conveniently checked and edited. For example, when abnormality information of a plurality of abnormality frames is simultaneously viewed, it is possible to roughly understand the overall situation, for example, from which key frame an error has occurred, and the like.
In one embodiment, the characteristic information may further include displacement and deflection information of the key frame and the adjacent key frame, and the key frame and the adjacent key frame may be associated by the displacement and deflection information. FIG. 4 illustrates a flow chart of linking key frames according to an example embodiment of the present application. As shown in fig. 4, the following steps may be further included after step 102:
in step 401, a link connecting an icon representing a key frame with an icon representing an adjacent key frame is displayed on the visual editing interface, thereby linking the key frame with the adjacent key frame.
Thereafter, step 402 is entered, after detecting a selection of a link, displaying displacement and deflection information of the key frame and adjacent key frames for editing. In one embodiment, editing of the key frames and/or feature information of the key frames includes adding, moving, and/or removing lines of the key frames to neighboring key frames, and/or modifying displacement and deflection information of the key frames to neighboring key frames. The operation may be performed by any known input means.
Thereafter, step 403 is performed to construct the visual positioning map according to the displacement and deflection information of the edited key frame and the adjacent key frame.
In other embodiments, the key frame may be connected with other information of the adjacent key frame as required, and the connection is not limited to the displacement and deflection information. By connecting a keyframe with an adjacent keyframe, the relationship between two keyframes can be easily viewed and adjusted.
In one embodiment, in the case that the key frame is connected with the adjacent key frame through a connection line, when feature information of the key frame is edited, the feature information of the adjacent key frame can be edited correspondingly according to the connection information of the key frame and the adjacent key frame, for example, according to displacement and deflection information of the key frame and the adjacent key frame.
For example, when the position information of the key frame is modified, the position information of the adjacent key frame is correspondingly modified according to the displacement information of the key frame and the adjacent key frame; when the angle information of the key frame is modified, the angle information of the adjacent key frame is correspondingly modified according to the deflection information of the key frame and the adjacent key frame. The key frames are connected with the adjacent key frames, so that the association editing can be conveniently carried out.
The key frames are further compared with adjacent key frames, and suspicious connecting lines can be screened out. FIG. 5 illustrates a flowchart for screening outlier links according to an example embodiment of the present application. As shown in fig. 5, the above visual positioning method may further include the steps of:
in step 501, it is determined whether the feature point matching pair number of the key frame and the neighboring key frame exceeds a second preset threshold. If not, go to step 502; if so, the process returns to step 501 to continue processing the next set of key frames until all sets of key frames have been processed. The second preset threshold may be set as needed. The calculation of the feature point matching pair numbers of the key frame and the adjacent key frame is a known calculation method, and is not described herein.
In step 502, the connection line between the key frame and the neighboring key frame, the number of which does not exceed the second preset threshold, is marked as an abnormal connection line. And screening out the connecting lines with the number of the feature point matching pairs smaller than a second preset threshold value, and calibrating the connecting lines as abnormal connecting lines, so that the user can check conveniently. If the number of feature point matches of a key frame to a neighboring key frame is not sufficient, the neighboring relationship may be problematic or the environment may change, requiring attention.
In other embodiments, when a connection is made with other information of an adjacent key frame through a key frame, the abnormal connection is screened through other information.
After the abnormal links are screened, they can be aggregated to form a list and displayed when they need to be viewed. FIG. 6 illustrates a flowchart showing abnormal wiring according to an example embodiment of the present application. As shown in fig. 6, the above visual positioning method may further include the steps of:
in step 601, an abnormal connection list is provided on a visual editing interface, the abnormal connection list including one or more abnormal connections. When an abnormal connection exists, an abnormal connection list including the abnormal connection may be displayed on either side of the visual editing interface. In one embodiment, the anomaly information of each anomaly link, such as how much the feature point matching pair number is still worse, etc., may also be displayed in the anomaly link list for reference.
Thereafter, step 602 is entered, after detecting selection of the list of abnormal links, displaying one or more abnormal links on the visual editing interface in a manner different from the non-abnormal links. In one embodiment, the abnormal connection and the non-abnormal connection are displayed in different colors on the visual editing interface. In one embodiment, the abnormal connection and the non-abnormal connection are displayed in different lines on the visual editing interface. In other embodiments, the anomalous and non-anomalous links may also be displayed in other different ways, such as in bold and the like.
The abnormal connection lines and the non-abnormal connection lines are displayed in different modes, so that the abnormal connection lines and the non-abnormal connection lines can be conveniently checked and edited. For example, when abnormality information of a plurality of abnormal wirings is simultaneously checked, it is possible to make a rough knowledge of the overall situation, for example, from which wiring an error has occurred, and the like.
The above lists various example processes for analyzing key frames, which may be used alone or in combination. It will be appreciated that other analysis processes may be performed on the keyframes to facilitate viewing and editing.
The method embodiments of the present invention may be implemented in software, hardware, firmware, etc. Regardless of whether the invention is implemented in software, hardware, or firmware, the instruction code may be stored in any type of computer accessible memory (e.g., permanent or modifiable, volatile or non-volatile, solid or non-solid, fixed or removable media, etc.). Also, the Memory may be, for example, programmable array logic (Programmable Array Logic, abbreviated as "PAL"), random access Memory (Random Access Memory, abbreviated as "RAM"), programmable Read-Only Memory (Programmable Read Only Memory, abbreviated as "PROM"), read-Only Memory (ROM), electrically erasable programmable Read-Only Memory (Electrically Erasable Programmable ROM, abbreviated as "EEPROM"), magnetic disk, optical disk, digital versatile disk (Digital Versatile Disc, abbreviated as "DVD"), and the like.
Fig. 7 illustrates a visual positioning system for visual editing according to an example embodiment of the present application, which may implement the visual positioning method described above. As shown in fig. 7, the visual positioning system includes a first acquisition module, a creation module, a detection module, a display module, and a construction module.
The first acquisition module is used for acquiring key frames of the scene image and characteristic information of the key frames, wherein the characteristic information comprises position information of the key frames. The first acquisition module may be any device capable of acquiring an image of a scene.
The creation module is used for creating a visual editing interface and displaying icons representing the key frames on the visual editing interface according to the position information of the key frames acquired by the first acquisition module. Icons representing key frames may be displayed and set as described above.
The detection module is used for detecting selection of icons representing key frames. When the detection module detects the selection of the icon representing the key frame, the display module is used for displaying the key frame and/or the characteristic information of the key frame for editing. In one embodiment, the visual positioning system may further include an editing module to edit the key frames and the feature information of the key frames, and the editing module may be implemented by any input device. In one embodiment, the editing module adds, moves, and/or removes key frames, and/or modifies feature information of key frames. In one embodiment, the feature information includes coordinates of the feature points, descriptors of the feature points, bag of words values of the feature points, and/or other information. In other embodiments, the editing module may perform other operations on the keyframes as desired.
If the key frame or the characteristic information of the key frame is edited, the construction module is used for constructing the visual positioning map through the edited key frame and the characteristic information of the key frame.
In the case that the above-mentioned visual positioning system is a SLAM system, by providing flexible implementation of the visual editing interface, it is possible to ensure recognition accuracy to adapt to complex and diverse environments while the mobile robot has a certain autonomy.
In various embodiments of the present application, each module may analyze and process each keyframe to facilitate viewing and editing.
In one embodiment, the creation module may be configured to form a keyframe list from a plurality of keyframes having the same location information and display an icon representing the keyframe list on the visual editing interface. The detection module is used for detecting selection of an icon representing a key frame list. When the detection module detects selection of an icon representing a key frame list, the display module is used for displaying a plurality of key frames in the key frame list and/or characteristic information of the plurality of key frames so as to edit. And forming a key frame list by a plurality of key frames with the same position information, so that batch processing can be conveniently carried out.
It can be appreciated that in other embodiments of the present application, other key frames with the same information may be combined to form a list, so as to facilitate batch processing.
The visual positioning system may also include an anomaly frame screening subsystem, fig. 8 illustrates a block diagram of the anomaly frame screening subsystem according to an example embodiment of the present application. As shown in fig. 8, the abnormal frame screening subsystem may include a comparison module, a second acquisition module, a first determination module, and a first calibration module.
The comparison module is used for comparing the feature information of each key frame in the key frame list with the feature information of other adjacent key frames in the key frame list in a similarity mode. The second acquisition module is used for acquiring the key frame with the highest similarity with the characteristic information of each key frame according to the comparison result of the comparison module.
The first judging module is used for judging whether the similarity difference between each key frame and the key frame with the highest similarity exceeds a first preset threshold value. The first calibration module is used for calibrating the keyframes, the similarity difference of which between the keyframes and the keyframes with the highest similarity is determined by the first judgment module and exceeds a first preset threshold value, as abnormal frames. And screening out the key frames with similarity differences with other key frames in the key frame list exceeding a first preset threshold value and calibrating the key frames as abnormal frames, so that the user can conveniently check the key frames.
In other embodiments, other feature information besides similarity may be used to perform screening or auxiliary screening, and may be set according to specific situations.
In one embodiment, when an abnormal frame exists, the creating module may be further configured to provide an abnormal frame list on the visual editing interface, where the abnormal frame list includes one or more abnormal frames calibrated by the first calibration module. The creation module may display an abnormal frame list including abnormal frames on either side of the visual editing interface. In one embodiment, the creation module may display, as a reference, the anomaly information for each anomaly frame, such as how much the similarity exceeds, etc., in the anomaly frame list.
The detection module is used for detecting the selection of the abnormal frame list. When the detection module detects the selection of the abnormal frame list, the display module is used for displaying icons representing the key frame list containing the abnormal frames on the visual editing interface in a mode different from the key frame list not containing the abnormal frames. Icons representing a list of keyframes containing an abnormal frame and icons representing a list of keyframes not containing an abnormal frame may be displayed in the manner as described above, thereby facilitating viewing and editing. When abnormality information of a plurality of abnormality frames is simultaneously viewed, the overall situation can be roughly understood.
In one embodiment, a key frame may be associated with a neighboring key frame. For example, the characteristic information may further include displacement and deflection information of the key frame and the adjacent key frame, and the key frame and the adjacent key frame may be connected in association through the displacement and deflection information.
The creation module may be configured to display a link on the visual editing interface connecting an icon representing a key frame with an icon representing an adjacent key frame.
The detection module is used for detecting the selection of the connecting line. When the detection module detects the selection of the connection, the display module is used for displaying displacement and deflection information of the key frame and the adjacent key frame for editing. In one embodiment, the visual positioning system may further comprise an editing module to edit displacement and deflection information of the keyframe and the neighboring keyframes. In one embodiment, the editing module adds, moves, and/or removes links of key frames to neighboring key frames, and/or modifies displacement and deflection information of key frames to neighboring key frames. In another embodiment, when the key frame is connected to the adjacent key frame through a connection line, the editing module edits the feature information of the key frame, and at the same time, the editing module may correspondingly edit the feature information of the adjacent key frame according to the connection information of the key frame and the adjacent key frame, for example, may correspondingly edit the feature information of the adjacent key frame according to displacement and deflection information of the key frame and the adjacent key frame.
If the displacement and deflection information of the key frame and the adjacent key frame is edited, the construction module is used for constructing the visual positioning map through the displacement and deflection information of the edited key frame and the adjacent key frame.
In other embodiments, the key frame may be connected with other information of the adjacent key frame as required, and the connection is not limited to the displacement and deflection information. By connecting a keyframe with an adjacent keyframe, the relationship between two keyframes can be easily viewed and adjusted.
The visual localization system may also include an abnormal wire screening subsystem, fig. 9 shows a block diagram of the abnormal wire screening subsystem, according to an example embodiment of the present application. As shown in fig. 9, the abnormal connection screening subsystem may include a second determination module and a second calibration module.
The second judging module is used for judging whether the feature point matching pair number of the key frame and the adjacent key frame exceeds a second preset threshold value. The second calibration module is used for calibrating the connection lines of the key frames, the number of which does not exceed a second preset threshold, and the adjacent key frames, which are determined by the second judgment module, as abnormal connection lines. And screening out the connecting lines with the number of the feature point matching pairs smaller than a second preset threshold value, and calibrating the connecting lines as abnormal connecting lines, so that the user can check conveniently.
In other embodiments, when connecting with other information of neighboring key frames through a key frame, the abnormal connection screening subsystem may screen abnormal connections through other information.
In one embodiment, when there is an abnormal connection, the creating module may be further configured to provide an abnormal connection list on the visual editing interface, where the abnormal connection list includes one or more abnormal connections calibrated by the second calibration module. The creation module may display an abnormal wire list including abnormal wires on either side of the visual editing interface. In one embodiment, the creation module may display, as a reference, the anomaly information for each anomaly wire in the anomaly wire list, such as how much the feature point matching pair number is worse.
The detection module is used for detecting the selection of the abnormal connection list. When the detection module detects the selection of the abnormal connection list, the display module is used for displaying one or more abnormal connection lines on the visual editing interface in a mode different from the non-abnormal connection lines. The abnormal links and non-abnormal links may be displayed in the manner as described above to facilitate viewing and editing. When abnormality information of a plurality of abnormal links is simultaneously viewed, the overall situation can be roughly understood.
The above exemplary listing of the modules analyzing the keyframes, it is understood that the modules may also perform other analysis on the keyframes for ease of viewing and editing.
FIG. 10 illustrates a visual editing interface according to one exemplary embodiment of the present application. As shown in fig. 10, each circular icon represents a key frame, and adjacent circular icons are connected by a connecting line. When one circular icon is selected, such as a fourth circular icon on the left side, the key frame and feature information of the key frame, such as attribute 1, attribute 2, attribute 3 …, are displayed on the visual editing interface; when a connection is selected, such as the left penultimate connection, displacement deflection information is displayed on the visual editing interface.
In the visual editing interface shown in fig. 10, when a plurality of key frames form a key frame list, the key frame list is represented by icons of large circles and small circles. Displaying an abnormal frame list and an abnormal link list on the right side of the visual editing interface, wherein when the abnormal frame list is selected, the corresponding abnormal frame (such as abnormal frame 1-2) is displayed as a black circle so as to be distinguished from the non-abnormal frame, and a small circle in an icon representing a key frame list containing the abnormal frame (such as abnormal frame 3) is displayed as a black circle so as to be distinguished from an icon of the key frame list not containing the abnormal frame; when the list of abnormal links is selected, the corresponding abnormal links (e.g., abnormal links 1-3) are thickened to distinguish from the non-abnormal links. By highlighting the abnormal frames, a key frame list containing the abnormal frames and the abnormal connection lines on the visual editing interface, the visual editing interface can be conveniently checked and edited.
It will be appreciated that the visual editing interface of fig. 10 is merely an example. In other embodiments of the present application, other forms of visual editing interfaces may be provided.
It should be noted that, in the embodiments of the systems of the present invention, each unit and/or module is a logic unit and/or module, and in physical terms, one logic unit and/or module may be a physical unit and/or module, or may be a part of one physical unit and/or module, or may be implemented by a combination of multiple physical units and/or modules, where the physical implementation manner of the logic unit and/or module is not the most important, and the combination of functions implemented by the logic unit and/or module is the key to solving the technical problem posed by the present invention. Furthermore, to highlight the innovative portions of the present invention, the various system embodiments of the present invention described above do not introduce elements and/or modules that are less closely related to solving the technical problems presented by the present invention, which does not indicate that other elements and/or modules are not present in the system embodiments described above.
It should be noted that in the claims and the description of the present application, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, 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" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element
All documents mentioned in this application are incorporated by reference as if each were individually incorporated by reference. Further, it will be appreciated that various changes and modifications may be made by those skilled in the art after reading the above teachings, and such equivalents are intended to fall within the scope of the claims appended hereto.
Claims (18)
1. A visual positioning method for visual editing, comprising the steps of:
acquiring a key frame of a scene image and characteristic information of the key frame, wherein the characteristic information comprises position information of the key frame;
creating a visual editing interface, and displaying an icon representing the key frame on the visual editing interface according to the position information of the key frame;
displaying the key frame and/or characteristic information of the key frame for editing after detecting selection of an icon representing the key frame; and
constructing a visual positioning map through the edited key frames and/or the characteristic information of the key frames;
wherein in the step of displaying icons representing the key frames on the visual editing interface according to the position information of the key frames, forming a key frame list from a plurality of key frames with the same position information and displaying icons representing the key frame list on the visual editing interface;
Displaying the key frames and/or characteristic information of the key frames for editing after detecting selection of the icons representing the key frames, and displaying the key frames and/or the characteristic information of the key frames in the key frame list for editing after detecting selection of the icons representing the key frame list;
the visual positioning method for visual editing further comprises the following steps:
comparing the feature information of each key frame in the key frame list with the feature information of other adjacent key frames in the key frame list in a similarity manner;
obtaining a key frame with highest similarity with the characteristic information of each key frame according to the comparison result;
judging whether the similarity difference between each key frame and the key frame with the highest similarity exceeds a first preset threshold value; and
and marking the key frame with the similarity difference exceeding the first preset threshold value with the key frame with the highest similarity as an abnormal frame.
2. The visual positioning method for visual editing according to claim 1, wherein the visual positioning method is an instant positioning and map construction method.
3. The visual localization method of claim 1, further comprising the steps of:
Providing an abnormal frame list on the visual editing interface, wherein the abnormal frame list comprises one or more abnormal frames; and
upon detecting a selection of the list of abnormal frames, an icon representing a list of key frames containing abnormal frames is displayed on the visual editing interface in a different manner than a list of key frames not containing abnormal frames.
4. The visual localization method of claim 1, wherein the characteristic information further comprises displacement and deflection information of the key frame from an adjacent key frame;
after the step of displaying the icon representing the key frame on the visual editing interface according to the position information of the key frame, the method further comprises the following steps:
displaying a connecting line for connecting the icon representing the key frame and the icon representing the adjacent key frame on the visual editing interface;
after detecting the selection of the connection, displaying displacement and deflection information of the key frame and the adjacent key frame for editing; and
and constructing the visual positioning map through the edited displacement and deflection information of the key frame and the adjacent key frame.
5. The visual localization method of claim 4, further comprising the steps of:
Judging whether the feature point matching pair number of the key frame and the adjacent key frame exceeds a second preset threshold value; and
and marking the connecting lines of the key frames, the number of which does not exceed the second preset threshold, of the feature point matching pair and the adjacent key frames as abnormal connecting lines.
6. The visual localization method of claim 5, further comprising the steps of:
providing an abnormal connection list on the visual editing interface, wherein the abnormal connection list comprises one or more abnormal connection lines; and
and after the selection of the abnormal connection list is detected, displaying one or more abnormal connection lines on the visual editing interface in a mode different from the non-abnormal connection lines.
7. The visual positioning method for visual editing according to claim 4, wherein after the step of displaying the key frame and/or the feature information of the key frame for editing after detecting the selection of the icon representing the key frame, further comprising the step of editing the feature information of the key frame while editing the feature information of the adjacent key frame according to the displacement and deflection information of the key frame and the adjacent key frame.
8. Visual localization method of a visual edit according to any of claims 1-7, characterized in that the editing of the key frame and/or feature information of the key frame comprises adding, moving and/or removing the key frame and/or modifying feature information of the key frame, wherein the feature information comprises coordinates of feature points, descriptors of feature points and/or bag of words values of feature points.
9. Visual localization method of a visual edit according to any of claims 4-7, characterized in that the editing of the key frames and/or characteristic information of the key frames comprises adding, moving and/or removing lines of the key frames with neighboring key frames and/or modifying displacement and deflection information of the key frames with neighboring key frames.
10. A visual positioning system for visual editing, the visual positioning system comprising:
the first acquisition module is used for acquiring a key frame of a scene image and characteristic information of the key frame, wherein the characteristic information comprises position information of the key frame;
the creation module is used for creating a visual editing interface and displaying icons representing the key frames on the visual editing interface according to the position information of the key frames acquired by the first acquisition module;
A detection module for detecting a selection of an icon representing the keyframe;
the display module is used for displaying the key frames and/or the characteristic information of the key frames for editing after the detection module detects the selection of the icons representing the key frames; and
the construction module is used for constructing a visual positioning map through the edited key frames and/or the characteristic information of the key frames;
the creation module is further used for forming a plurality of key frames with the same position information into a key frame list and displaying icons representing the key frame list on the visual editing interface;
the detection module is further configured to detect a selection of an icon representing the keyframe list;
the display module is further used for displaying a plurality of key frames in the key frame list and/or characteristic information of the plurality of key frames for editing after the detection module detects the selection of the icon representing the key frame list;
the visual positioning system further comprises:
the comparison module is used for comparing the similarity between the characteristic information of each key frame in the key frame list and the characteristic information of other adjacent key frames in the key frame list;
The second acquisition module is used for acquiring the key frame with the highest similarity with the characteristic information of each key frame according to the comparison result of the comparison module;
the first judging module is used for judging whether the similarity difference between each key frame and the key frame with the highest similarity exceeds a first preset threshold value; and
and the first calibration module is used for calibrating the keyframes, the similarity difference of which between the keyframes and the keyframes with the highest similarity is determined by the first judgment module and exceeds the first preset threshold value, as abnormal frames.
11. The visual positioning system of claim 10, wherein the visual positioning system is an instant positioning and mapping system.
12. The visual positioning system of claim 10, wherein the creation module is further configured to provide a list of outlier frames on the visual editing interface, the list of outlier frames including one or more of the outlier frames scaled by the first scaling module;
the detection module is also used for detecting the selection of the abnormal frame list;
the display module is further configured to display, on the visual editing interface, an icon representing a keyframe list containing an abnormal frame in a manner different from a keyframe list not containing the abnormal frame after the detection module detects the selection of the abnormal frame list.
13. The visual positioning system of claim 10, wherein the characteristic information further comprises displacement and deflection information of the keyframe from an adjacent keyframe;
the creation module is further used for displaying a connecting line for connecting the icon representing the key frame and the icon representing the adjacent key frame on the visual editing interface;
the detection module is also used for detecting the selection of the connecting line;
the display module is also used for displaying displacement and deflection information of the key frame and the adjacent key frame for editing after the detection module detects the selection of the connecting line;
the construction module is also used for constructing the visual positioning map through the edited displacement and deflection information of the key frame and the adjacent key frame.
14. The visual positioning system of claim 13, wherein the visual positioning system further comprises:
the second judging module is used for judging whether the characteristic point matching pair number of the key frame and the adjacent key frame exceeds a second preset threshold value; and
and the second calibration module is used for calibrating the connecting lines of the key frames, the number of which does not exceed the second preset threshold value, of the key frames and the adjacent key frames, which are determined by the second judgment module, as abnormal connecting lines.
15. The visual positioning system of claim 14, wherein the creation module is further configured to provide an abnormal connection list on the visual editing interface, the abnormal connection list including one or more of the abnormal connections calibrated by the second calibration module;
the detection module is also used for detecting the selection of the abnormal connection list;
the display module is further used for displaying one or more abnormal connecting lines on the visual editing interface in a mode different from the non-abnormal connecting lines after the detection module detects the selection of the abnormal connecting line list.
16. The visual positioning system of claim 13, further comprising an editing module for editing the characteristic information of the key frame in accordance with the displacement and deflection information of the key frame and the adjacent key frame while editing the characteristic information of the key frame.
17. Visual positioning system for visual editing according to any of claims 10 to 16, further comprising an editing module for adding, moving and/or removing the key frames and/or modifying feature information of the key frames, wherein the feature information comprises coordinates of feature points, descriptors of feature points and/or bag of words values of feature points.
18. Visual positioning system for visual editing according to any of claims 13 to 16, further comprising an editing module for adding, moving and/or removing lines of the key frame with neighboring key frames and/or modifying displacement and deflection information of the key frame with neighboring key frames.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811189739.6A CN111046698B (en) | 2018-10-12 | 2018-10-12 | Visual positioning method and system for visual editing |
| PCT/CN2019/108294 WO2020073818A1 (en) | 2018-10-12 | 2019-09-26 | Visual localization method and system for visual editing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811189739.6A CN111046698B (en) | 2018-10-12 | 2018-10-12 | Visual positioning method and system for visual editing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111046698A CN111046698A (en) | 2020-04-21 |
| CN111046698B true CN111046698B (en) | 2023-06-20 |
Family
ID=70164154
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811189739.6A Active CN111046698B (en) | 2018-10-12 | 2018-10-12 | Visual positioning method and system for visual editing |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111046698B (en) |
| WO (1) | WO2020073818A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112817789B (en) * | 2021-02-23 | 2023-01-31 | 浙江大华技术股份有限公司 | Modeling method and device based on browser transmission |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105247573A (en) * | 2013-06-11 | 2016-01-13 | 高通股份有限公司 | Interactive and automatic 3-d object scanning method for the purpose of database creation |
| CN107301402A (en) * | 2017-06-30 | 2017-10-27 | 锐捷网络股份有限公司 | A kind of determination method, device, medium and the equipment of reality scene key frame |
| CN107369183A (en) * | 2017-07-17 | 2017-11-21 | 广东工业大学 | Towards the MAR Tracing Registration method and system based on figure optimization SLAM |
| CN108267121A (en) * | 2018-01-24 | 2018-07-10 | 锥能机器人（上海）有限公司 | The vision navigation method and system of more equipment under a kind of variable scene |
| CN108375979A (en) * | 2018-02-10 | 2018-08-07 | 浙江工业大学 | Self-navigation robot general-purpose control system based on ROS |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101968908B1 (en) * | 2015-01-22 | 2019-04-15 | 한국전자통신연구원 | Apparatus and method for providing primitive visual knowledge |
| WO2018048353A1 (en) * | 2016-09-09 | 2018-03-15 | Nanyang Technological University | Simultaneous localization and mapping methods and apparatus |
| CN107194991B (en) * | 2017-05-17 | 2021-01-01 | 西南科技大学 | Three-dimensional global visual monitoring system construction method based on skeleton point local dynamic update |
| CN108648274B (en) * | 2018-05-10 | 2020-05-22 | 华南理工大学 | Cognitive point cloud map creating system of visual SLAM |
| CN108648270B (en) * | 2018-05-12 | 2022-04-19 | 西北工业大学 | Unmanned aerial vehicle real-time three-dimensional scene reconstruction method capable of realizing real-time synchronous positioning and map construction |
-
2018
- 2018-10-12 CN CN201811189739.6A patent/CN111046698B/en active Active
-
2019
- 2019-09-26 WO PCT/CN2019/108294 patent/WO2020073818A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105247573A (en) * | 2013-06-11 | 2016-01-13 | 高通股份有限公司 | Interactive and automatic 3-d object scanning method for the purpose of database creation |
| CN107301402A (en) * | 2017-06-30 | 2017-10-27 | 锐捷网络股份有限公司 | A kind of determination method, device, medium and the equipment of reality scene key frame |
| CN107369183A (en) * | 2017-07-17 | 2017-11-21 | 广东工业大学 | Towards the MAR Tracing Registration method and system based on figure optimization SLAM |
| CN108267121A (en) * | 2018-01-24 | 2018-07-10 | 锥能机器人（上海）有限公司 | The vision navigation method and system of more equipment under a kind of variable scene |
| CN108375979A (en) * | 2018-02-10 | 2018-08-07 | 浙江工业大学 | Self-navigation robot general-purpose control system based on ROS |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111046698A (en) | 2020-04-21 |
| WO2020073818A1 (en) | 2020-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10937144B2 (en) | Pipe feature identification using pipe inspection data analysis | |
| EP3270134B1 (en) | Gas leak location estimating device, gas leak location estimating system, gas leak location estimating method and gas leak location estimating program | |
| US20060029276A1 (en) | Object image detecting apparatus, face image detecting program and face image detecting method | |
| US9513621B2 (en) | Manipulation monitoring device and manipulation monitoring method | |
| CN109727275B (en) | Object detection method, device, system and computer readable storage medium | |
| US8483859B2 (en) | Image processing device and image processing method | |
| US11645851B2 (en) | Method of processing image data in a connectionist network | |
| CN111598913B (en) | Image segmentation method and system based on robot vision | |
| JPH06175715A (en) | Visual sensor coordinate system setting jig and setting method therefor | |
| US10339690B2 (en) | Image recognition scoring visualization | |
| CN111149129A (en) | Abnormality detection device and abnormality detection method | |
| AU2020351974B2 (en) | Fish counting system, fish counting method, and program | |
| US9256792B2 (en) | Image processing apparatus, image processing method, and program | |
| CN111046698B (en) | Visual positioning method and system for visual editing | |
| JP7422548B2 (en) | Label noise detection program, label noise detection method, and label noise detection device | |
| US20120237118A1 (en) | Image processing device, image processing method, and image processing program | |
| JP4993678B2 (en) | Interactive moving image monitoring method, interactive moving image monitoring apparatus, and interactive moving image monitoring program | |
| US10514825B2 (en) | Image recognition result visualization over time | |
| CN112509033B (en) | Automatic iron tower inclination detection method and device based on image processing | |
| JP2022009474A (en) | System and method for detecting lines in vision system | |
| CN111444834A (en) | Image text line detection method, device, equipment and storage medium | |
| CN115802012A (en) | Video overlapping method and system for container cargo content dome camera | |
| US20200272224A1 (en) | Method of generating a virtual overlay for a packaging machine | |
| JP2021128415A (en) | Machine learning method and information processing device for machine learning | |
| JP2008269264A (en) | Method, device and program for tracking multiconductor cable by image processing, and method, device and program for detecting abnormality of multiconductor cable using the same |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40026925 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |