CN110473245A - A kind of depth image document screening method and system - Google Patents

A kind of depth image document screening method and system Download PDF

Info

Publication number
CN110473245A
CN110473245A CN201910674809.5A CN201910674809A CN110473245A CN 110473245 A CN110473245 A CN 110473245A CN 201910674809 A CN201910674809 A CN 201910674809A CN 110473245 A CN110473245 A CN 110473245A
Authority
CN
China
Prior art keywords
image
line
subgraph
profile
depth image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910674809.5A
Other languages
Chinese (zh)
Inventor
卢仕辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhongshan City Oppe Metal Products Co Ltd
Original Assignee
Zhongshan City Oppe Metal Products Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhongshan City Oppe Metal Products Co Ltd filed Critical Zhongshan City Oppe Metal Products Co Ltd
Priority to CN201910674809.5A priority Critical patent/CN110473245A/en
Publication of CN110473245A publication Critical patent/CN110473245A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/51—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/55—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • 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
    • G06T7/55—Depth or shape recovery from multiple images
    • G06T7/564—Depth or shape recovery from multiple images from contours
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics

Abstract

The invention discloses a kind of depth image document screening method and system, it will real-time collected depth image file division be currently multiple subgraphs, and the characteristics of image for extracting subgraph carries out abnormal point estimation, to which the depth image file for filtering out qualified is stored, the less depth image of abnormal point can be quickly and effectively filtered out to be saved, it saves memory space and improves the collection effect and collecting efficiency of depth image acquisition equipment, improve the precision of collected depth image, it effectively increases and obtains accurate colouring information and depth information from depth image and then the reduction degree of the threedimensional model that restores object out or scene.

Description

A kind of depth image document screening method and system
Technical field
This disclosure relates to file storage, technical field of image processing, and in particular to a kind of depth image document screening method And system.
Background technique
Depth image is also referred to as range image, refers to distance (depth) conduct of each point in from image acquisition device to scene The image of pixel value, it directly reflects the geometry of scenery visible surface, existing during conventional depth Image Acquisition The depth image of some binocular depth camera acquisitions includes depth information, three-dimensional scene information with space multistory information, figure As required memory space is very big, image may be caused unstable due to the shake of equipment in the acquisition of depth image, And then it is inaccurate to lead to the depth information finally got, so that the precision of such depth image is lower, it substantially cannot be from figure Accurate colouring information and depth information are obtained as in, and then restores the threedimensional model of object out or scene.Therefore some Depth image value for preservation it is relatively low, serious waste memory space and collection effect, therefore, existing depth image is adopted The collecting efficiency of collection, image effect and the precision of acquisition are completely unsatisfactory.
Summary of the invention
To solve the above problems, the disclosure provides a kind of technical solution of depth image document screening method and system, it will Current collected depth image file division in real time is multiple subgraphs, and the characteristics of image for extracting subgraph carries out abnormal point Estimation is stored to filter out qualified depth image file.
To achieve the goals above, according to the one side of the disclosure, a kind of depth image document screening method is provided, it is described Method the following steps are included:
Depth image is denoted as the first image by S100；
First image segmentation is multiple subgraphs by watershed algorithm by S200, and the subgraph quantity of acquisition is n, note Subgraph is Σi,(0<i≤n)；
S300 extracts the characteristics of image of each subgraph profile；
S400 carries out abnormal point estimation according to characteristics of image；
S500 gives up the first image when the quantity of abnormal point in the first image is greater than outlier threshold；
S600 saves the first image when the quantity of abnormal point in the first image is less than or equal to outlier threshold.
Further, in S100, the depth image is to pass through laser radar Depth Imaging method, computer stereo vision Any one method is clapped relative to the horizon angle of depression by 30 ° in imaging, coordinate measuring machine method, Moire fringe technique, Structure light method Take the photograph acquisition image.
Further, in S300, the method for extracting the characteristics of image of each subgraph profile are as follows:
The method for extracting each subgraph profile is by any one in Canny operator, Sobel operator, Perwit operator The profile at operator detection image edge；Described image feature are as follows:
Feature={ Gri,Hi,Ai,Pi,Nli,Vli} (1)
In formula, GriIndicate subgraph ΣiGray average, Hi={ hi,siIndicate subgraph ΣiMiddle frequency of occurrence is most H, S component value, H, S component be subgraph hsv color space H, S component；AiFor sum of all pixels in subgraph；PiIt indicates Profile ContouriFocus point position, NliThe straight line in contour line after having recorded the profile dismantling of subgraph, VliFor subgraph The vertical line in contour line after the profile dismantling of picture；
NliAnd VliCalculation method it is as follows:
First with the marginal point P on the contour line of subgraph edge imagej(xij,yij), centered on (H < j≤m-H), construction Size is the sliding window Slop of L to profile ContouriLocal direction coding is carried out, default setting L=80 pixel, m is profile The sum of all pixels of line, contour line by group of edge points at；
The method of local direction coding are as follows: the extreme coordinates for setting the contour line line segment two sides that Slop is cut are respectively (xi1, yi1),(xi2,yi2), then marginal point PjLocal direction θ are as follows:
Wherein, straight line ratio factor s=D/L, D indicate endpoint (xi1,yi1),(xi2,yi2) between linear distance, L be sliding The length for the profile that window is intercepted, T are the threshold value of setting, default setting T=0.5；
The edge of subgraph edge image after coding will be split into a plurality of mutually consecutive straight-line segment in corner point, then Each straight-line segment is Nli={ l1,l2,…,lk, wherein K is the sum of straight line in profile, m1And m2Respectively indicate the beginning and end pixel distance profile starting point of kth straight line in profile Pixel number.
For the profile Contour of subgraphiIn straight line lkTaking two-end-point is A and B, lkInclined angle calculation it is public Formula are as follows:
Wherein,
If inclined angle | θk- 90 | < σ (disclosure default setting σ=10) judges lkFor vertical line, and it is saved in Vli。
Further, in S400, according to the method for the abnormal point estimation of characteristics of image progress are as follows:
By the vertical line Vl in all subgraph feature vectorsi, form parallel vertical line sequence line1,line2,..., linei...,linep, wherein straight line lineiLinear equation are as follows:
Y=aix+bi (4)
According to least square method to lineiIt carries out straight line fitting and obtains the minimum value of fitting a straight line error:
Determine slope ai, y intercept bi, crosspoint is then solved by any two fitting a straight lines of simultaneous:
The each crosspoint being calculated, as abnormal point set；By FuzzycMeans Clustering algorithm to each crosspoint It is clustered, the center for corresponding to most class members in Clustering is selected in the result of FuzzycMeans Clustering as abnormal Point Vr={ xi,yi, and then obtained the quantity of abnormal point in the first image.
Further, in S500 and S600, the outlier threshold is the integer numerical value manually set, in the disclosure, Default setting outlier threshold is 30.
The present invention also provides a kind of depth image file screening system, the system comprises: memory, processor and The computer program that can be run in the memory and on the processor is stored, the processor executes the computer Program operates in the unit of following system:
Image reading unit, for depth image to be denoted as the first image；
Image segmentation unit is multiple subgraphs for passing through watershed algorithm for the first image segmentation；
Feature extraction unit, for extracting the characteristics of image of each subgraph profile；
Abnormal point estimation unit, for carrying out abnormal point estimation according to characteristics of image；
Image gives up unit, for giving up the first image simultaneously when the quantity of abnormal point in the first image is greater than outlier threshold Go to image reading unit；
Image storing unit, for saving first when the quantity of abnormal point in the first image is less than or equal to outlier threshold Image.
The disclosure has the beneficial effect that the present invention provides a kind of depth image document screening method and system, can be quick It effectively filters out the less depth image of abnormal point to be saved, saves memory space and set with depth image acquisition is improved Standby collection effect and collecting efficiency, improves the precision of collected depth image, effectively increases and obtains from depth image Restore the reduction degree of the threedimensional model of object out or scene in turn to accurate colouring information and depth information.
Detailed description of the invention
By the way that the embodiment in conjunction with shown by attached drawing is described in detail, above-mentioned and other features of the disclosure will More obvious, identical reference label indicates the same or similar element in disclosure attached drawing, it should be apparent that, it is described below Attached drawing be only some embodiments of the present disclosure, for those of ordinary skill in the art, do not making the creative labor Under the premise of, it is also possible to obtain other drawings based on these drawings, in the accompanying drawings:
Fig. 1 show a kind of flow chart of depth image document screening method；
Fig. 2 show a kind of depth image file screening system structure chart.
Specific embodiment
It is carried out below with reference to technical effect of the embodiment and attached drawing to the design of the disclosure, specific structure and generation clear Chu, complete description, to be completely understood by the purpose, scheme and effect of the disclosure.It should be noted that the case where not conflicting Under, the features in the embodiments and the embodiments of the present application can be combined with each other.
It is as shown in Figure 1 to be come according to a kind of flow chart of depth image document screening method of the disclosure below with reference to Fig. 1 Illustrate a kind of depth image document screening method according to embodiment of the present disclosure.
The disclosure proposes a kind of depth image document screening method, specifically includes the following steps:
Depth image is denoted as the first image by S100；
First image segmentation is multiple subgraphs by watershed algorithm by S200, and the subgraph quantity of acquisition is n, note Subgraph is Σi,(0<i≤n)；
S300 extracts the characteristics of image of each subgraph profile；
S400 carries out abnormal point estimation according to characteristics of image；
S500 gives up the first image when the quantity of abnormal point in the first image is greater than outlier threshold；
S600 saves the first image when the quantity of abnormal point in the first image is less than or equal to outlier threshold.
Further, in S100, the depth image is to pass through laser radar Depth Imaging method, computer stereo vision Any one method is clapped relative to the horizon angle of depression by 30 ° in imaging, coordinate measuring machine method, Moire fringe technique, Structure light method Take the photograph acquisition image.
Further, in S300, the method for extracting the characteristics of image of each subgraph profile are as follows:
The method for extracting each subgraph profile is by any one in Canny operator, Sobel operator, Perwit operator The profile at operator detection image edge；Described image feature are as follows:
Feature={ Gri,Hi,Ai,Pi,Nli,Vli} (1)
In formula, GriIndicate subgraph ΣiGray average, Hi={ hi,siIndicate subgraph ΣiMiddle frequency of occurrence is most H, S component value, H, S component be subgraph hsv color space H, S component；AiFor sum of all pixels in subgraph；PiIt indicates Profile ContouriFocus point position, NliThe straight line in contour line after having recorded the profile dismantling of subgraph, VliFor subgraph The vertical line in contour line after the profile dismantling of picture；
NliAnd VliCalculation method it is as follows:
First with the marginal point P on the contour line of subgraph edge imagej(xij,yij), centered on (H < j≤m-H), construction Size is the sliding window Slop of L to profile ContouriLocal direction coding is carried out, default setting L=80 pixel, m is profile The sum of all pixels of line, contour line by group of edge points at；
The method of local direction coding are as follows: the extreme coordinates for setting the contour line line segment two sides that Slop is cut are respectively (xi1, yi1),(xi2,yi2), then marginal point PjLocal direction θ are as follows:
Wherein, straight line ratio factor s=D/L, D indicate endpoint (xi1,yi1),(xi2,yi2) between linear distance, L be sliding The length for the profile that window is intercepted, T are the threshold value of setting, default setting T=0.5；
The edge of subgraph edge image after coding will be split into a plurality of mutually consecutive straight-line segment in corner point, then Each straight-line segment is Nli={ l1,l2,…,lk, wherein K is the sum of straight line in profile, m1And m2Respectively indicate the beginning and end pixel distance profile starting point of kth straight line in profile Pixel number.
For the profile Contour of subgraphiIn straight line lkTaking two-end-point is A and B, lkInclined angle calculation it is public Formula are as follows:
Wherein,
If inclined angle | θk- 90 | < σ (disclosure default setting σ=10) judges lkFor vertical line, and it is saved in Vli。
Further, in S400, according to the method for the abnormal point estimation of characteristics of image progress are as follows:
By the vertical line Vl in all subgraph feature vectorsi, form parallel vertical line sequence line1,line2,..., linei...,linep, wherein straight line lineiLinear equation are as follows:
Y=aix+bi (4)
According to least square method to lineiIt carries out straight line fitting and obtains the minimum value of fitting a straight line error:
Determine slope ai, y intercept bi, crosspoint is then solved by any two fitting a straight lines of simultaneous:
The each crosspoint being calculated, as abnormal point set；By FuzzycMeans Clustering algorithm to each crosspoint It is clustered, the center for corresponding to most class members in Clustering is selected in the result of FuzzycMeans Clustering as abnormal Point Vr={ xi,yi, and then obtained the quantity of abnormal point in the first image.
Preferably, it is not save current collected first image that the first image is given up in S500, that is, is abandoned unqualified Image；It is that the first image is saved in memory that the first image is saved in S600, i.e. preservation qualified images.
Further, in S500 and S600, the outlier threshold is the integer numerical value manually set, in the disclosure, According to test experience, default setting outlier threshold is 30.
A kind of depth image file screening system that embodiment of the disclosure provides, is illustrated in figure 2 one kind of the disclosure Depth image file screening system structure chart, a kind of depth image file screening system of the embodiment include: processor, storage Device and storage in the memory and the computer program that can run on the processor, described in the processor execution The step in a kind of above-mentioned depth image file screening system embodiment is realized when computer program.
It can be transported in the memory and on the processor the system comprises: memory, processor and storage Capable computer program, the processor execute the computer program and operate in the unit of following system:
Image reading unit, for depth image to be denoted as the first image；
Image segmentation unit is multiple subgraphs for passing through watershed algorithm for the first image segmentation；
Feature extraction unit, for extracting the characteristics of image of each subgraph profile；
Abnormal point estimation unit, for carrying out abnormal point estimation according to characteristics of image；
Image gives up unit, for giving up the first image simultaneously when the quantity of abnormal point in the first image is greater than outlier threshold Go to image reading unit；
Image storing unit, for saving first when the quantity of abnormal point in the first image is less than or equal to outlier threshold Image.
A kind of depth image file screening system can run on desktop PC, notebook, palm PC and Cloud server etc. calculates in equipment.A kind of depth image file screening system, the system that can be run may include, but not only It is limited to, processor, memory.It will be understood by those skilled in the art that the example is only a kind of depth image document screening The example of system does not constitute the restriction to a kind of depth image file screening system, may include more more or less than example Component, perhaps combine certain components or different components, such as a kind of depth image file screening system can be with Including input-output equipment, network access equipment, bus etc..
Alleged processor can be central processing unit (Central Processing Unit, CPU), can also be it His general processor, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field- Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic, Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor Deng, the processor is a kind of control centre of depth image file screening system operating system, using various interfaces and Connection entirely a kind of depth image file screening system can operating system various pieces.
The memory can be used for storing the computer program and/or module, and the processor is by operation or executes Computer program in the memory and/or module are stored, and calls the data being stored in memory, described in realization A kind of various functions of depth image file screening system.The memory can mainly include storing program area and storing data Area, wherein storing program area can application program needed for storage program area, at least one function (such as sound-playing function, Image player function etc.) etc.；Storage data area, which can be stored, uses created data (such as audio data, electricity according to mobile phone Script for story-telling etc.) etc..In addition, memory may include high-speed random access memory, it can also include nonvolatile memory, such as Hard disk, memory, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card), at least one disk memory, flush memory device or other volatibility are solid State memory device.
Although the description of the disclosure is quite detailed and especially several embodiments are described, it is not Any of these details or embodiment or any specific embodiments are intended to be limited to, but should be considered as is by reference to appended A possibility that claim provides broad sense in view of the prior art for these claims explanation, to effectively cover the disclosure Preset range.In addition, the disclosure is described with inventor's foreseeable embodiment above, its purpose is to be provided with Description, and those equivalent modifications that the disclosure can be still represented to the unsubstantiality change of the disclosure still unforeseen at present.

Claims (5)

1. a kind of depth image document screening method, which is characterized in that the described method comprises the following steps:
Depth image is denoted as the first image by S100；
S200, by watershed algorithm by the first image segmentation be multiple subgraphs；
S300 extracts the characteristics of image of each subgraph profile；
S400 carries out abnormal point estimation according to characteristics of image；
S500 gives up the first image when the quantity of abnormal point in the first image is greater than outlier threshold；
S600 saves the first image when the quantity of abnormal point in the first image is less than or equal to outlier threshold.
2. a kind of depth image document screening method according to claim 1, which is characterized in that in S100, the depth Degree image is to pass through laser radar Depth Imaging method, computer stereo vision imaging, coordinate measuring machine method, Moire fringe technique, knot Any one method is to acquire image captured by 30 ° relative to the horizon angle of depression in structure light method.
3. a kind of depth image document screening method according to claim 2, which is characterized in that in S300, extract each The method of the characteristics of image of subgraph profile are as follows:
The method for extracting each subgraph profile is by any one operator in Canny operator, Sobel operator, Perwit operator The profile at detection image edge；
Described image feature are as follows:
Feature={ Gri,Hi,Ai,Pi,Nli,Vli} (1)
In formula, GriIndicate subgraph ΣiGray average, Hi={ hi,siIndicate subgraph ΣiMiddle frequency of occurrence most H, S Component value, H, S component are the H in the hsv color space of subgraph, S component；AiFor sum of all pixels in subgraph；PiIndicate profile ContouriFocus point position, NliThe straight line in contour line after having recorded the profile dismantling of subgraph, VliFor subgraph The vertical line in contour line after profile dismantling；
NliAnd VliCalculation method it is as follows:
First with the marginal point P on the contour line of subgraph edge imagej(xij,yij), centered on (H < j≤m-H), construct size For L sliding window Slop to profile ContouriLocal direction coding, default setting L=80 pixel are carried out, m is contour line Sum of all pixels, contour line by group of edge points at；
The method of local direction coding are as follows: the extreme coordinates for setting the contour line line segment two sides that Slop is cut are respectively (xi1,yi1), (xi2,yi2), then marginal point PjLocal direction θ are as follows:
Wherein, straight line ratio factor s=D/L, D indicate endpoint (xi1,yi1),(xi2,yi2) between linear distance, L is sliding window The length of the profile intercepted, T are the threshold value of setting, default setting T=0.5；
The edge of subgraph edge image after coding will be split into a plurality of mutually consecutive straight-line segment in corner point, then each straight Line line segment is Nli={ l1,l2,…,lk, wherein K is the sum of straight line in profile, m1And m2Respectively indicate the beginning and end pixel distance profile starting point of kth straight line in profile Pixel number；
For the profile Contour of subgraphiIn straight line lkTaking two-end-point is A and B, lkInclined angle calculation formula are as follows:
Wherein,
If inclined angle | θk- 90 | < σ judges lkFor vertical line, and it is saved in Vli。
4. a kind of depth image document screening method according to claim 3, which is characterized in that in S400, according to figure The method for carrying out abnormal point estimation as feature are as follows:
By the vertical line Vl in all subgraph feature vectorsi, form parallel vertical line sequence line1,line2,..., linei...,linep, wherein straight line lineiLinear equation are as follows:
Y=aix+bi (4)
According to least square method to lineiIt carries out straight line fitting and obtains the minimum value of fitting a straight line error:
Determine slope ai, y intercept bi, crosspoint is then solved by any two fitting a straight lines of simultaneous:
The each crosspoint being calculated, as abnormal point set；Each crosspoint is carried out by FuzzycMeans Clustering algorithm Cluster, selects the center that most class members are corresponded in Clustering as abnormal point V in the result of FuzzycMeans Clusteringr ={ xi,yi}。
5. a kind of depth image file screening system, which is characterized in that the system comprises: memory, processor and storage In the memory and the computer program that can run on the processor, the processor execute the computer program It operates in the unit of following system:
Image reading unit, for depth image to be denoted as the first image；
Image segmentation unit is multiple subgraphs for passing through watershed algorithm for the first image segmentation；
Feature extraction unit, for extracting the characteristics of image of each subgraph profile；
Abnormal point estimation unit, for carrying out abnormal point estimation according to characteristics of image；
Image gives up unit, for giving up the first image when the quantity of abnormal point in the first image is greater than outlier threshold and going to Image reading unit；
Image storing unit, for saving the first figure when the quantity of abnormal point in the first image is less than or equal to outlier threshold Picture.
CN201910674809.5A 2019-07-25 2019-07-25 A kind of depth image document screening method and system Pending CN110473245A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910674809.5A CN110473245A (en) 2019-07-25 2019-07-25 A kind of depth image document screening method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910674809.5A CN110473245A (en) 2019-07-25 2019-07-25 A kind of depth image document screening method and system

Publications (1)

Publication Number Publication Date
CN110473245A true CN110473245A (en) 2019-11-19

Family

ID=68508880

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910674809.5A Pending CN110473245A (en) 2019-07-25 2019-07-25 A kind of depth image document screening method and system

Country Status (1)

Country Link
CN (1) CN110473245A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114359114A (en) * 2022-03-16 2022-04-15 宁波杜比医疗科技有限公司 Mononuclear focus hue reduction method and device, electronic equipment and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120195471A1 (en) * 2011-01-31 2012-08-02 Microsoft Corporation Moving Object Segmentation Using Depth Images
CN106960424A (en) * 2017-03-31 2017-07-18 上海澜澈生物科技有限公司 Tubercle bacillus image segmentation and identification method and device based on optimized watershed algorithm
CN109191438A (en) * 2018-08-17 2019-01-11 中科光绘（上海）科技有限公司 A kind of method for recognizing impurities for laser foreign matter remover

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120195471A1 (en) * 2011-01-31 2012-08-02 Microsoft Corporation Moving Object Segmentation Using Depth Images
CN106960424A (en) * 2017-03-31 2017-07-18 上海澜澈生物科技有限公司 Tubercle bacillus image segmentation and identification method and device based on optimized watershed algorithm
CN109191438A (en) * 2018-08-17 2019-01-11 中科光绘（上海）科技有限公司 A kind of method for recognizing impurities for laser foreign matter remover

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114359114A (en) * 2022-03-16 2022-04-15 宁波杜比医疗科技有限公司 Mononuclear focus hue reduction method and device, electronic equipment and storage medium
CN114359114B (en) * 2022-03-16 2022-08-23 宁波杜比医疗科技有限公司 Mononuclear focus hue reduction method and device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
US9307221B1 (en) Settings of a digital camera for depth map refinement
CN109840881B (en) 3D special effect image generation method, device and equipment
CN112581629A (en) Augmented reality display method and device, electronic equipment and storage medium
US9542735B2 (en) Method and device to compose an image by eliminating one or more moving objects
CN105960800A (en) Image display device and image display system
JP5538868B2 (en) Image processing apparatus, image processing method and program
CN107103619B (en) Method, device and system for processing hair texture direction
CN108234826B (en) Image processing method and device
CN111161348B (en) Object pose estimation method, device and equipment based on monocular camera
CN109344750B (en) Complex structure three-dimensional object identification method based on structure descriptor
CN110473245A (en) A kind of depth image document screening method and system
Chen et al. Range image segmentation for modeling and object detection in urban scenes
CN115546027B (en) Image suture line determination method, device and storage medium
CN113496138A (en) Dense point cloud data generation method and device, computer equipment and storage medium
CN113256484B (en) Method and device for performing stylization processing on image
CN112785651A (en) Method and apparatus for determining relative pose parameters
CN116051736A (en) Three-dimensional reconstruction method, device, edge equipment and storage medium
CN108416346B (en) License plate character positioning method and device
JP2016045538A (en) Information processing apparatus, image determination method, and program
CN114723883A (en) Three-dimensional scene reconstruction method, device, equipment and storage medium
CN113963004A (en) Sampling method and device and electronic equipment
CN112967321A (en) Moving object detection method and device, terminal equipment and storage medium
CN109213515B (en) Multi-platform lower buried point normalization method and device and electronic equipment
CN112183431A (en) Real-time pedestrian number statistical method and device, camera and server
CN111630569B (en) Binocular matching method, visual imaging device and device with storage function

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
CB02 Change of applicant information

Address after: No.45 Zhaoyi Road, Dongsheng Town, Zhongshan City, Guangdong Province 528415

Applicant after: Guangdong AOPO smart home Co.,Ltd.

Address before: No.45 Zhaoyi Road, Dongsheng Town, Zhongshan City, Guangdong Province 528415

Applicant before: ZHONGSHAN AOPO METAL MANUFACTORY Co.,Ltd.

CB02 Change of applicant information
AD01 Patent right deemed abandoned

Effective date of abandoning: 20230922

AD01 Patent right deemed abandoned