CN106254864A - Snowflake in monitor video and noise noise detecting method - Google Patents

Snowflake in monitor video and noise noise detecting method Download PDF

Info

Publication number
CN106254864A
CN106254864A CN201610872016.0A CN201610872016A CN106254864A CN 106254864 A CN106254864 A CN 106254864A CN 201610872016 A CN201610872016 A CN 201610872016A CN 106254864 A CN106254864 A CN 106254864A
Authority
CN
China
Prior art keywords
noise
ratio
yardstick
piecemeal
zonule
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
Application number
CN201610872016.0A
Other languages
Chinese (zh)
Other versions
CN106254864B (en
Inventor
徐向华
金建成
程宗毛
张善卿
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.)
Hangzhou Dianzi University
Hangzhou Electronic Science and Technology University
Original Assignee
Hangzhou Electronic Science and Technology University
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 Hangzhou Electronic Science and Technology University filed Critical Hangzhou Electronic Science and Technology University
Priority to CN201610872016.0A priority Critical patent/CN106254864B/en
Publication of CN106254864A publication Critical patent/CN106254864A/en
Application granted granted Critical
Publication of CN106254864B publication Critical patent/CN106254864B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N17/00—Diagnosis, testing or measuring for television systems or their details
    • H04N17/02—Diagnosis, testing or measuring for television systems or their details for colour television signals
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/758—Involving statistics of pixels or of feature values, e.g. histogram matching
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/14—Picture signal circuitry for video frequency region
    • H04N5/21—Circuitry for suppressing or minimising disturbance, e.g. moiré or halo

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The present invention relates to the snowflake in a kind of monitor video and noise noise detecting method.First the present invention does poor frame and processes and eliminate fixed background impact, and carries out maximum variance between clusters and obtain optimal binary-state threshold, re-uses optimal threshold binaryzation difference frame figure, to highlight interference characteristic；Next divides equally bianry image is the statistic in small area statistics zonule；Stationarity finally by statistic judges whether snow noise or the method for noise noise.The method can detect the image being distributed noise noise containing snow noise or approaches uniformity, well adapting to property.The present invention carries out statistics based on real scene sample data and determines that judgment threshold, snow noise and noise noise measuring rate are high, and real-time is good.

Description

Snowflake in monitor video and noise noise detecting method
Technical field
The invention mainly relates to video image quality diagnostic field, particularly to the snow noise in a kind of video image and Noise noise method for detecting abnormality, it is adaptable to snow noise and the noise noise measuring of approaches uniformity distribution.
Background technology
Along with becoming increasingly popular of video monitoring, the abnormal conditions occurred in video monitoring the most quickly increase.Video approximation is all The noise of even distribution and snow noise are exactly two kinds in exception, and the existence of interference can badly influence the recognizability of image. Lose original information the most completely.Therefore find that this exception is just particularly important in time.Obviously in substantial amounts of video face The mode of front manual detection can not meet demand；And the cost of human input is more and more higher, is not easy to system administration.
The detection method of current snow noise and noise noise has: Zhang Wei, Fu Songlin et al. are " a kind of based on convolutional Neural The image noise detection method of network " (patent No.: 201410215084.0) proposes by collecting sample image and according to making an uproar Vertex type manually marks classification, and these sample images input convolutional neural networks system carries out the instruction of disaggregated model Practice, and also the sample image block of classification error is collected in categorizing process and carry out relearning classification, from there through people The mode that work and machine coordinate is labeled noise of classifying, and is finally reached testing goal.Luo Tao, height wait people quietly " based on minimum The noise detection method that locally mean square deviation calculates " (patent No.: 201510688993.0) proposes a kind of according to neighborhood of pixel points Interior local mean square deviation carries out local detection with the difference size of the local mean square deviation removing itself and judges whether this point is noise The method of point.Shi Zaifeng, Zhou Jiahui et al. " based on secondary noise detection image denoising method " (patent No.: 201510757953.7 propose Adaptive Second noise spot detection method based on directional information in).Wan Chen, Yang Bo are " a kind of The four directional operator video noise detection sides based on improving " in (patent No.: 201210428662.X) proposition according to four directions calculations Image is scanned by son, obtains the minima of four directional operator central values, and records preservation minima, and then obtains this frame figure The number of the pixel in smooth region in Xiang, finally judges the method whether this two field picture exists noise.He Qing, cold refined etc. People propose in the system and method for snow noise " a kind of monitoring video occur " (201410636977.2) a kind of based on The detection method of target image signal to noise ratio.
Summary of the invention
It is an object of the invention to for the deficiencies in the prior art, it is provided that the present invention proposes the snowflake in a kind of monitor video With noise noise detecting method.First do poor frame to process and eliminate fixed background impact, and carry out maximum variance between clusters and obtain Good binary-state threshold, re-uses optimal threshold binaryzation difference frame figure, to highlight interference characteristic；Next divides equally bianry image is community Statistic in statistics zonule, territory；Stationarity finally by statistic judges whether snow noise or noise noise Method.The method can detect the image being distributed noise noise containing snow noise or approaches uniformity, well adapting to property.
Technical scheme step is as follows:
Step 1: obtain target video, extracts the figure image width of video with high.
Step 2: extract the picture frame in video sequence, and the storage format of picture frame is converted into single channel by multichannel Gray level image storage format.
Step 3: the grayscale format image sequence of step 2 is taken turns doing before and after's frame frame difference and processes, obtain error image sequence.
Step 4: the error image sequence of step 3 is carried out maximum variance between clusters process and obtains optimal binary-state threshold, And by this threshold value, difference frame figure is carried out binaryzation, obtain binaryzation difference frame figure.
Step 5: the binaryzation difference frame figure of step 4 carries out piecemeal operation, and repeatedly the yardstick of piecemeal is different.
Binaryzation difference frame figure is divided into multiple zonule under a kind of piecemeal yardstick by 5-1., and calculates each zonule block The interior zonule block number not containing connected region and the ratio I of the total number of zonule block；
5-2. calculates the number ratio with this zonule block area that pixel value in the block of each zonule is the pixel of 1 II, the area ratio vector of a length of zonule number is constituted with ratio II.
5-3., for different piecemeal yardsticks, is all calculated ratio I, ratio II and area ratio vector.
Step 6: for different piecemeal yardsticks, calculate its standard deviation and average respectively by area ratio vector, thus Obtain the ratio III of standard deviation and average；Every kind of piecemeal yardstick all has the ratio III of its correspondence；By the ratio under different piecemeal yardsticks Value III composition ratio vector；The threshold decision vector that and different piecemeal yardstick vectorial by ratio is constituted compares, it is judged that this difference frame Whether there is snow noise or noise noise.
Described threshold decision vector is many experiments gained.
The present invention has the beneficial effect that:
The present invention is directed to snow noise and noise noise problem in monitor video, it is proposed that first pass through poor frame and remove fixing Background influence, thus reach prominent snow noise or approaches uniformity distribution noise noise purpose；And pass through maximum variance between clusters The mode highlighting interference noise obtains being easy to the bianry image of analysis.Mode again by statistical sample draws snow noise Judgment threshold with noise noise measuring.It is finally reached detection snow noise and the method for approaches uniformity distribution noise noise.This Invention carries out statistics based on real scene sample data and determines that judgment threshold, snow noise and noise noise measuring rate are high, in real time Property is good.
Accompanying drawing explanation
Fig. 1: overall flowchart；
Fig. 2: Statistic analysis threshold figure；
Fig. 3: binaryzation result figure；
Fig. 4: data result figure；
Fig. 5: data result figure；
Detailed description of the invention
Below in conjunction with the accompanying drawings specific embodiments of the present invention are done and be described in more detail further.
As Figure 1-5, the snowflake in monitor video and noise noise detecting method, it is intended to solve to exist in monitor video Snow noise and the abnormality detection problem of noise noise of approaches uniformity distribution.In the presence of snow noise and noise, poor Frame bianry image has the feature of obvious approaches uniformity distribution, and then uses the standard deviation by calculating data and the ratio of average It is worth this statistic to judge the uniformity coefficient of data.Mode finally by statistical sample draws the differentiation threshold value of uniformity coefficient Judge whether snow noise or noise noise.The present invention implements process as it is shown in figure 1, comprise the steps:
Step 1: extract detection video or video flowing first judges whether video is single channel gray scale frame sequence, if not single-pass Road gray scale frame sequence, is converted into single channel gray level image by frame of video, and extract the width of frame of video be designated as W the most respectively, H。
Step 2: the sequence of single channel gray level image is taken turns doing the process of before and after's frame frame difference, obtains error image sequence.Right Error image sequence carries out maximum variance between clusters process and obtains optimal binary-state threshold, and by this threshold value, difference frame figure is carried out two Value, obtains binaryzation difference frame figure.
Obtain binary image such as accompanying drawing 3.
Step 3: binaryzation difference frame figure carries out piecemeal operation, and repeatedly the yardstick of piecemeal is different, if after i-th kind of grade divides yardstick The width of each zonule block is with high and be LiPixel, have employed decile yardsticks different in N altogether, and every kind of grade divides the L under yardsticki Value is i times of M, i.e. Li=M*i.Wherein i-th kind of grade divides the width of zonule block under yardstick, height to be designated as respectively: wi、hi。
Decile rule under every kind of yardstick is: wi=Li* W/ (W+H), hi=Li*H/(W+H)；
Wherein W, H are respectively the width of artwork with high；M is empirical value.In the present embodiment, N takes 17, M takes 20.
Binaryzation difference frame figure is divided into multiple zonule under a kind of piecemeal yardstick by 3-1., and calculates each zonule block The interior zonule block number without connected region and the ratio I of the total number of zonule block, be designated as L_counti,
3-2. calculates the number ratio with this zonule block area that pixel value in the block of each zonule is the pixel of 1 II, the area ratio vector of a length of zonule number is constituted with ratio II.Wherein the number of pixel is designated as S_countikj, Ratio II is designated as S_countikj/(wi*hi)；
3-3., for different piecemeal yardsticks, is all calculated ratio I, ratio II and area ratio vector, specifically counts Calculation formula is as follows:
Formula is as follows:
S i k j = S _ count i k j w i * h i
Wherein SikjIt is (k, j) the area accounting of individual zonule in i-th under decile yardstick
m i = Σ k = 1 h i Σ j = 1 w i S i k j w i * h i
V i = Σ k = 1 h i Σ j = 1 w i ( S i k j - m i ) ^ 2 w i * h i
T i = V i / m i
Wherein miM is that i-th kind of grade divides the long-pending average of accounting, V below yardstickiIt is that i-th kind of grade divides the side of long-pending accounting below yardstick Difference, TiIt it is i-th kind of grade ratio i.e. uniformity decision content of dividing scale calibration difference and average.
Snow noise and noise noise corresponding data image such as accompanying drawing 4 is obtained by this step process.
Step 4: by uniformity decision content TiWith L_countiThe corresponding judgment threshold added up with it respectively compares Relatively, approaches uniformity distribution is presented due to snow noise and noise noise its noise after step 2 processes.So the standard obtained Difference and average smaller and the region unit number accounting without connected region that obtains also can be the least or be approximately zero.Base Snow noise or noise noise is judged whether in such conclusion.If Tmin<T2<Tmax、T17<TtAnd L_counti<LTTime It is judged to snow noise, if 0 < T2≤ Tmin、T17<TtAnd L_counti<LTTime be judged to noise, other situation be judged to without snow Flower and noise noise.
Wherein TminThe judgment threshold lower bound of area ratio, T when being about 40 pixel for piecemeal yardstickmaxIt is figure for piecemeal yardstick Image width degree with height sum 1/8th pixels time area ratio the judgment threshold upper bound, LTThe judgment threshold upper bound for ratio I； T2For corresponding TminUniformity decision content under piecemeal yardstick, T17For corresponding TmaxUniformity decision content under piecemeal yardstick.This is real Execute the T in exampleminTake 0.42, TmaxTake 1, LTTake 0.06.Judgment threshold in other this embodiment of pixel size image is depended on The width of the piecemeals such as the premise being so suitable for is, acquirement is minimum and height sum are about 20 pixels.
Accompanying drawing 2 is specifically described:
Snow noise, noise noise and the sample of these two groups of situations non-will be there is under cut-and-dried many group fixed scenes Video sequence is used for statistical computation.Sample is repeated several times first three step illustrated of accompanying drawing 1 respectively, draws three groups of statistics Data.One group for there are snow noise data, one group for there is noise noise data, another group is for without snowflake and noise situation number According to.Take between three and reliably distinguish threshold value, bring sample to be tested inspection into.Part comparing result is shown in accompanying drawing 4 and Fig. 5.

Claims (7)

1. the snowflake in monitor video and noise noise detecting method, it is characterised in that comprise the steps:
Step 1: obtain target video, extracts the figure image width of video with high；
Step 2: extract the picture frame in video sequence, and the storage format of picture frame is converted into single pass ash by multichannel Degree image storage format；
Step 3: the grayscale format image sequence of step 2 is taken turns doing before and after's frame frame difference and processes, obtain error image sequence；
Step 4: the error image sequence of step 3 is carried out maximum variance between clusters process and obtains optimal binary-state threshold, and use This threshold value carries out binaryzation to difference frame figure, obtains binaryzation difference frame figure；
Step 5: the binaryzation difference frame figure of step 4 carries out piecemeal operation, and repeatedly the yardstick of piecemeal is different；If i-th kind of Equant ruler After degree, the width of each zonule block is with high and be LiPixel, have employed decile yardsticks different in N altogether, and every kind of grade is divided under yardstick LiValue is i times of M, i.e. Li=M*i；Wherein i-th kind of grade divides the width of zonule block under yardstick, height to be designated as respectively: wi、hi
Step 6: for different piecemeal yardsticks, calculate its standard deviation and average respectively by area ratio vector, thus obtain Standard deviation and the ratio III of average；Every kind of piecemeal yardstick all has the ratio III of its correspondence；By the ratio III under different piecemeal yardsticks Constitute ratio vector；The threshold decision vector that and different piecemeal yardstick vectorial by ratio is constituted compares, it is judged that whether this difference frame There is snow noise or noise noise.
Snowflake in monitor video the most according to claim 1 and noise noise detecting method, it is characterised in that step 5 has Body is as follows:
Binaryzation difference frame figure is divided into multiple zonule under a kind of piecemeal yardstick by 5-1., and calculates in the block of each zonule not Zonule block number containing connected region and the ratio I of the total number of zonule block, be designated as L_counti,
5-2. calculates the number ratio II with this zonule block area that pixel value in the block of each zonule is the pixel of 1, uses Ratio II constitutes the area ratio vector of a length of zonule number；
5-3., for different piecemeal yardsticks, is all calculated ratio I, ratio II and area ratio vector.
Snowflake in monitor video the most according to claim 2 and noise noise detecting method, it is characterised in that every kind of chi Decile rule under Du is: wi=Li* W/ (W+H), hi=Li*H/(W+H)；
Wherein W, H are respectively the width of artwork with high；M is empirical value.
Snowflake in monitor video the most according to claim 2 and noise noise detecting method, it is characterised in that step 5-2 The number of described pixel is designated as S_countikj, then ratio II is designated as S_countikj/(wi*hi)。
Snowflake in monitor video the most according to claim 2 and noise noise detecting method, it is characterised in that step 5-3 Described for different piecemeal yardsticks, all it is calculated ratio I, ratio II and area ratio vector, specific formula for calculation As follows:
Formula is as follows:
S i k j = S _ count i k j w i * h i
Wherein SikjIt is (k, j) the area accounting of individual zonule in i-th under decile yardstick
m i = &Sigma; k = 1 h i &Sigma; j = 1 w i S i k j w i * h i
V i = &Sigma; k = 1 h i &Sigma; i = 1 w i ( S i k j - m i ) ^ 2 w i * h i
T i = V i / m i
Wherein miM is that i-th kind of grade divides the long-pending average of accounting, V below yardstickiBe i-th kind of grade divide below yardstick long-pending accounting variance, TiIt it is i-th kind of grade ratio i.e. uniformity decision content of dividing scale calibration difference and average.
Snowflake in monitor video the most according to claim 5 and noise noise detecting method, it is characterised in that step 6 Concrete judgement is as follows:
By uniformity decision content TiWith L_countiThe corresponding judgment threshold added up with it respectively compares, if Tmin<T2< Tmax、T17<TtAnd L_counti<LTTime be judged to snow noise, if 0 < T2≤ Tmin、T17<TtAnd L_counti<LTTime be judged to Noise, other situation is judged to without snowflake and noise noise；
Wherein TminThe judgment threshold lower bound of area ratio, T when being about 40 pixel for piecemeal yardstickmaxIt is figure image width for piecemeal yardstick The judgment threshold upper bound of area ratio, L when spending 1/8th pixel with height sumTThe judgment threshold upper bound for ratio I；T2For Corresponding TminUniformity decision content under piecemeal yardstick, T17For corresponding TmaxUniformity decision content under piecemeal yardstick.
Snowflake in monitor video the most according to claim 6 and noise noise detecting method, it is characterised in that when N takes 17, when M takes 20, TminTake 0.42, TmaxTake 1, LTTake 0.06, when obtaining the width of the piecemeals such as minimum and highly sum in 20 pixels During left and right, TminAnd TmaxValue the judgment threshold of other pixel size image is still suitable for.
CN201610872016.0A 2016-09-30 2016-09-30 Snowflake and noise noise detecting method in monitor video Active CN106254864B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610872016.0A CN106254864B (en) 2016-09-30 2016-09-30 Snowflake and noise noise detecting method in monitor video

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610872016.0A CN106254864B (en) 2016-09-30 2016-09-30 Snowflake and noise noise detecting method in monitor video

Publications (2)

Publication Number Publication Date
CN106254864A true CN106254864A (en) 2016-12-21
CN106254864B CN106254864B (en) 2017-12-15

Family

ID=57612075

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610872016.0A Active CN106254864B (en) 2016-09-30 2016-09-30 Snowflake and noise noise detecting method in monitor video

Country Status (1)

Country Link
CN (1) CN106254864B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107453944A (en) * 2017-07-07 2017-12-08 上海斐讯数据通信技术有限公司 A kind of method and system for the optimal test connection number for determining network throughput test
CN109547777A (en) * 2018-11-06 2019-03-29 中国铁路上海局集团有限公司科学技术研究所 A kind of video noise rapid detection method of complex scene
CN109859124A (en) * 2019-01-11 2019-06-07 深圳奥比中光科技有限公司 A kind of depth image noise reduction method and device
CN112270317A (en) * 2020-10-16 2021-01-26 西安工程大学 Traditional digital water meter reading identification method based on deep learning and frame difference method

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6741277B1 (en) * 2000-01-13 2004-05-25 Koninklijke Philips Electronics N.V. System and method for automated testing of digital television receivers
CN101123681A (en) * 2007-09-20 2008-02-13 宝利微电子***控股公司 A digital image noise reduction method and device
CN103095967A (en) * 2011-10-28 2013-05-08 浙江大华技术股份有限公司 Video noise quantization calculation method and video noise quantization calculation system
CN103377472A (en) * 2012-04-13 2013-10-30 富士通株式会社 Method for removing adhering noise and system
CN104469345A (en) * 2014-12-10 2015-03-25 北京理工大学 Video fault diagnosis method based on image processing

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6741277B1 (en) * 2000-01-13 2004-05-25 Koninklijke Philips Electronics N.V. System and method for automated testing of digital television receivers
CN101123681A (en) * 2007-09-20 2008-02-13 宝利微电子***控股公司 A digital image noise reduction method and device
CN103095967A (en) * 2011-10-28 2013-05-08 浙江大华技术股份有限公司 Video noise quantization calculation method and video noise quantization calculation system
CN103377472A (en) * 2012-04-13 2013-10-30 富士通株式会社 Method for removing adhering noise and system
CN104469345A (en) * 2014-12-10 2015-03-25 北京理工大学 Video fault diagnosis method based on image processing

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
来晟: "《基于FPGA的视频图像雪花检测研究》", 《信息通信》 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107453944A (en) * 2017-07-07 2017-12-08 上海斐讯数据通信技术有限公司 A kind of method and system for the optimal test connection number for determining network throughput test
CN107453944B (en) * 2017-07-07 2021-04-02 台州市吉吉知识产权运营有限公司 Method and system for determining optimal test connection number of network throughput test
CN109547777A (en) * 2018-11-06 2019-03-29 中国铁路上海局集团有限公司科学技术研究所 A kind of video noise rapid detection method of complex scene
CN109859124A (en) * 2019-01-11 2019-06-07 深圳奥比中光科技有限公司 A kind of depth image noise reduction method and device
CN109859124B (en) * 2019-01-11 2020-12-18 深圳奥比中光科技有限公司 Depth image noise reduction method and device
CN112270317A (en) * 2020-10-16 2021-01-26 西安工程大学 Traditional digital water meter reading identification method based on deep learning and frame difference method
CN112270317B (en) * 2020-10-16 2024-06-07 西安工程大学 Reading identification method of traditional digital water meter based on deep learning and frame difference method

Also Published As

Publication number Publication date
CN106254864B (en) 2017-12-15

Similar Documents

Publication Publication Date Title
CN106254864A (en) Snowflake in monitor video and noise noise detecting method
CN102883175B (en) Methods for extracting depth map, judging video scene change and optimizing edge of depth map
CN102855617B (en) Method and system for processing adaptive images
CN101127908B (en) Video image motion processing method and implementation device with global feature classification
CN102842203B (en) Method for monitoring bridge fault on basis of video image
CN104318582B (en) Detection method for bad state of rotating double-lug component pin of high-speed rail contact network
CN104268505A (en) Automatic cloth defect point detection and recognition device and method based on machine vision
CN106056968B (en) A kind of method for detecting parking stalls based on optical imagery
CN105263018A (en) Method and device for detecting superposed stripe in video image
CN104732236B (en) A kind of crowd&#39;s abnormal behaviour intelligent detecting method based on layered shaping
CN115100206B (en) Printing defect identification method for textile with periodic pattern
CN101739549A (en) Face detection method and system
CN114897908B (en) Machine vision-based method and system for analyzing defects of selective laser powder spreading sintering surface
CN106503640A (en) A kind of detection method for taking bus zone
CN111753749A (en) Lane line detection method based on feature matching
CN115909256B (en) Road disease detection method based on road visual image
CN106408563A (en) Snow noise detection method based on variation coefficient
CN113706566A (en) Perfuming spray performance detection method based on edge detection
CN115171218A (en) Material sample feeding abnormal behavior recognition system based on image recognition technology
CN106127813B (en) The monitor video motion segments dividing method of view-based access control model energy sensing
CN109711313B (en) Real-time video monitoring method for identifying sewage poured into river channel
CN106951820A (en) Passenger flow statistical method based on annular template and ellipse fitting
CN111882549A (en) Automatic detection and identification method and system for grayish green small foreign fibers
Li et al. Detection of small size defects in belt layer of radial tire based on improved faster r-cnn
CN111339843A (en) Method and device for detecting crowdedness of motor train unit carriage

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant