CN109712315A - A kind of Vending Machine cargo based on dual camera falls detection method - Google Patents
A kind of Vending Machine cargo based on dual camera falls detection method Download PDFInfo
- Publication number
- CN109712315A CN109712315A CN201811607304.9A CN201811607304A CN109712315A CN 109712315 A CN109712315 A CN 109712315A CN 201811607304 A CN201811607304 A CN 201811607304A CN 109712315 A CN109712315 A CN 109712315A
- Authority
- CN
- China
- Prior art keywords
- image
- holder
- camera
- cargo
- vending machine
- 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.)
- Granted
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of, and the Vending Machine cargo based on dual camera falls detection method, detecting step are as follows: (one) completes when equipment detects that user pays, layer stops where holder rises to cargo, at this point, starting holder two sides camera is captured；(2) image is captured in the image processing module processing for starting equipment local, it is set first according to the holder side plate black and white chessboard case of measured in advance, it cuts and captures image, extraneous areas is removed, then, does gray processing processing to picture is cut, finally, edge detection is carried out to it using sobel edge detection operator, generates edge image, and save edge image as Background；(3) after background shooting, start cargo path conveyer belt, while starting holder both sides camera shooting tripod head state；(4) stop conveyer belt, close camera；The present invention can detecte smaller kinds of goods, flat kinds of goods, detects transparent substance, effectively prevents influence of the environment light to freight detection.
Description
Technical field
The present invention relates to a kind of cargos of Vending Machine to fall detection method, more particularly to based on dual camera from
Dynamic vending machine cargo falls detection method.
Background technique
Vending Machine has the characteristics that lay that simple, site requirements is low, saves cost of labor, is increasingly becoming new retail
The mainstream of industry.
The shipment of Vending Machine is controlled by equipment, and whether cargo, which successfully falls, will directly affect businessman's interests and user's body
It tests, therefore, cargo falls the particularly significant problem that detection is the confidential solution of automatic vending.
Traditional cargo falls detection method and is generally divided into three kinds: the first is infrared ray grating approach, and this method is in goods
Object holder both ends install the transmitter-receiver device of infrared ray additional respectively, form infrared ray grating, when there is kinds of goods to fall to holder,
Infrared ray formation can be blocked, system determines whether cargo falls according to coverage extent, the disadvantages of this method are: (1) infrared ray
There is interval between inductor, slender body can not be detected；(2) infrared inductor can only detect the object on grating planar,
If cargo is flat (such as chewing gum), under detection plane, then can not detect；(3) for transparent kinds of goods (such as glass
Son), infrared ray can not be formed and effectively be blocked, it is difficult to detected.
Second is holder weighing method, and this method installs weighing device additional on holder, by detecting holder weight change
Determine whether that cargo is fallen, this method the problem is that: weighing sensitivity is difficult to control, if sensitivity is excessively high, is held
Easily cause erroneous judgement；It, can not the lighter cargo of sense weight if sensitivity is too low.
The third is picture control methods, and this method shoots vacant holder in advance first, normal pictures is formed, then in goods
Object captures holder during falling, and finally the difference of picture and normal pictures is captured in comparison, judges whether cargo falls accordingly
Fall, this method the problem is that: (1) patent use preset standard picture, to using transparent panel Vending Machine, by
It is influenced in being shone by exterior light, different time sections, often difference is very big for normal pictures captured by different weather, if under kinds of goods
The light environment of the picture and default picture that fall shooting is inconsistent, it is easy to cause to judge by accident；(2) camera is pacified in patent proposition
At the top of vending machine, when being located at the commodity shipment of bottom cargo path, farther out due to shooting distance, the object institute taken
It is smaller, unless being otherwise difficult to differentiate using high-definition camera；(3) Vending Machine controls conveyer belt (bullet using preset time
Spring) shipment mode；Since there are idle runnings for conveyer belt (spring) shipment, after especially multiple shipment, idle running accumulation can increase,
ETCD estimated time of commencing discharging is difficult to determine out；If preset time is too long, it be easy to cause and has more goods, causes damages to businessman；If when default
Between it is too short, it will cause shipment failures.
Summary of the invention
For the above technical problems, the purpose of the present invention is: propose a kind of automatic selling based on dual camera
The machine cargo of selling falls detection method.
The technical solution of the invention is as follows is achieved: a kind of Vending Machine cargo based on dual camera is fallen
Detection method, including the Vending Machine with holder；Two side baffle of holder of the Vending Machine installs camera additional respectively；Institute
Camera is stated diagonally to place；Two side baffle of holder, which is pasted to draw, the tessellated paster of black and white；Detecting step are as follows:
(1) it is completed when equipment detects that user pays, layer stops where holder rises to cargo, at this point, starting holder two
Side camera is captured；
(2) image is captured in the image processing module processing for starting equipment local, first according to the holder side plate of measured in advance
Black and white chessboard case is set, and is cut and is captured image, and extraneous areas is removed, and then, gray processing processing is done to picture is cut, finally, making
Edge detection is carried out to it with sobel edge detection operator, generates edge image, and save edge image as Background；
(3) after background shooting, start cargo path conveyer belt, while starting holder both sides camera shooting tripod head state；
Start each frame of the image processing module processing shooting video of Vending Machine, and compared with Background, calculates difference, then
Whether successfully fallen, comprised the concrete steps that according to diversity judgement cargo:
The first step pre-processes video frame using the method for step (2), forms edge image；
Second step makes the difference edge image and background image, forms difference image；
Third step does binarization threshold segmentation to differential image；
4th step does morphological transformation to the image after Threshold segmentation, first carries out expansion process, carries out corrosion treatment afterwards；
5th step is found image outline, and is marked using rectangle frame；
6th step removes the lesser rectangle frame of area, calculates the area summation of surplus rectangle frame, and reference area accounting；
7th step uses time-based moving average method correction area accounting；
8th step, judges whether revised area accounting is greater than preset threshold, if it is greater, then thinking that cargo has fallen
It falls, terminates；Otherwise, the first step is returned.
(4) stop conveyer belt, close camera.
Due to the application of the above technical scheme, compared with the prior art, the invention has the following advantages:
A kind of Vending Machine cargo based on dual camera of the invention falls detection method,
(1) invention installs camera in holder two sides respectively, and places by diagonal line, the camera shooting relative to top placement
Head can avoid the shooting lesser problem of kinds of goods, can be in addition, relative to infrared ray grating, inductor interval is not present in camera
Detect smaller kinds of goods, flat kinds of goods.
(2) invention pastes black and white gridiron pattern paster in holder side plate, when transparent kinds of goods (such as glassware) fall into holder
When, due to light refraction, camera can detect the tessellated deformation of black and white, to detect transparent substance.
(3) invention handles black and white lattice paster using binarization threshold segmentation and edge detection algorithm, forms background image,
Since black and white contrast is huge, even if illumination changes, the Background which forms is also almost unchanged, effectively avoids
Influence of the environment light to freight detection.
(4) invention detects cargo using video, rather than captures image, can real-time control cargo path conveyer belt (bullet
Spring) running, without be previously set conveyer belt (spring) running time.
(5) invention has used time smoothing (sliding average) method when calculating kinds of goods ratio, can effectively avoid image
It is judged by accident caused by mutation (holder shakes, camera shakes).
(6) shooting background figure before each shipment of the invention can avoid different time, not on the same day without default Background
It is influenced caused by illumination variation under compression ring border.
Detailed description of the invention
Technical scheme of the present invention is further explained with reference to the accompanying drawing:
Attached drawing 1 is the flow chart that a kind of Vending Machine cargo based on dual camera of the invention falls detection method.
Specific embodiment
The present invention will now be explained with reference to the accompanying drawings.
It is as shown in Fig. 1 that a kind of Vending Machine cargo based on dual camera of the present invention falls detection side
Method, including the Vending Machine with holder；Two side baffle of holder of the Vending Machine installs camera additional respectively；The camera shooting
Head is diagonal to be placed；Two side baffle of holder, which is pasted to draw, the tessellated paster of black and white；Detecting step are as follows:
(1) it is completed when equipment detects that user pays, layer stops where holder rises to cargo, at this point, starting holder two
Side camera is captured；
(2) image is captured in the image processing module processing for starting equipment local, first according to the holder side plate of measured in advance
Black and white chessboard case is set, and is cut and is captured image, and extraneous areas is removed, and then, gray processing processing is done to picture is cut, finally, making
Edge detection is carried out to it with sobel edge detection operator, generates edge image, and save edge image as Background；
(3) after background shooting, start cargo path conveyer belt, while starting holder both sides camera shooting tripod head state；
Start each frame of the image processing module processing shooting video of Vending Machine, and compared with Background, calculates difference, then
Whether successfully fallen, comprised the concrete steps that according to diversity judgement cargo:
The first step pre-processes video frame using the method for step (2), forms edge image；
Second step makes the difference edge image and background image, forms difference image；
Third step does binarization threshold segmentation to differential image；
4th step does morphological transformation to the image after Threshold segmentation, first carries out expansion process, carries out corrosion treatment afterwards；
5th step is found image outline, and is marked using rectangle frame；
6th step removes the lesser rectangle frame of area, calculates the area summation of surplus rectangle frame, and reference area accounting；
7th step uses time-based moving average method correction area accounting；
8th step, judges whether revised area accounting is greater than preset threshold, if it is greater, then thinking that cargo has fallen
It falls, terminates；Otherwise, the first step is returned.
(4) stop conveyer belt, close camera.
When it is implemented, the both sides side plate of equipment cargo holder installs camera respectively, placed according to diagonal positions, one
A camera is located at left side side plate, and close to holder front edge, another is located at the right side plate, close holder rear edge, and two
A camera is located at sustained height, and camera horizontal centre is located at side plate height center position on the lower side, camera base and holder
Pedestal is concordant.
Left and right sides baffle pastes black and white gridiron pattern paster respectively, and by baffle range, all (except camera, institute is in place for covering
Set), the paster is as detection target.
Matte management is done on holder surface, reduce cargo shadow or it is reflective caused by influence.
Implementation of the invention can be divided into following steps:
S1, after the completion of user's payment, layer stops where holder rises to cargo, prepares shipment；At this point, starting holder two sides
Camera is captured, and image M1, M2, the corresponding left side camera of M1, the corresponding right side camera of M2 are generated；It is required that picture format is RGB
Color image or gray level image, other forms need to be converted.
S2 pre-processes M1, M2, forms Background B1, the B2 unrelated with illumination.
Its processing step is:
(S2.1) it is set according to the holder side plate black and white chessboard case of measured in advance, cuts M1, M2, removed extraneous areas, obtain
To image C1, C2.
(S2.2) it if picture format is RGB color image, needs to be C1, C2 gray processing processing, obtains gray level image
G1、G2。
(S2.3) edge detection is carried out to G1, G2 using sobel operator, generates edge image B1, B2.When it is implemented,
Sobel operator uses the kernel of 3*3, carries out derivation to the direction x and the direction y respectively, then folds the result of both direction
Add.
(S2.4) it is saved B1, B2 as Background.
S3 starts cargo path conveyer belt (spring), while starting holder both sides camera shooting tripod head state.
S4, each frame F1, F2 of dual camera shooting are compared with Background B1, B2, difference are calculated, then according to difference
It is different to judge whether cargo successfully falls.It is comprised the concrete steps that:
(S4.1) it sets and falls decision threshold as T1, rectangular area threshold value is T2, smoothing factor α, average area accounting
ForWhen it is implemented, the value of T1 is preset as 0.2, threshold value T2 is preset as 200, and smoothing factor is that α is set as 0.9, average
Area accountingIt is set as 0, specific value can be adjusted according to the actual situation.
(S4.2) frame F1, F2 in video is extracted, is pre-processed using step (2.1)-(2.4) method, is formed
Edge image F ' 1, F ' 2.
(S4.3) F ' 1, F ' 2 are made the difference respectively with B1, B2, forms difference image D1, D2, its calculation formula is: Di(x,y)
=| Fi’(x,y)-Bi(x,y)|
Wherein, Di(x,y)、Fi' (x, y) and Bi(x, y) respectively represent i-th of difference diagram, x in video frame and background image
The pixel value of row y column.
(S4.4) binarization threshold segmentation is carried out to D1, D2, generates image I1, I2.Segmentation threshold is preset as 100, can root
Factually border light conditions are adjusted.
(S4.5) morphological image transformation is carried out to I1, I2, first carries out expansive working, carry out etching operation afterwards, form figure
As K1, K2.Expansion, corrosion are all made of the round kernel that size is 9*9, each iteration 2 times.
(S4.6) profile point is found in K1, K2, and marks profile exterior square boundary, formation square boundary set R1,
R2。
(S4.7) area of the surrounded rectangle of square boundary is calculated, removal area is less than the rectangle frame of T2, obtains new square
Shape boundary set R ' 1, R ' 2.
(S4.8) the sum of rectangular area composed by all square boundaries S1, S2 in R ' 1, R ' 2 is calculated separately, and calculates face
Accounting r1, r2 of the product relative to image.
(S4.9) average area accounting is corrected using moving average methodIts formula are as follows:
(S4.10) judgeWhether there is any one to be greater than T1, if it is, thinking that cargo has been fallen, detects
Terminate；Otherwise, return step (S4.2).
S5 stops conveyer belt (spring), closes camera.
A kind of Vending Machine cargo based on dual camera of the invention falls detection method,
(1) invention installs camera in holder two sides respectively, and places by diagonal line, the camera shooting relative to top placement
Head can avoid the shooting lesser problem of kinds of goods, can be in addition, relative to infrared ray grating, inductor interval is not present in camera
Detect smaller kinds of goods, flat kinds of goods.
(2) invention pastes black and white gridiron pattern paster in holder side plate, when transparent kinds of goods (such as glassware) fall into holder
When, due to light refraction, camera can detect the tessellated deformation of black and white, to detect transparent substance.
(3) invention handles black and white lattice paster using binarization threshold segmentation and edge detection algorithm, forms background image,
Since black and white contrast is huge, even if illumination changes, the Background which forms is also almost unchanged, effectively avoids
Influence of the environment light to freight detection.
(4) invention detects cargo using video, rather than captures image, can real-time control cargo path conveyer belt (bullet
Spring) running, without be previously set conveyer belt (spring) running time.
(5) invention has used time smoothing (sliding average) method when calculating kinds of goods ratio, can effectively avoid image
It is judged by accident caused by mutation (holder shakes, camera shakes).
(6) shooting background figure before each shipment of the invention can avoid different time, not on the same day without default Background
It is influenced caused by illumination variation under compression ring border.
The above embodiments merely illustrate the technical concept and features of the present invention, and its object is to allow person skilled in the art
Scholar can understand the contents of the present invention and be implemented, and it is not intended to limit the scope of the present invention, it is all according to the present invention
Equivalent change or modification made by Spirit Essence, should be covered by the scope of protection of the present invention.
Claims (1)
1. a kind of Vending Machine cargo based on dual camera falls detection method, it is characterised in that: including with holder from
Dynamic vending machine；Two side baffle of holder of the Vending Machine installs camera additional respectively；The camera is diagonally placed；The cloud
Two side baffle of platform, which is pasted to draw, the tessellated paster of black and white；Detecting step are as follows:
(1) it is completed when equipment detects that user pays, layer stops where holder rises to cargo, at this point, starting holder two sides are taken the photograph
As head is captured；
(2) image is captured in the image processing module processing for starting equipment local, first according to the holder side plate black and white of measured in advance
Gridiron pattern position cuts and captures image, removes extraneous areas, then, gray processing processing is done to picture is cut, finally, using
Sobel edge detection operator carries out edge detection to it, generates edge image, and save edge image as Background；
(3) after background shooting, start cargo path conveyer belt, while starting holder both sides camera shooting tripod head state；Starting
Each frame of the image processing module processing shooting video of Vending Machine, and compared with Background, difference is calculated, then basis
Whether diversity judgement cargo successfully falls, and comprises the concrete steps that:
The first step pre-processes video frame using the method for step (2), forms edge image；
Second step makes the difference edge image and background image, forms difference image；
Third step does binarization threshold segmentation to differential image；
4th step does morphological transformation to the image after Threshold segmentation, first carries out expansion process, carries out corrosion treatment afterwards；
5th step is found image outline, and is marked using rectangle frame；
6th step removes the lesser rectangle frame of area, calculates the area summation of surplus rectangle frame, and reference area accounting；
7th step uses time-based moving average method correction area accounting；
8th step, judges whether revised area accounting is greater than preset threshold, if it is greater, then thinking that cargo has been fallen, ties
Beam；Otherwise, the first step is returned.
(4) stop conveyer belt, close camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811607304.9A CN109712315B (en) | 2018-12-27 | 2018-12-27 | Automatic vending machine cargo falling detection method based on double cameras |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811607304.9A CN109712315B (en) | 2018-12-27 | 2018-12-27 | Automatic vending machine cargo falling detection method based on double cameras |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109712315A true CN109712315A (en) | 2019-05-03 |
| CN109712315B CN109712315B (en) | 2021-04-20 |
Family
ID=66258647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811607304.9A Active CN109712315B (en) | 2018-12-27 | 2018-12-27 | Automatic vending machine cargo falling detection method based on double cameras |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109712315B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110363905A (en) * | 2019-07-31 | 2019-10-22 | 浪潮金融信息技术有限公司 | The method of the positioning of vending machine detection zone and detection shipment based on sliding rail |
| CN110443847A (en) * | 2019-07-31 | 2019-11-12 | 浪潮金融信息技术有限公司 | A kind of automatic vending machine head position finding and detection method based on camera |
| CN110475046A (en) * | 2019-07-31 | 2019-11-19 | 浪潮金融信息技术有限公司 | A kind of method of vending machine installation phase orientation detection zone |
| CN110807816A (en) * | 2019-10-31 | 2020-02-18 | 浪潮金融信息技术有限公司 | Automatic vending machine holder positioning detection method |
| CN113159074A (en) * | 2021-04-26 | 2021-07-23 | 京东数科海益信息科技有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN113762248A (en) * | 2021-01-20 | 2021-12-07 | 北京京东振世信息技术有限公司 | Target landing detection method and device, electronic equipment and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001006168A (en) * | 1999-03-31 | 2001-01-12 | Hoya Corp | Fabrication method of glass substrate for information recording medium, and fabrication method of information recording medium |
| CN101476878A (en) * | 2008-10-24 | 2009-07-08 | 北京秦润玻璃有限公司 | Detection method for architectural glass surface optical reflection image deflection |
| US20130335563A1 (en) * | 2012-06-19 | 2013-12-19 | Mckesson Financial Holdings | Method, apparatus, and computer program product for replenishment of articles in a dispensing system |
| JP2014127168A (en) * | 2012-12-27 | 2014-07-07 | Nec Corp | Vending machine management device, data processing method of the same and program |
| CN105486700A (en) * | 2016-02-01 | 2016-04-13 | 许迪 | System for detecting defects of transparent object and use method thereof |
| CN107833361A (en) * | 2017-09-28 | 2018-03-23 | 中南大学 | A kind of method that automatic vending machine based on image recognition falls Cargo Inspection survey |
| US20180096555A1 (en) * | 2016-10-01 | 2018-04-05 | Cantaloupe Systems, Inc. | Method and device of automatically determining a planogram in vending |
| CN108182417A (en) * | 2017-12-29 | 2018-06-19 | 广东安居宝数码科技股份有限公司 | Shipment detection method, device, computer equipment and automatic vending machine |
| CN108416902A (en) * | 2018-02-28 | 2018-08-17 | 成都果小美网络科技有限公司 | Real-time object identification method based on difference identification and device |
| CN108877040A (en) * | 2018-06-04 | 2018-11-23 | 北京无人店科技有限公司 | Automatic monitoring method, device, electronic equipment and the computer readable storage medium of open unmanned counter |
| CN108985339A (en) * | 2018-06-21 | 2018-12-11 | 浙江工业大学 | A kind of supermarket's articles from the storeroom method for identifying and classifying based on target identification Yu KNN algorithm |
| CN109003390A (en) * | 2018-06-29 | 2018-12-14 | 深圳和而泰数据资源与云技术有限公司 | A kind of commodity recognition method, self-service machine and computer readable storage medium |
-
2018
- 2018-12-27 CN CN201811607304.9A patent/CN109712315B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001006168A (en) * | 1999-03-31 | 2001-01-12 | Hoya Corp | Fabrication method of glass substrate for information recording medium, and fabrication method of information recording medium |
| CN101476878A (en) * | 2008-10-24 | 2009-07-08 | 北京秦润玻璃有限公司 | Detection method for architectural glass surface optical reflection image deflection |
| US20130335563A1 (en) * | 2012-06-19 | 2013-12-19 | Mckesson Financial Holdings | Method, apparatus, and computer program product for replenishment of articles in a dispensing system |
| JP2014127168A (en) * | 2012-12-27 | 2014-07-07 | Nec Corp | Vending machine management device, data processing method of the same and program |
| CN105486700A (en) * | 2016-02-01 | 2016-04-13 | 许迪 | System for detecting defects of transparent object and use method thereof |
| US20180096555A1 (en) * | 2016-10-01 | 2018-04-05 | Cantaloupe Systems, Inc. | Method and device of automatically determining a planogram in vending |
| CN107833361A (en) * | 2017-09-28 | 2018-03-23 | 中南大学 | A kind of method that automatic vending machine based on image recognition falls Cargo Inspection survey |
| CN108182417A (en) * | 2017-12-29 | 2018-06-19 | 广东安居宝数码科技股份有限公司 | Shipment detection method, device, computer equipment and automatic vending machine |
| CN108416902A (en) * | 2018-02-28 | 2018-08-17 | 成都果小美网络科技有限公司 | Real-time object identification method based on difference identification and device |
| CN108877040A (en) * | 2018-06-04 | 2018-11-23 | 北京无人店科技有限公司 | Automatic monitoring method, device, electronic equipment and the computer readable storage medium of open unmanned counter |
| CN108985339A (en) * | 2018-06-21 | 2018-12-11 | 浙江工业大学 | A kind of supermarket's articles from the storeroom method for identifying and classifying based on target identification Yu KNN algorithm |
| CN109003390A (en) * | 2018-06-29 | 2018-12-14 | 深圳和而泰数据资源与云技术有限公司 | A kind of commodity recognition method, self-service machine and computer readable storage medium |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110363905A (en) * | 2019-07-31 | 2019-10-22 | 浪潮金融信息技术有限公司 | The method of the positioning of vending machine detection zone and detection shipment based on sliding rail |
| CN110443847A (en) * | 2019-07-31 | 2019-11-12 | 浪潮金融信息技术有限公司 | A kind of automatic vending machine head position finding and detection method based on camera |
| CN110475046A (en) * | 2019-07-31 | 2019-11-19 | 浪潮金融信息技术有限公司 | A kind of method of vending machine installation phase orientation detection zone |
| CN110363905B (en) * | 2019-07-31 | 2021-09-17 | 浪潮金融信息技术有限公司 | Vending machine detection area positioning and goods discharge detection method based on sliding rail |
| CN110443847B (en) * | 2019-07-31 | 2022-08-05 | 浪潮金融信息技术有限公司 | Automatic vending machine holder positioning detection method based on camera |
| CN110807816A (en) * | 2019-10-31 | 2020-02-18 | 浪潮金融信息技术有限公司 | Automatic vending machine holder positioning detection method |
| CN110807816B (en) * | 2019-10-31 | 2022-08-09 | 浪潮金融信息技术有限公司 | Automatic vending machine holder positioning detection method |
| CN113762248A (en) * | 2021-01-20 | 2021-12-07 | 北京京东振世信息技术有限公司 | Target landing detection method and device, electronic equipment and storage medium |
| CN113762248B (en) * | 2021-01-20 | 2024-05-24 | 北京京东振世信息技术有限公司 | Target landing detection method and device, electronic equipment and storage medium |
| CN113159074A (en) * | 2021-04-26 | 2021-07-23 | 京东数科海益信息科技有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN113159074B (en) * | 2021-04-26 | 2024-02-09 | 京东科技信息技术有限公司 | Image processing method, device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109712315B (en) | 2021-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109712315A (en) | A kind of Vending Machine cargo based on dual camera falls detection method | |
| CN101770646B (en) | Edge detection method based on Bayer RGB images | |
| CN106228546B (en) | A kind of detection method and device of board | |
| US8319854B2 (en) | Shadow removal in an image captured by a vehicle based camera using a non-linear illumination-invariant kernel | |
| JP2007234019A (en) | Vehicle image area specifying device and method for it | |
| JP2001227924A (en) | Wheel measuring apparatus | |
| CN105092473B (en) | A kind of quality determining method and system of polysilicon membrane | |
| WO2022068438A1 (en) | Method, apparatus and system for testing static contact angle of reagent on asphalt | |
| CN107218894A (en) | A kind of subpixel accuracy thickness of detector detection method of fast and stable | |
| CN106775077A (en) | Touch panel | |
| WO2015125296A1 (en) | Local location computation device and local location computation method | |
| US20150324651A1 (en) | Three-dimensional object detection device and three-dimensional object detection method | |
| US8610770B2 (en) | Image sensing apparatus and method for sensing target that has defective portion region | |
| CN109087295A (en) | Bridge based on gray value sciagraphy reveals muscle visible detection method | |
| CN109343041A (en) | The monocular distance measuring method driven for high-grade intelligent auxiliary | |
| CN108827597A (en) | A kind of the hot spot uniformity detection method and detection system of structured light projection device | |
| CN110572628A (en) | Projector based on double-path laser fixed-included-angle distance measurement and horizontal trapezoid correction method thereof | |
| EP2063259A1 (en) | Method for inspecting mounting status of electronic component | |
| CN110475046B (en) | Method for positioning detection area in installation stage of vending machine | |
| CN102314258B (en) | Optical touch system as well as object position calculating device and method | |
| CN208863001U (en) | Optical projection system | |
| CN102073877B (en) | Method and system for detecting boxing by machine vision | |
| CN109934126A (en) | Vehicle tail smoke detection method and system | |
| CN210536819U (en) | Projector based on double-path laser fixed-included-angle distance measurement | |
| WO2017092589A1 (en) | Method and device for determining portrait contour in image |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210326 Address after: 215100 818 Wusong Road, Wusong River Industrial Park, Wuzhong development area, Suzhou, Jiangsu Applicant after: INSPUR FINANCIAL INFORMATION TECHNOLOGY Co.,Ltd. Address before: 215100 Building 1, 178 Tayun Road, Yuexi street, Wuzhong District, Suzhou City, Jiangsu Province Applicant before: SUZHOU INSPUR INTELLIGENT SOFTWARE Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |