CN109241964A - The acquisition methods and equipment of the crawl point of mechanical arm - Google Patents
The acquisition methods and equipment of the crawl point of mechanical arm Download PDFInfo
- Publication number
- CN109241964A CN109241964A CN201810942396.XA CN201810942396A CN109241964A CN 109241964 A CN109241964 A CN 109241964A CN 201810942396 A CN201810942396 A CN 201810942396A CN 109241964 A CN109241964 A CN 109241964A
- Authority
- CN
- China
- Prior art keywords
- picture
- stereo
- mechanical arm
- scanning
- stereotome
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The object of the present invention is to provide the acquisition methods and equipment of a kind of crawl of mechanical arm point, the present invention utilizes the movement of mechanical arm itself, carries out single pass to object, the stereo-picture of object can be obtained, construction body three-dimensional models, the collecting method is efficient, and effect is good.In addition, going out the emulation picture under actual scene by object dimensional model rendering, the advantages that object pose information, this method have speed fast, and effect is good, robust is predicted based on analogous diagram one deep neural network of training.
Description
Technical field
The present invention relates to the acquisition methods and equipment of a kind of crawl of computer field more particularly to mechanical arm point.
Background technique
Intelligent robot as the mankind grab object, is needed according to object to identify target object from complex scene
The posture of body selects suitable grasp mode, this is a basic function of intelligent robot.Therefore a kind of vision positioning is designed
System not only can accurately identify target object, and can judge its posture have very wide application prospect.
As long as current robot carries out knowing when grabbing object there are two types of method for distinguishing, one is utilize laser radar scanning object
Body obtains threedimensional model, then carries out template matching by threedimensional model and obtain object pose, and carry out robot crawl based on this
Planning.There are two disadvantages for this method, first is that laser radar price is high, and needs people to be manually operated and carry out three-dimensional modeling, mistake
Journey is cumbersome.Second the disadvantage is that the object pose estimating speed based on template matching is slower, while can not handle partial occlusion
The case where.
Summary of the invention
It is an object of the present invention to provide the acquisition methods and equipment of a kind of crawl of mechanical arm point.
According to an aspect of the invention, there is provided a kind of acquisition methods of the crawl point of mechanical arm, this method comprises:
Mechanical arm carries out stereoscan around object to be scanned, obtains object stereo-picture with scanning;
Front and back scape segmentation based on depth map is carried out to the object stereo-picture that scanning obtains, after obtaining background
Object stereotome;
According to the object stereotome reconstruction of objects threedimensional model after the background;
Using the emulation picture under the object dimensional model rendering actual scene, generated according to the emulation picture default
The training sample of quantity, based on training sample training deep neural network;
In the actual scene, the current stereo-picture of object is obtained, current stereo-picture is inputted into the depth mind
Through network, the posture information of the object in the current stereo-picture is calculated by the deep neural network, according to calculating
The posture information of the object arrived obtains mechanical arm and grabs point.
Further, in the above method, mechanical arm carries out stereoscan around object to be scanned, obtains object with scanning
Stereo-picture, comprising:
Mechanical arm carries out the stereoscan at each visual angle around object to be scanned, obtains the object at each visual angle with scanning
Stereo-picture.
Further, in the above method, according to the object stereotome reconstruction of objects threedimensional model gone after background, packet
It includes:
Using fast fusion, according to the object stereotome reconstruction of objects threedimensional model gone after background.
Further, in the above method, using in the emulation picture under the object dimensional model rendering actual scene,
The posture information of the emulation picture inclusion body.
According to another aspect of the present invention, a kind of acquisition equipment of the crawl point of mechanical arm is additionally provided, which includes:
Scanning means obtains object solid for making mechanical arm carry out stereoscan around object to be scanned with scanning
Image;
Processing unit, the object stereo-picture for obtaining to scanning carry out the front and back scape based on depth map and divide,
Object stereotome after obtaining background;
Model building device, for according to the object stereotome reconstruction of objects threedimensional model after the background;
Training device, for being imitated according to described using the emulation picture under the object dimensional model rendering actual scene
True picture generates the training sample of preset quantity, based on training sample training deep neural network;
Computing device, it is for obtaining the current stereo-picture of object in the actual scene, current stereo-picture is defeated
Enter the deep neural network, is believed by the pose that the deep neural network calculates the object in the current stereo-picture
Breath obtains mechanical arm according to the posture information for the object being calculated and grabs point.
Further, in above equipment, the scanning means, for keeping mechanical arm each around object progress to be scanned
The stereoscan at visual angle obtains the object stereo-picture at each visual angle with scanning.
Further, in above equipment, the model building device, for utilize fast fusion, according to it is described go background after
Object stereotome reconstruction of objects threedimensional model.
Further, in above equipment, the posture information of the emulation picture inclusion body.
According to the another side of the application, a kind of equipment based on calculating is also provided, comprising:
Processor;And
It is arranged to the memory of storage computer executable instructions, the executable instruction makes the place when executed
Manage device:
Mechanical arm carries out stereoscan around object to be scanned, obtains object stereo-picture with scanning;
Front and back scape segmentation based on depth map is carried out to the object stereo-picture that scanning obtains, after obtaining background
Object stereotome;
According to the object stereotome reconstruction of objects threedimensional model after the background;
Using the emulation picture under the object dimensional model rendering actual scene, generated according to the emulation picture default
The training sample of quantity, based on training sample training deep neural network;
In the actual scene, the current stereo-picture of object is obtained, current stereo-picture is inputted into the depth mind
Through network, the posture information of the object in the current stereo-picture is calculated by the deep neural network, according to calculating
The posture information of the object arrived obtains mechanical arm and grabs point.
According to the another side of the application, a kind of computer readable storage medium is also provided, computer is stored thereon with
Executable instruction, the computer executable instructions make the processor when being executed by processor:
Mechanical arm carries out stereoscan around object to be scanned, obtains object stereo-picture with scanning;
Front and back scape segmentation based on depth map is carried out to the object stereo-picture that scanning obtains, after obtaining background
Object stereotome;
According to the object stereotome reconstruction of objects threedimensional model after the background;
Using the emulation picture under the object dimensional model rendering actual scene, generated according to the emulation picture default
The training sample of quantity, based on training sample training deep neural network;
In the actual scene, the current stereo-picture of object is obtained, current stereo-picture is inputted into the depth mind
Through network, the posture information of the object in the current stereo-picture is calculated by the deep neural network, according to calculating
The posture information of the object arrived obtains mechanical arm and grabs point.
Compared with prior art, the present invention utilizes the movement of mechanical arm itself, carries out single pass to object, can be obtained
The stereo-picture of object, construction body three-dimensional models, the collecting method is efficient, and effect is good.In addition, passing through object dimensional mould
Type renders the emulation picture under actual scene, predicts object pose information based on analogous diagram one deep neural network of training,
The advantages that this method has speed fast, and effect is good, robust.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, of the invention other
Feature, objects and advantages will become more apparent upon:
Fig. 1 shows a kind of flow chart of the acquisition methods of the crawl point of mechanical arm of one aspect according to the present invention.
The same or similar appended drawing reference represents the same or similar component in attached drawing.
Specific embodiment
Present invention is further described in detail with reference to the accompanying drawing.
In a typical configuration of this application, terminal, the equipment of service network and trusted party include one or more
Processor (CPU), input/output interface, network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flashRAM).Memory is showing for computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or
Any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, computer
Readable medium does not include non-temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
As shown in Figure 1, the present invention provides a kind of acquisition methods of the crawl point of mechanical arm, which comprises
Step S1, mechanical arm carry out stereoscan around object to be scanned, obtain object stereo-picture with scanning;
Step S2 carries out the front and back scape based on depth map to the object stereo-picture that scanning obtains and divides, gone
Object stereotome after background;
Step S3, according to the object stereotome reconstruction of objects threedimensional model after the background;
Step S4, using the emulation picture under the object dimensional model rendering actual scene, according to the emulation picture
The training sample for generating preset quantity, based on training sample training deep neural network;
Step S5 obtains the current stereo-picture of object in the actual scene, currently will input institute to stereo-picture
Deep neural network is stated, the posture information of the object in the current stereo-picture, root are calculated by the deep neural network
Mechanical arm, which is obtained, according to the posture information for the object being calculated grabs point.
Here, the present invention utilizes the movement of mechanical arm itself, single pass is carried out to object, the solid of object can be obtained
Image, construction body three-dimensional models, the collecting method is efficient, and effect is good.In addition, being gone out by object dimensional model rendering real
Emulation picture under the scene of border predicts that object pose information, this method have based on analogous diagram one deep neural network of training
The advantages that speed is fast, and effect is good, robust.
In one embodiment of acquisition methods of the crawl point of mechanical arm of the invention, step S1, mechanical arm is around to be scanned
Object carries out stereoscan, obtains object stereo-picture with scanning, comprising:
Mechanical arm carries out the stereoscan at each visual angle around object to be scanned, obtains the object at each visual angle with scanning
Stereo-picture.
Here, carrying out single pass i.e. using the movement of mechanical arm itself to object, each visual angle of object can be obtained
Object stereo-picture can construct more accurate object dimensional model according to the object stereo-picture at each visual angle of object.
Mechanical arm of the invention crawl point one embodiment of acquisition methods in, step S3, according to it is described go background after
Object stereotome reconstruction of objects threedimensional model, comprising:
Using fast fusion or similar algorithm, according to the object stereotome reconstruction of objects three gone after background
Dimension module.
Here, FastFusion is the algorithm for being served only for SLAM modeling, depth image, rgb image and pose are inputted
It can be in Real-time modeling set under CPU.It, can more rapidly efficient reconstruction of objects threedimensional model using fast fusion algorithm.
In one embodiment of acquisition methods of the crawl point of mechanical arm of the invention, step S4 utilizes the object dimensional mould
Type renders in the emulation picture under actual scene,
The posture information of the emulation picture inclusion body.
It include pair in the emulation picture here, going out the emulation picture under actual scene by object dimensional model rendering
The object pose information answered can train a more accurate depth nerve net according to the object pose information in emulation picture
Network, to predict the advantages that posture information of object, this method have speed fast, and effect is good, robust.
According to another aspect of the present invention, a kind of acquisition equipment of the crawl point of mechanical arm is additionally provided, which includes:
Scanning means obtains object solid for making mechanical arm carry out stereoscan around object to be scanned with scanning
Image;
Processing unit, the object stereo-picture for obtaining to scanning carry out the front and back scape based on depth map and divide,
Object stereotome after obtaining background;
Model building device, for according to the object stereotome reconstruction of objects threedimensional model after the background;
Training device, for being imitated according to described using the emulation picture under the object dimensional model rendering actual scene
True picture generates the training sample of preset quantity, based on training sample training deep neural network;
Computing device, it is for obtaining the current stereo-picture of object in the actual scene, current stereo-picture is defeated
Enter the deep neural network, is believed by the pose that the deep neural network calculates the object in the current stereo-picture
Breath obtains mechanical arm according to the posture information for the object being calculated and grabs point.
Further, in above equipment, the scanning means, for keeping mechanical arm each around object progress to be scanned
The stereoscan at visual angle obtains the object stereo-picture at each visual angle with scanning.
Further, in above equipment, the model building device, for utilize fast fusion, according to it is described go background after
Object stereotome reconstruction of objects threedimensional model.
Further, in above equipment, the posture information of the emulation picture inclusion body.
According to the another side of the application, a kind of equipment based on calculating is also provided, comprising:
Processor;And
It is arranged to the memory of storage computer executable instructions, the executable instruction makes the place when executed
Manage device:
Mechanical arm carries out stereoscan around object to be scanned, obtains object stereo-picture with scanning;
Front and back scape segmentation based on depth map is carried out to the object stereo-picture that scanning obtains, after obtaining background
Object stereotome;
According to the object stereotome reconstruction of objects threedimensional model after the background;
Using the emulation picture under the object dimensional model rendering actual scene, generated according to the emulation picture default
The training sample of quantity, based on training sample training deep neural network;
In the actual scene, the current stereo-picture of object is obtained, current stereo-picture is inputted into the depth mind
Through network, the posture information of the object in the current stereo-picture is calculated by the deep neural network, according to calculating
The posture information of the object arrived obtains mechanical arm and grabs point.
According to the another side of the application, a kind of computer readable storage medium is also provided, computer is stored thereon with
Executable instruction, the computer executable instructions make the processor when being executed by processor:
Mechanical arm carries out stereoscan around object to be scanned, obtains object stereo-picture with scanning;
Front and back scape segmentation based on depth map is carried out to the object stereo-picture that scanning obtains, after obtaining background
Object stereotome;
According to the object stereotome reconstruction of objects threedimensional model after the background;
Using the emulation picture under the object dimensional model rendering actual scene, generated according to the emulation picture default
The training sample of quantity, based on training sample training deep neural network;
In the actual scene, the current stereo-picture of object is obtained, current stereo-picture is inputted into the depth mind
Through network, the posture information of the object in the current stereo-picture is calculated by the deep neural network, according to calculating
The posture information of the object arrived obtains mechanical arm and grabs point.
The detailed content of above-mentioned each equipment, each embodiment of storage medium can specifically participate in the correspondence portion of each method embodiment
Point, here, not repeating.
Obviously, those skilled in the art can carry out various modification and variations without departing from the essence of the application to the application
Mind and range.In this way, if these modifications and variations of the application belong to the range of the claim of this application and its equivalent technologies
Within, then the application is also intended to include these modifications and variations.
It should be noted that the present invention can be carried out in the assembly of software and/or software and hardware, for example, can adopt
With specific integrated circuit (ASIC), general purpose computer or any other realized similar to hardware device.In one embodiment
In, software program of the invention can be executed to implement the above steps or functions by processor.Similarly, of the invention
Software program (including relevant data structure) can be stored in computer readable recording medium, for example, RAM memory,
Magnetic or optical driver or floppy disc and similar devices.In addition, some of the steps or functions of the present invention may be implemented in hardware, example
Such as, as the circuit cooperated with processor thereby executing each step or function.
In addition, a part of the invention can be applied to computer program product, such as computer program instructions, when its quilt
When computer executes, by the operation of the computer, it can call or provide according to the method for the present invention and/or technical solution.
And the program instruction of method of the invention is called, it is possibly stored in fixed or moveable recording medium, and/or pass through
Broadcast or the data flow in other signal-bearing mediums and transmitted, and/or be stored according to described program instruction operation
In the working storage of computer equipment.Here, according to one embodiment of present invention including a device, which includes using
Memory in storage computer program instructions and processor for executing program instructions, wherein when the computer program refers to
When enabling by processor execution, method and/or skill of the device operation based on aforementioned multiple embodiments according to the present invention are triggered
Art scheme.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included in the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.This
Outside, it is clear that one word of " comprising " does not exclude other units or steps, and odd number is not excluded for plural number.That states in device claim is multiple
Unit or device can also be implemented through software or hardware by a unit or device.The first, the second equal words are used to table
Show title, and does not indicate any particular order.
Claims (10)
1. a kind of acquisition methods of the crawl point of mechanical arm, wherein this method comprises:
Mechanical arm carries out stereoscan around object to be scanned, obtains object stereo-picture with scanning;
Front and back scape segmentation based on depth map is carried out to the object stereo-picture that scanning obtains, the object after obtaining background
Stereotome;
According to the object stereotome reconstruction of objects threedimensional model after the background;
Using the emulation picture under the object dimensional model rendering actual scene, preset quantity is generated according to the emulation picture
Training sample, based on the training sample training deep neural network;
In the actual scene, the current stereo-picture of object is obtained, current stereo-picture is inputted into the depth nerve net
Network calculates the posture information of the object in the current stereo-picture by the deep neural network, according to what is be calculated
The posture information of the object obtains mechanical arm and grabs point.
2. according to the method described in claim 1, wherein, mechanical arm carries out stereoscan around object to be scanned, with scanning
Obtain object stereo-picture, comprising:
Mechanical arm carries out the stereoscan at each visual angle around object to be scanned, obtains the object solid at each visual angle to scan
Image.
3. according to the method described in claim 1, wherein, going the object stereotome reconstruction of objects after background three-dimensional according to described
Model, comprising:
Using fast fusion, according to the object stereotome reconstruction of objects threedimensional model gone after background.
4. method according to any one of claims 1 to 3, wherein utilize the object dimensional model rendering actual scene
Under emulation picture in,
The posture information of the emulation picture inclusion body.
5. a kind of acquisition equipment of the crawl point of mechanical arm, wherein the equipment includes:
Scanning means obtains object stereo-picture for making mechanical arm carry out stereoscan around object to be scanned with scanning;
Processing unit, the object stereo-picture for obtaining to scanning carry out the front and back scape based on depth map and divide, obtain
Object stereotome after going background;
Model building device, for according to the object stereotome reconstruction of objects threedimensional model after the background;
Training device, for utilizing the emulation picture under the object dimensional model rendering actual scene, according to the analogous diagram
Piece generates the training sample of preset quantity, based on training sample training deep neural network;
Current stereo-picture is inputted institute for obtaining the current stereo-picture of object in the actual scene by computing device
Deep neural network is stated, the posture information of the object in the current stereo-picture, root are calculated by the deep neural network
Mechanical arm, which is obtained, according to the posture information for the object being calculated grabs point.
6. equipment according to claim 5, wherein the scanning means, for making mechanical arm around object to be scanned
The stereoscan at each visual angle is carried out, the object stereo-picture at each visual angle is obtained with scanning.
7. equipment according to claim 5, wherein the model building device, for utilizing fast fusion, according to described
Object stereotome reconstruction of objects threedimensional model after going background.
8. according to the described in any item equipment of claim 5 to 7, wherein the posture information of the emulation picture inclusion body.
9. a kind of equipment based on calculating, wherein include:
Processor;And
It is arranged to the memory of storage computer executable instructions, the executable instruction makes the processing when executed
Device:
Mechanical arm carries out stereoscan around object to be scanned, obtains object stereo-picture with scanning;
Front and back scape segmentation based on depth map is carried out to the object stereo-picture that scanning obtains, the object after obtaining background
Stereotome;
According to the object stereotome reconstruction of objects threedimensional model after the background;
Using the emulation picture under the object dimensional model rendering actual scene, preset quantity is generated according to the emulation picture
Training sample, based on the training sample training deep neural network;
In the actual scene, the current stereo-picture of object is obtained, current stereo-picture is inputted into the depth nerve net
Network calculates the posture information of the object in the current stereo-picture by the deep neural network, according to what is be calculated
The posture information of the object obtains mechanical arm and grabs point.
10. a kind of computer readable storage medium, is stored thereon with computer executable instructions, wherein the computer is executable
Instruction makes the processor when being executed by processor:
Mechanical arm carries out stereoscan around object to be scanned, obtains object stereo-picture with scanning;
Front and back scape segmentation based on depth map is carried out to the object stereo-picture that scanning obtains, the object after obtaining background
Stereotome;
According to the object stereotome reconstruction of objects threedimensional model after the background;
Using the emulation picture under the object dimensional model rendering actual scene, preset quantity is generated according to the emulation picture
Training sample, based on the training sample training deep neural network;
In the actual scene, the current stereo-picture of object is obtained, current stereo-picture is inputted into the depth nerve net
Network calculates the posture information of the object in the current stereo-picture by the deep neural network, according to what is be calculated
The posture information of the object obtains mechanical arm and grabs point.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810942396.XA CN109241964A (en) | 2018-08-17 | 2018-08-17 | The acquisition methods and equipment of the crawl point of mechanical arm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810942396.XA CN109241964A (en) | 2018-08-17 | 2018-08-17 | The acquisition methods and equipment of the crawl point of mechanical arm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109241964A true CN109241964A (en) | 2019-01-18 |
Family
ID=65071698
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810942396.XA Pending CN109241964A (en) | 2018-08-17 | 2018-08-17 | The acquisition methods and equipment of the crawl point of mechanical arm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109241964A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109816728A (en) * | 2019-01-30 | 2019-05-28 | 国网江苏省电力有限公司苏州供电分公司 | Method based on the mechanical arm crawl point location detection for generating inquiry network |
CN110335314A (en) * | 2019-06-24 | 2019-10-15 | 华中科技大学 | The method of two dimensional image prediction target object real-time pose based on target object |
CN111476087A (en) * | 2020-03-02 | 2020-07-31 | 深圳市商汤科技有限公司 | Target detection method and related model training method, device and apparatus |
CN112734727A (en) * | 2021-01-11 | 2021-04-30 | 安徽理工大学 | Apple picking method based on improved deep neural network |
CN112775959A (en) * | 2020-07-24 | 2021-05-11 | 上海芯翌智能科技有限公司 | Method and system for determining grabbing pose of manipulator and storage medium |
CN113034668A (en) * | 2021-03-01 | 2021-06-25 | 中科数据(青岛)科技信息有限公司 | AR-assisted mechanical simulation operation method and system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6873927B2 (en) * | 2002-07-30 | 2005-03-29 | Via Technologies, Inc. | Control method of an automatic integrated circuit full testing system |
CN105598965A (en) * | 2015-11-26 | 2016-05-25 | 哈尔滨工业大学 | Robot under-actuated hand autonomous grasping method based on stereoscopic vision |
CN106874914A (en) * | 2017-01-12 | 2017-06-20 | 华南理工大学 | A kind of industrial machinery arm visual spatial attention method based on depth convolutional neural networks |
CN108044627A (en) * | 2017-12-29 | 2018-05-18 | 深圳市越疆科技有限公司 | Detection method, device and the mechanical arm of crawl position |
-
2018
- 2018-08-17 CN CN201810942396.XA patent/CN109241964A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6873927B2 (en) * | 2002-07-30 | 2005-03-29 | Via Technologies, Inc. | Control method of an automatic integrated circuit full testing system |
CN105598965A (en) * | 2015-11-26 | 2016-05-25 | 哈尔滨工业大学 | Robot under-actuated hand autonomous grasping method based on stereoscopic vision |
CN106874914A (en) * | 2017-01-12 | 2017-06-20 | 华南理工大学 | A kind of industrial machinery arm visual spatial attention method based on depth convolutional neural networks |
CN108044627A (en) * | 2017-12-29 | 2018-05-18 | 深圳市越疆科技有限公司 | Detection method, device and the mechanical arm of crawl position |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109816728A (en) * | 2019-01-30 | 2019-05-28 | 国网江苏省电力有限公司苏州供电分公司 | Method based on the mechanical arm crawl point location detection for generating inquiry network |
CN109816728B (en) * | 2019-01-30 | 2022-06-14 | 国网江苏省电力有限公司苏州供电分公司 | Mechanical arm grabbing point positioning detection method based on query network generation |
CN110335314A (en) * | 2019-06-24 | 2019-10-15 | 华中科技大学 | The method of two dimensional image prediction target object real-time pose based on target object |
CN111476087A (en) * | 2020-03-02 | 2020-07-31 | 深圳市商汤科技有限公司 | Target detection method and related model training method, device and apparatus |
CN112775959A (en) * | 2020-07-24 | 2021-05-11 | 上海芯翌智能科技有限公司 | Method and system for determining grabbing pose of manipulator and storage medium |
CN112734727A (en) * | 2021-01-11 | 2021-04-30 | 安徽理工大学 | Apple picking method based on improved deep neural network |
CN113034668A (en) * | 2021-03-01 | 2021-06-25 | 中科数据(青岛)科技信息有限公司 | AR-assisted mechanical simulation operation method and system |
CN113034668B (en) * | 2021-03-01 | 2023-04-07 | 中科数据(青岛)科技信息有限公司 | AR-assisted mechanical simulation operation method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109241964A (en) | The acquisition methods and equipment of the crawl point of mechanical arm | |
EP3293705B1 (en) | 3d reconstruction of a real object from a depth map | |
Cartillier et al. | Semantic mapnet: Building allocentric semantic maps and representations from egocentric views | |
CN108648274B (en) | Cognitive point cloud map creating system of visual SLAM | |
Sallab et al. | Lidar sensor modeling and data augmentation with gans for autonomous driving | |
CN108401461A (en) | Three-dimensional mapping method, device and system, cloud platform, electronic equipment and computer program product | |
US20150009214A1 (en) | Real-time 3d computer vision processing engine for object recognition, reconstruction, and analysis | |
JP2016218999A (en) | Method for training classifier to detect object represented in image of target environment | |
JP2014096152A (en) | Backfilling points in point cloud | |
CN109906600B (en) | Simulated depth of field | |
KR101590253B1 (en) | Method and device for simulation of sonar images of multi-beam imaging sonar | |
CN113449570A (en) | Image processing method and device | |
CN110567441B (en) | Particle filter-based positioning method, positioning device, mapping and positioning method | |
CN109146786A (en) | Scene chart generation method and device, electronic equipment and storage medium | |
CN104735435A (en) | Image processing method and electronic device | |
KR101602593B1 (en) | Method and arrangement for 3d model morphing | |
CN110910452A (en) | Low-texture industrial part pose estimation method based on deep learning | |
CN112070782A (en) | Method and device for identifying scene contour, computer readable medium and electronic equipment | |
JP6819758B1 (en) | Point cloud data identity estimation device and point cloud data identity estimation system | |
CN116342782A (en) | Method and apparatus for generating avatar rendering model | |
CN107194359B (en) | Method and device for constructing scale space of video image sequence | |
Li et al. | Blinkflow: A dataset to push the limits of event-based optical flow estimation | |
JP2019016164A (en) | Learning data generation device, estimation device, estimation method, and computer program | |
JP2018120402A (en) | Event detecting device, event detecting method, and program | |
CN114332156A (en) | Real-time three-dimensional motion completion method based on graph convolution neural network |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190118 |