CN107636727A - Target detection method and device - Google Patents
Target detection method and device Download PDFInfo
- Publication number
- CN107636727A CN107636727A CN201680016608.0A CN201680016608A CN107636727A CN 107636727 A CN107636727 A CN 107636727A CN 201680016608 A CN201680016608 A CN 201680016608A CN 107636727 A CN107636727 A CN 107636727A
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- depth value
- candidate region
- pixel
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000004891 communication Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 5
- 238000012546 transfer Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 13
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 13
- 238000012545 processing Methods 0.000 description 9
- 238000000605 extraction Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004549 pulsed laser deposition Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
A target detection method and a device relate to the technical field of artificial intelligence and are applied to the process of target detection. In order to solve the problem of limited target detection precision, the method comprises the following steps: acquiring an image to be detected and depth values of a plurality of pixel points in the image to be detected (101); and carrying out target detection (102) on the image to be detected by combining the depth values of all the pixel points.
Description
Technical field
The application is related to field of artificial intelligence, more particularly to a kind of method and device of target detection.
Background technology
The method of existing target detection is generally divided into three phases：First candidate region is selected in given image；So
Feature extraction is carried out to these candidate regions afterwards, finally candidate region classified using the grader of training, and then is detected
Obtain all possibility target objects.Wherein, it is main at present when selecting candidate region (region proposal) in the first stage
The object detection method of stream is usually using information such as the texture in image, edge, colors, and finding out target in image in advance may
The position of appearance, extraction hundreds to thousands candidate region.The above-mentioned object detection method based on candidate region exist it is following not
Foot：
1st, follow-up feature extraction is carried out to hundreds to thousands candidate region, not only amount of calculation is larger, and candidate
The quantity in region generally includes the quantity of object considerably beyond image so that many calculate is also unnecessary.
2nd, the two-dimensional spatial location of some objects is adjacent in image, but its depth value is different, because color, texture are similar,
It is likely to be taken as integrally to extract in same candidate region, and then influences the precision of target detection.
The content of the invention
Embodiments herein provides a kind of object detection method and device, mainly solves target detection of the prior art
Target detection limited precision existing for method and it is computationally intensive the problem of.
To reach above-mentioned purpose, embodiments herein adopts the following technical scheme that：
In a first aspect, the application provides a kind of object detection method, including：Obtain image to be detected and image to be detected
In multiple pixels depth value；Target detection is carried out to image to be detected with reference to the depth value of each pixel.
Second aspect, the application provide a kind of object detecting device, including：Acquiring unit, for obtaining image to be detected
And in image to be detected multiple pixels depth value；Object detection unit, it is each for being obtained with reference to the acquiring unit
The depth value of individual pixel carries out target detection to image to be detected.
The third aspect, the application provides a kind of computer-readable storage medium, and for storing computer software instructions, it includes and held
The program code designed by object detection method described in row first aspect.
Fourth aspect, the application provide a kind of computer program product, can be loaded directly into the internal storage of computer
In, and contain software code, the computer program is loaded into via computer and can realized described in first aspect after performing
Object detection method.
5th aspect, the application provide a kind of electronic equipment, including：Memory, communication interface and processor, the storage
Device is used to store computer-executable code, and the processor is used to perform the computer-executable code control execution first
The aspect object detection method, the communication interface are used for the data transfer of the electronic equipment and external equipment.
6th aspect, the application provide a kind of robot, including the electronic equipment described in the 5th aspect.
The scheme that the application provides, when carrying out target detection, obtain first in image to be detected and image to be detected
The depth value of multiple pixels；And the depth value for combining each pixel carries out target detection to image to be detected.With existing skill
The information such as the texture based on image, edge, color in art carry out target detection compare, the application when carrying out target detection,
Depth value is considered, therefore in target detection, color, the target object that texture is similar but depth is different can be subjected to area
Point, and then the precision of target detection can be improved.
Brief description of the drawings
, below will be to embodiment or existing in order to illustrate more clearly of the embodiment of the present application or technical scheme of the prior art
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of application, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the configuration diagram for the object detection system that the embodiment of the present application provides；
Fig. 2 is the schematic flow sheet for the object detection method that the embodiment of the present application provides；
Fig. 3 is that method shown in image to be detected, depth image and use Fig. 2 of the embodiment of the present application offer divides to obtain
Initial candidate region schematic diagram；
Fig. 4 is the schematic flow sheet for another object detection method that the embodiment of the present application provides；
Fig. 5 splits to obtain mesh using the method shown in Fig. 4 for the embodiment of the present application to the initial candidate region shown in Fig. 3
Mark the schematic diagram of candidate region；
Fig. 6 is the schematic flow sheet for another object detection method that the embodiment of the present application provides；
Fig. 7 is a kind of structural representation for object detection apparatus that the embodiment of the present application provides；
Fig. 8 is the structural representation for another object detection apparatus that the embodiment of the present application provides；
Fig. 9 is the structural representation for a kind of electronic equipment that the embodiment of the present application provides.
Embodiment
The system architecture and business scenario of the embodiment of the present application description are in order to which more clearly explanation the application is implemented
The technical scheme of example, the restriction of the technical scheme provided for the embodiment of the present application, those of ordinary skill in the art are not formed
Understand, with the differentiation of system architecture and the appearance of new business scene, the technical scheme that the embodiment of the present application provides is for similar
Technical problem, it is equally applicable.
It should be noted that in the embodiment of the present application, " exemplary " or " such as " etc. word make example, example for expression
Card or explanation.Be described as in the embodiment of the present application " exemplary " or " such as " any embodiment or design should
It is interpreted than other embodiments or design more preferably or more advantage.Specifically, " exemplary " or " example are used
Such as " word is intended to that related notion is presented in a concrete fashion.
It should be noted that in the embodiment of the present application, " (English：Of) ", " corresponding (English：Corresponding,
Relevant it is) " and " corresponding (English：Corresponding) " can use with sometimes, it is noted that do not emphasizing it
During difference, its is to be expressed be meant that it is consistent.
The embodiment of the present application provides a kind of object detection system, as shown in figure 1, the system includes：Image capture device 11
With object detection apparatus 12.Wherein, image capture device 11, which is used to treating detection zone, carries out IMAQ and will collect
Image is sent to object detection apparatus 12, exemplary, and the image capture device 11 can obtain figure to be single or multiple
The video camera of the two-dimensional signal of picture can obtain binocular camera of three-dimensional information etc..Object detection apparatus 12 is used for from image
The image that collecting device 11 receives is analyzed and processed to carry out target detection, object detection apparatus using the image received
12 can be the equipment with processing function, such as server.The specific reality of image capture device 11 and object detection apparatus 12
Prior art is now referred to, here is omitted.
The embodiment of the present application provides a kind of object detection method, can be applied in the system shown in Fig. 1, when applied to Fig. 1
When in shown system, the executive agent of this method can be the object detection apparatus 12 shown in Fig. 1.Hereafter using executive agent as
Object detection apparatus 12 illustrates, as shown in Fig. 2 this method includes：
Step 101, the depth value for obtaining multiple pixels in image to be detected and image to be detected.
Wherein, image to be detected is to treat the image obtained after detection zone is shot, can be the figure directly obtained
Picture, or the image for the coloured image that this is directly obtained obtain after the processing such as gray scale, denoising.
Exemplary, treat detection zone using equipment such as common camera or the mobile phones with camera function and clapped
The image for taking the photograph to obtain can be used as image to be detected signified in the application.
Depth value can be by obtaining depth image corresponding to image to be detected；And mapping to be checked is determined from depth image
The depth value of each pixel of picture.
Wherein, depth image (depth image) is also referred to as range image (range image), refers to from image
Collector, such as image of the distance (or referred to as depth) as pixel value of binocular camera each point into region to be detected, energy
It is enough directly to reflect the geometry of object visible surface, namely can directly determine the contour line of each object.In depth image,
What each pixel represented is in the visual field of image acquisition device, and object is to imaging head plane at specific (x, the y) coordinate
Distance.Therefore, each pixel is corresponding with depth value in depth image, for representing the depth of each object in region to be detected
Angle value.The acquisition methods of common depth image have laser radar Depth Imaging method, computer stereo vision imaging, measurement of coordinates
Machine method, Moire fringe technique, Structure light method etc., the specific implementation of depth image refer to prior art, and here is omitted.
Step 102, the depth value with reference to each pixel carry out target detection to image to be detected.
, can be by image to be detected in a kind of implementation of step 102, depth value is located at the pixel in same scope
Point is divided into same candidate region.
Exemplary, as shown in figure 3, the application respectively illustrates image to be detected, depth image and performs step 102
Obtained candidate region 1 and candidate region 2 is divided afterwards.
After candidate region is determined according to the depth value of pixel, feature extraction directly can be carried out to candidate region, most
Candidate region is classified using the grader of training afterwards, so as to realize target detection.The specific implementation process of the step can
With reference to prior art, here is omitted.
In another implementation of this step 102, can using according to the candidate region that depth value is determined as just
Beginning candidate region, and to initial candidate region carry out further split obtain object candidate area, as shown in figure 4, step 102 has
Body can be realized：
Step 201, depth value is located at the pixel in same scope be divided into same initial candidate region.
Step 202, according to characteristics of image initial candidate region is split as object candidate area.
Step 203, target is determined in object candidate area.
Wherein, described image feature includes any one in following feature or any several：Color characteristic, texture are special
Any one or more in sign, architectural feature, face characteristic or contour feature.Should be according to characteristics of image to initial candidate region
The specific implementation for being split to obtain object candidate area refers to carry out region to a region in the prior art
Proposal implementation process.
For example, when the characteristics of image is contour line feature, above-mentioned steps 202 specifically can be implemented as：Detect respectively
Contour line in each initial candidate region；When exist at least one initial candidate region include at least two mutually it is independent
During closed contour, each initial candidate region at least one initial candidate region is split to obtain at least two
Individual object candidate area is to cause each object candidate area to include an at most closed contour.
The multiple initial candidate regions obtained with reference to Fig. 3, tear open to each initial candidate region according to contour line feature
After point, initial candidate region 1 can be split as to two object candidate areas, obtain object candidate area as shown in Figure 5.
And for example, when the characteristics of image is contour line feature, above-mentioned steps 202 specifically can be implemented as：Detect respectively
Color characteristic in each initial candidate region.When at least one initial candidate region be present and include at least two colors,
Each initial candidate region at least one initial candidate region is split as at least two object candidate areas respectively
To cause each object candidate area to include a kind of color characteristic.
It should be noted that above-mentioned only illustrate by taking contour line feature and color characteristic as an example, drawn in practical application
, may multiple features such as color combining, texture during partial objectives for candidate region.
In another implementation of step 102, as shown in fig. 6, including：
Step 301, according to characteristics of image image to be detected is divided into initial candidate region.
Wherein, described image feature includes any one in following feature or any several：Color characteristic, texture are special
Any one or more in sign, architectural feature, face characteristic or contour feature.Image to be detected should be entered according to characteristics of image
The specific implementation that row division obtains initial candidate region refers to carry out region proposal to a region in the prior art
Implementation process.
Step 302, the depth value of pixel is removed not in the initial candidate region of same scope.
Step 303, determine target in remaining initial candidate region.
The scheme that the application provides, when carrying out target detection, obtain first in image to be detected and image to be detected
The depth value of multiple pixels；And the depth value for combining each pixel carries out target detection to image to be detected.With existing skill
The information such as the texture based on image, edge, color in art carry out target detection compare, the application when carrying out target detection,
Depth value is considered, therefore in target detection, color, the target object that texture is similar but depth is different can be subjected to area
Point, and then the precision of target detection can be improved.
In addition, in general, the depth information included in region to be detected is in most cases less than its color included
Information, such as：One object may include multiple color, but depth value may only have one corresponding to this whole object, therefore,
The amount of calculation for dividing to obtain candidate region according to depth value also greatly reduces.
Optionally, after target is identified, object detection apparatus 12 can also export the information such as the classification of target, profile.
The method that the embodiment of the present application provides can be used in the scene for needing to carry out target identification, such as：Applied to shifting
In mobile robot, mobile robot can use the application body method automatic identification its object in the environment to carry out
Decision-making.During can be applied in auxiliary user's searching specific objective object.Any need detection, the process of identification object
The method that can all apply the application to provide.
Those skilled in the art should be readily appreciated that, each example described with reference to the embodiments described herein
Unit and algorithm steps, the application can be realized with the combining form of hardware or hardware and computer software.Some function is studied carefully
Unexpectedly performed in a manner of hardware or computer software driving hardware, application-specific and design constraint depending on technical scheme
Condition.Professional and technical personnel can realize described function using distinct methods to each specific application, but this
Kind is realized it is not considered that exceeding scope of the present application.
The embodiment of the present application can carry out the division of functional module, example according to above method example to object detection apparatus etc.
Such as, each function can be corresponded to and divide each functional module, two or more functions can also be integrated at one
Manage in module.Above-mentioned integrated module can both be realized in the form of hardware, can also use the form of software function module
Realize.It should be noted that the division in the embodiment of the present application to module is schematical, only a kind of logic function is drawn
Point, there can be other dividing mode when actually realizing.
In the case where dividing each functional module using corresponding each function, Fig. 7 shows involved in above-described embodiment
And object detection apparatus a kind of possible structural representation, object detection apparatus includes：Acquiring unit 401 and target
Detection unit 402.Acquiring unit 401 is used to support object detection apparatus to perform the process 101 in Fig. 2；Object detection unit 402
For supporting object detection apparatus to perform the process 102 in Fig. 2, process 201 in Fig. 4,202, the process 301 in 203, Fig. 6,
302、303.Wherein, all related contents for each step that above method embodiment is related to can quote corresponding function module
Function description, will not be repeated here.
In the case of using integrated unit, Fig. 8 shows object detection apparatus involved in above-described embodiment
A kind of possible structural representation.Object detection apparatus includes：Processing module 501 and communication module 502.Processing module 501 is used
Management is controlled in the action to object detection apparatus, for example, processing module 501 is used to support object detection apparatus execution figure
Process 301,302,303 in process 101 in 2,102, the process 201 in 103, Fig. 4,202,203, Fig. 6, and/or be used for
Other processes of techniques described herein.Communication module 502 is used to support the logical of object detection apparatus and other network entities
Letter, such as the communication between the functional module with being shown in Fig. 1 or network entity.Object detection apparatus can also include storage mould
Block 503, for storing the program code and data of object detection apparatus.
Wherein, processing module 501 can be processor or controller, such as can be central processing unit (Central
Processing Unit, CPU), general processor, digital signal processor (Digital Signal Processor, DSP),
Application specific integrated circuit (Application-Specific Integrated Circuit, ASIC), field programmable gate array
It is (Field Programmable Gate Array, FPGA) or other PLDs, transistor logic, hard
Part part or its any combination.What it can realize or perform with reference to described by present disclosure various exemplary patrols
Collect square frame, module and circuit.The processor can also be the combination for realizing computing function, such as include one or more micro- places
Manage device combination, combination of DSP and microprocessor etc..Communication module 502 can be transceiver, transmission circuit or communication interface
Deng.Memory module 503 can be memory.
When processing module 501 is processor, communication module 502 is communication interface, when memory module 503 is memory, this
It can be the electronic equipment shown in Fig. 9 to apply for the object detection apparatus involved by embodiment.
As shown in fig.9, the electronic equipment includes：Processor 601, communication interface 602, memory 603 and bus
604.Wherein, communication interface 602, processor 601 and memory 603 are connected with each other by bus 604；Bus 604 can be
Peripheral Component Interconnect standard (Peripheral Component Interconnect, PCI) bus or EISA
(Extended Industry Standard Architecture, EISA) bus etc..It is total that the bus can be divided into address
Line, data/address bus, controlling bus etc..For ease of representing, only represented in Fig. 9 with a thick line, it is not intended that only one total
Line or a type of bus.
The step of method or algorithm with reference to described by present disclosure, can be realized in a manner of hardware, also may be used
By be by computing device software instruction in a manner of realize.Software instruction can be made up of corresponding software module, software mould
Block can be stored on random access memory (Random Access Memory, RAM), flash memory, read-only storage (Read
Only Memory, ROM), Erasable Programmable Read Only Memory EPROM (Erasable Programmable ROM, EPROM), electricity can
EPROM (Electrically EPROM, EEPROM), register, hard disk, mobile hard disk, read-only optical disc
(CD-ROM) or in the storage medium of any other form well known in the art.A kind of exemplary storage medium is coupled to place
Device is managed, so as to enable a processor to from the read information, and information can be write to the storage medium.Certainly, store
Medium can also be the part of processor.Processor and storage medium can be located in ASIC.
Those skilled in the art are it will be appreciated that in said one or multiple examples, work(described herein
It is able to can be realized with hardware, software, firmware or their any combination.When implemented in software, can be by these functions
It is stored in computer-readable medium or is transmitted as one or more instructions on computer-readable medium or code.
Computer-readable medium includes computer-readable storage medium and communication media, and wherein communication media includes being easy to from a place to another
Any medium of one place transmission computer program.It is any that storage medium can be that universal or special computer can access
Usable medium.
Above-described embodiment, the purpose, technical scheme and beneficial effect of the application are carried out further
Describe in detail, should be understood that the embodiment that the foregoing is only the application, be not used to limit the application
Protection domain, all any modification, equivalent substitution and improvements on the basis of the technical scheme of the application, done etc., all should
It is included within the protection domain of the application.
Claims (14)
- A kind of 1. object detection method, it is characterised in that including：Obtain the depth value of multiple pixels in image to be detected and image to be detected；Target detection is carried out to image to be detected with reference to the depth value of each pixel.
- 2. according to the method for claim 1, it is characterised in that the depth for obtaining multiple pixels in image to be detected Value includes：Obtain depth image corresponding to image to be detected；The depth value of each pixel of image to be detected is determined from depth image.
- 3. according to the method for claim 1, it is characterised in that the depth value of each pixel of combination is to figure to be detected As carrying out target detection, including：Depth value is located at into the pixel in same scope to be divided into same initial candidate region；Initial candidate region is split as object candidate area according to characteristics of image；Target is determined in object candidate area.
- 4. according to the method for claim 1, it is characterised in that the depth value of each pixel of combination is to figure to be detected As carrying out target detection, including：Image to be detected is divided into initial candidate region according to characteristics of image；The depth value of pixel is removed not in the initial candidate region of same scope；Target is determined in remaining initial candidate region.
- 5. the method according to claim 3 or 4, it is characterised in that described image feature includes any in following feature It is one or any several：In color characteristic, textural characteristics, architectural feature, face characteristic or contour feature any one or It is a variety of.
- A kind of 6. object detecting device, it is characterised in that including：Acquiring unit, for obtaining the depth value of multiple pixels in image to be detected and image to be detected；Object detection unit, the depth value of each pixel for being obtained with reference to the acquiring unit are carried out to image to be detected Target detection.
- 7. device according to claim 6, it is characterised in that the acquiring unit, it is corresponding for obtaining image to be detected Depth image；The depth value of each pixel of image to be detected is determined from depth image.
- 8. device according to claim 6, it is characterised in thatThe object detection unit, is additionally operable to depth value being located at the pixel in same scope and is divided into same initial candidate area In domain；Initial candidate region is split as object candidate area according to characteristics of image；Target is determined in object candidate area.
- 9. device according to claim 6, it is characterised in thatThe object detection unit, it is additionally operable to that image to be detected is divided into initial candidate region according to characteristics of image；Remove picture The depth value of vegetarian refreshments is not or not the initial candidate region of same scope；Target is determined in remaining initial candidate region.
- 10. device according to claim 8 or claim 9, it is characterised in that described image feature includes any in following feature It is one or any several：In color characteristic, textural characteristics, architectural feature, face characteristic or contour feature any one or It is a variety of.
- 11. a kind of electronic equipment, it is characterised in that including：Memory, communication interface and processor, the memory are used to deposit Computer-executable code is stored up, the processor is used to perform the computer-executable code control perform claim requirement 1-5 Any one object detection method, the communication interface are used for the data transfer of the electronic equipment and external equipment.
- 12. a kind of robot, it is characterised in that including the electronic equipment described in claim 11.
- 13. a kind of computer-readable storage medium, it is characterised in that for storing computer software instructions, it will comprising perform claim Seek the program code designed by the object detection method described in any one of 1-5.
- 14. a kind of computer program product, it is characterised in that can be loaded directly into the internal storage of computer, and contain Software code, the computer program are loaded into via computer and can realized described in claim any one of 1-5 after performing Object detection method.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2016/113548 WO2018120038A1 (en) | 2016-12-30 | 2016-12-30 | Method and device for target detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107636727A true CN107636727A (en) | 2018-01-26 |
Family
ID=61113496
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201680016608.0A Pending CN107636727A (en) | 2016-12-30 | 2016-12-30 | Target detection method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107636727A (en) |
| WO (1) | WO2018120038A1 (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110348333A (en) * | 2019-06-21 | 2019-10-18 | 深圳前海达闼云端智能科技有限公司 | Object detecting method, device, storage medium and electronic equipment |
| CN110502978A (en) * | 2019-07-11 | 2019-11-26 | 哈尔滨工业大学 | A kind of laser radar waveform Modulation recognition method based on BP neural network model |
| CN111179332A (en) * | 2018-11-09 | 2020-05-19 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic device and storage medium |
| CN111210471A (en) * | 2018-11-22 | 2020-05-29 | 北京欣奕华科技有限公司 | Positioning method, device and system |
| CN111366916A (en) * | 2020-02-17 | 2020-07-03 | 北京睿思奥图智能科技有限公司 | Method and device for determining distance between interaction target and robot and electronic equipment |
| CN111383238A (en) * | 2018-12-28 | 2020-07-07 | Tcl集团股份有限公司 | Target detection method, target detection device and intelligent terminal |
| CN111950543A (en) * | 2019-05-14 | 2020-11-17 | 北京京东尚科信息技术有限公司 | Target detection method and device |
| WO2023109069A1 (en) * | 2021-12-13 | 2023-06-22 | 深圳前海微众银行股份有限公司 | Image retrieval method and apparatus |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110853127A (en) * | 2018-08-20 | 2020-02-28 | 浙江宇视科技有限公司 | Image processing method, device and equipment |
| CN111324139A (en) * | 2018-12-13 | 2020-06-23 | 顺丰科技有限公司 | Unmanned aerial vehicle landing method, device, equipment and storage medium |
| CN111353115B (en) * | 2018-12-24 | 2023-10-27 | 中移（杭州）信息技术有限公司 | Method and device for generating snowplow map |
| CN110276742B (en) * | 2019-05-07 | 2023-10-10 | 平安科技（深圳）有限公司 | Train tail lamp monitoring method, device, terminal and storage medium |
| CN110264460A (en) * | 2019-06-24 | 2019-09-20 | 科大讯飞股份有限公司 | A kind of discrimination method of object detection results, device, equipment and storage medium |
| CN112446918A (en) * | 2019-09-04 | 2021-03-05 | 三赢科技（深圳）有限公司 | Method and device for positioning target object in image, computer device and storage medium |
| CN111199198B (en) * | 2019-12-27 | 2023-08-04 | 深圳市优必选科技股份有限公司 | Image target positioning method, image target positioning device and mobile robot |
| CN111223111B (en) * | 2020-01-03 | 2023-04-25 | 歌尔光学科技有限公司 | Depth image contour generation method, device, equipment and storage medium |
| CN111507958B (en) * | 2020-04-15 | 2023-05-26 | 全球能源互联网研究院有限公司 | Target detection method, training method of detection model and electronic equipment |
| CN113538449A (en) * | 2020-04-20 | 2021-10-22 | 顺丰科技有限公司 | Image correction method, device, server and storage medium |
| CN111783584B (en) * | 2020-06-22 | 2023-08-08 | 杭州飞步科技有限公司 | Image target detection method, device, electronic equipment and readable storage medium |
| CN111898641A (en) * | 2020-07-01 | 2020-11-06 | 中国建设银行股份有限公司 | Target model detection device, electronic equipment and computer readable storage medium |
| CN112258482A (en) * | 2020-10-23 | 2021-01-22 | 广东博智林机器人有限公司 | Building exterior wall mortar flow drop detection method and device |
| CN113420735B (en) * | 2021-08-23 | 2021-12-21 | 深圳市信润富联数字科技有限公司 | Contour extraction method, device, equipment and storage medium |
| CN114004788A (en) * | 2021-09-23 | 2022-02-01 | 中大(海南)智能科技有限公司 | Defect detection method, device, equipment and storage medium |
| CN115019157B (en) * | 2022-07-06 | 2024-03-22 | 武汉市聚芯微电子有限责任公司 | Object detection method, device, equipment and computer readable storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101657825A (en) * | 2006-05-11 | 2010-02-24 | 普莱姆传感有限公司 | Modeling of humanoid forms from depth maps |
| CN101840577A (en) * | 2010-06-11 | 2010-09-22 | 西安电子科技大学 | Image automatic segmentation method based on graph cut |
| CN102243759A (en) * | 2010-05-10 | 2011-11-16 | 东北大学 | Three-dimensional lung vessel image segmentation method based on geometric deformation model |
| CN103093473A (en) * | 2013-01-25 | 2013-05-08 | 北京理工大学 | Multi-target picture segmentation based on level set |
| CN104217225A (en) * | 2014-09-02 | 2014-12-17 | 中国科学院自动化研究所 | A visual target detection and labeling method |
| CN105354838A (en) * | 2015-10-20 | 2016-02-24 | 努比亚技术有限公司 | Method and terminal for acquiring depth information of weak texture region in image |
| CN105872477A (en) * | 2016-05-27 | 2016-08-17 | 北京旷视科技有限公司 | Video monitoring method and system |
| CN106250812A (en) * | 2016-07-15 | 2016-12-21 | 汤平 | A kind of model recognizing method based on quick R CNN deep neural network |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7003134B1 (en) * | 1999-03-08 | 2006-02-21 | Vulcan Patents Llc | Three dimensional object pose estimation which employs dense depth information |
| CN100579174C (en) * | 2007-02-02 | 2010-01-06 | 华为技术有限公司 | Motion detection method and device |
| CN102402687B (en) * | 2010-09-13 | 2016-06-15 | 三星电子株式会社 | Rigid body part direction detection method and device based on depth information |
| CN102855459B (en) * | 2011-06-30 | 2015-11-25 | 株式会社理光 | For the method and system of the detection validation of particular prospect object |
-
2016
- 2016-12-30 WO PCT/CN2016/113548 patent/WO2018120038A1/en active Application Filing
- 2016-12-30 CN CN201680016608.0A patent/CN107636727A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101657825A (en) * | 2006-05-11 | 2010-02-24 | 普莱姆传感有限公司 | Modeling of humanoid forms from depth maps |
| CN102243759A (en) * | 2010-05-10 | 2011-11-16 | 东北大学 | Three-dimensional lung vessel image segmentation method based on geometric deformation model |
| CN101840577A (en) * | 2010-06-11 | 2010-09-22 | 西安电子科技大学 | Image automatic segmentation method based on graph cut |
| CN103093473A (en) * | 2013-01-25 | 2013-05-08 | 北京理工大学 | Multi-target picture segmentation based on level set |
| CN104217225A (en) * | 2014-09-02 | 2014-12-17 | 中国科学院自动化研究所 | A visual target detection and labeling method |
| CN105354838A (en) * | 2015-10-20 | 2016-02-24 | 努比亚技术有限公司 | Method and terminal for acquiring depth information of weak texture region in image |
| CN105872477A (en) * | 2016-05-27 | 2016-08-17 | 北京旷视科技有限公司 | Video monitoring method and system |
| CN106250812A (en) * | 2016-07-15 | 2016-12-21 | 汤平 | A kind of model recognizing method based on quick R CNN deep neural network |
Non-Patent Citations (2)
| Title |
|---|
| 吴鑫: "融合Kinect深度和颜色信息的机器人视觉系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 李海坤: "基于彩色和深度的前景分割研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111179332A (en) * | 2018-11-09 | 2020-05-19 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic device and storage medium |
| CN111179332B (en) * | 2018-11-09 | 2023-12-19 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN111210471A (en) * | 2018-11-22 | 2020-05-29 | 北京欣奕华科技有限公司 | Positioning method, device and system |
| CN111210471B (en) * | 2018-11-22 | 2023-08-25 | 浙江欣奕华智能科技有限公司 | Positioning method, device and system |
| CN111383238A (en) * | 2018-12-28 | 2020-07-07 | Tcl集团股份有限公司 | Target detection method, target detection device and intelligent terminal |
| CN111950543A (en) * | 2019-05-14 | 2020-11-17 | 北京京东尚科信息技术有限公司 | Target detection method and device |
| CN111950543B (en) * | 2019-05-14 | 2024-08-16 | 北京京东乾石科技有限公司 | Target detection method and device |
| CN110348333A (en) * | 2019-06-21 | 2019-10-18 | 深圳前海达闼云端智能科技有限公司 | Object detecting method, device, storage medium and electronic equipment |
| CN110502978A (en) * | 2019-07-11 | 2019-11-26 | 哈尔滨工业大学 | A kind of laser radar waveform Modulation recognition method based on BP neural network model |
| CN111366916A (en) * | 2020-02-17 | 2020-07-03 | 北京睿思奥图智能科技有限公司 | Method and device for determining distance between interaction target and robot and electronic equipment |
| CN111366916B (en) * | 2020-02-17 | 2021-04-06 | 山东睿思奥图智能科技有限公司 | Method and device for determining distance between interaction target and robot and electronic equipment |
| WO2023109069A1 (en) * | 2021-12-13 | 2023-06-22 | 深圳前海微众银行股份有限公司 | Image retrieval method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2018120038A1 (en) | 2018-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107636727A (en) | Target detection method and device | |
| CN104778721B (en) | The distance measurement method of conspicuousness target in a kind of binocular image | |
| KR101854554B1 (en) | Method, device and storage medium for calculating building height | |
| EP2811423B1 (en) | Method and apparatus for detecting target | |
| CN108381549B (en) | Binocular vision guide robot rapid grabbing method and device and storage medium | |
| US20180018528A1 (en) | Detecting method and device of obstacles based on disparity map and automobile driving assistance system | |
| JP6955783B2 (en) | Information processing methods, equipment, cloud processing devices and computer program products | |
| CN106446862A (en) | Face detection method and system | |
| CN110458772B (en) | Point cloud filtering method and device based on image processing and storage medium | |
| CN108475433A (en) | Method and system for determining RGBD camera postures on a large scale | |
| CN105809651A (en) | Image saliency detection method based on edge non-similarity comparison | |
| CN110751620B (en) | Method for estimating volume and weight, electronic device, and computer-readable storage medium | |
| CN107203742B (en) | Gesture recognition method and device based on significant feature point extraction | |
| CN104915642B (en) | Front vehicles distance measuring method and device | |
| WO2020258297A1 (en) | Image semantic segmentation method, movable platform, and storage medium | |
| CN111340834B (en) | Lining plate assembly system and method based on laser radar and binocular camera data fusion | |
| CN111837158A (en) | Image processing method and device, shooting device and movable platform | |
| CN111382658B (en) | Road traffic sign detection method in natural environment based on image gray gradient consistency | |
| CN111126393A (en) | Vehicle appearance refitting judgment method and device, computer equipment and storage medium | |
| CN115439607A (en) | Three-dimensional reconstruction method and device, electronic equipment and storage medium | |
| CN109784171A (en) | Car damage identification method for screening images, device, readable storage medium storing program for executing and server | |
| CN108596032B (en) | Detection method, device, equipment and medium for fighting behavior in video | |
| CN114898321B (en) | Road drivable area detection method, device, equipment, medium and system | |
| CN116342519A (en) | Image processing method based on machine learning | |
| CN116643291A (en) | SLAM method for removing dynamic targets by combining vision and laser radar |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210201 Address after: 201111 2nd floor, building 2, no.1508, Kunyang Road, Minhang District, Shanghai Applicant after: Dalu Robot Co.,Ltd. Address before: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Applicant before: Shenzhen Qianhaida Yunyun Intelligent Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| CB02 | Change of applicant information |
Address after: 201111 Building 8, No. 207, Zhongqing Road, Minhang District, Shanghai Applicant after: Dayu robot Co.,Ltd. Address before: 201111 2nd floor, building 2, no.1508, Kunyang Road, Minhang District, Shanghai Applicant before: Dalu Robot Co.,Ltd. |
|
| CB02 | Change of applicant information |