CN103747213A - Traffic monitoring video real-time defogging method based on moving targets - Google Patents

Traffic monitoring video real-time defogging method based on moving targets Download PDF

Info

Publication number
CN103747213A
CN103747213A CN201410017407.5A CN201410017407A CN103747213A CN 103747213 A CN103747213 A CN 103747213A CN 201410017407 A CN201410017407 A CN 201410017407A CN 103747213 A CN103747213 A CN 103747213A
Authority
CN
China
Prior art keywords
frame
image
processing
mist elimination
video
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
CN201410017407.5A
Other languages
Chinese (zh)
Other versions
CN103747213B (en
Inventor
卓力
胡笑尘
李晓光
张菁
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.)
Beijing University of Technology
Original Assignee
Beijing University of Technology
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 Beijing University of Technology filed Critical Beijing University of Technology
Priority to CN201410017407.5A priority Critical patent/CN103747213B/en
Publication of CN103747213A publication Critical patent/CN103747213A/en
Application granted granted Critical
Publication of CN103747213B publication Critical patent/CN103747213B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Closed-Circuit Television Systems (AREA)
  • Image Analysis (AREA)

Abstract

The invention relates to a traffic monitoring video real-time defogging method based on moving targets. According to the characteristics of traffic monitoring videos, the contents of video frames are divided into foreground moving targets and background parts, and different methods are respectively adopted for carrying out defogging processing on the foreground and the background, wherein the foreground moving targets are mainly processed. Meanwhile, the relevance between the adjacent frames of the videos is utilized for adopting non-estimation or less-estimation methods on the background, and the processing speed is greatly accelerated. For 720*576 standard-definition videos, the processing speed being 25 frames/second can be reached, the real-time processing requirements can be met, and the problem that the defogging method in the prior art cannot meet the traffic monitoring video real-time processing requirement due to high processing complexity is solved. The defogging processing method provided by the invention has the advantages that higher pertinence is realized, the real color of the foreground moving targets can be more effectively remained, the color distortion can be reduced, and good foundation is laid for the further intelligent processing of traffic videos.

Description

The real-time defogging method capable of a kind of Traffic Surveillance Video based on moving target
Technical field
The invention belongs to image/video signals process field, relate to the real-time defogging method capable of a kind of Traffic Surveillance Video based on moving target.
Background technology
Serious haze weather can cause serious impact to the quality of Traffic Surveillance Video, and mist elimination is processed significant to the follow-up intelligent analysis work of Traffic Surveillance Video.The key of mist elimination processing is to estimate transmissivity and atmosphere light intensity.If estimate and, just can obtain the image after mist elimination by observed image.At present, the defogging method capable based on dark primary priori is main stream approach.
Dark primary priori rule is pointed out: in a regional area of most natural images, some pixel has at least a Color Channel to have very low value.According to dark primary priori rule, can estimate atmosphere light intensity and transmissivity.
The method of estimation of atmosphere light intensity is: in dark primary image, first by the brightness value of each pixel according to successively decrease order according to sequence, then determine that numerical values recited is point residing position in dark primary image of front 0.1%, finally find out the valuation as atmosphere light intensity of maximum in the corresponding original mist image-region in these positions.
The method of estimation of transmissivity is: first, the each pixel that has mist image observing is got to the minimum value in tri-passages of RGB, obtain a width gray level image.Next gray level image is carried out to mini-value filtering operation, then by atmosphere light intensity, deduct the gray value of each point of image after filtering and obtain transmission plot.Transmission plot obtains normalized transmissivity divided by atmosphere light intensity.
Application number is that the patent of CN201210125321.5 discloses a kind of video image defogging method capable based on self adaptation tolerance.The method utilization guiding filtering is carried out refinement to the estimation of transmissivity, thereby obtains more careful transmission plot, makes mist elimination result finer and smoother.But the process of guiding filtering will consume a large amount of time, can not meet the requirement of real-time of Video processing.
Application number is that the patent of CN201110134572.5 discloses a kind of real-time video defogging system.This system does not have huge guiding filtering consuming time, and utilizes digital integrated circuit to realize above-mentioned mist elimination step, by the hardware-accelerated speed that promotes mist elimination processing.The video rate of this system processing 288 × 352 can reach for 60 frame/seconds, and the SD video rate of processing 720 × 576 can reach for 15 frame/seconds.The method can be processed the video that size is less in real time, but can only substantially meet real-time processing requirements for 720 × 576 SD video.
Equal content of differentiate between images not when in addition, above-mentioned two kinds of methods are processed.For Traffic Surveillance Video, this processing method effect being equal to is unsatisfactory.This is because in order to guarantee the mist elimination effect of integral image, tends to cause the moving target in monitoring scene to produce cross-color, and follow-up intelligent analysis is produced to certain impact.
Summary of the invention
The present invention proposes the real-time defogging method capable of a kind of Traffic Surveillance Video based on moving target.The method, according to the feature of Traffic Surveillance Video, is divided into foreground moving target and background part by the content of frame of video, to prospect and background, adopts respectively diverse ways to process.The color characteristics that can retain well like this foreground target, can meet again the requirement of real-time processing, for follow-up transport information intelligent processing method lays the first stone.
For achieving the above object, the present invention by the following technical solutions.
1. the division of video content
What the intelligent processing method of Traffic Surveillance Video was more paid close attention to is moving target, therefore should guarantee emphatically the mist elimination treatment effect of this part content.To the Traffic Surveillance Video collecting, first the present invention adopts neighbor frame difference method that frame of video is divided into moving target and two parts of background.For this two parts content, adopt respectively different defogging method capables to process, to guarantee the video quality after mist elimination.
2. the mist elimination processing of different content
First estimate the value of atmosphere light intensity and transmissivity, then by observed image, obtain the image after mist elimination.The estimation of transmissivity is part the most consuming time in whole mist elimination process.How to introduce the content for Traffic Surveillance Video below, estimate the value of atmosphere light intensity and transmissivity, meet the requirement of processing in real time.
(1) estimation of atmosphere light intensity
Atmosphere light intensity remains unchanged conventionally within long period of time, therefore, and without the value of each frame of video all being estimated to atmosphere light intensity.The present invention estimates the value of an atmosphere light intensity at set intervals to frame of video, thereby greatly reduces the computation complexity of atmosphere light intensity valuation.
(2) estimation of transmissivity
For the frame of video of having estimated atmosphere light intensity, carry out the estimation of transmissivity, and whole frame of video is carried out to mist elimination processing.For other frame of video, moving target and background parts are processed respectively.
1) the mist elimination processing of moving target
For the processing of foreground moving target is had more to specific aim, also in order to promote mist elimination processing speed, the present invention only carries out estimation and the mist elimination processing of transmissivity to foreground moving target, and has removed mini-value filtering process, the speed of estimating to improve transmissivity.
In real life, in air, always exist some particles, people still can feel the impact of mist when the object of observing at a distance, the existence of mist can allow people feel the existence of the depth of field in addition, therefore be necessary in mist elimination, to retain mist to a certain degree, to strengthen the sense of reality and the depth of field sense of image.For this reason, the present invention introduces a decay factor and controls mist elimination dynamics.
2) the mist elimination processing of background
For Traffic Surveillance Video, its background is basic fixing, between consecutive frame, changes not quite, and therefore the present invention directly adopts the mist elimination result in previous frame, no longer reappraises the value of transmissivity, can greatly promote like this speed of mist elimination processing.
When the moving target after mist elimination and background area are combined, obtain a complete mist elimination frame of video.
Compared with prior art, the present invention has following obvious advantage and useful effect:
1. computation complexity is low, execution speed is fast.It is high that existing defogging method capable is processed complexity, cannot meet the demand that Traffic Surveillance Video is processed in real time.The present invention, according to the feature of Traffic Surveillance Video, is divided into foreground moving target and background two parts by the content of frame of video, processes respectively, and wherein emphasis is processed foreground moving target.Meanwhile, utilize the correlation between video consecutive frame, background is adopted and do not estimated or few method of estimating, greatly improved processing speed.For 720 × 576 SD video, can reach the processing speed of 25 frame/seconds, meet the demand of processing in real time.
2. mist elimination processing has more specific aim, can more effectively retain the true colors of foreground moving target.The present invention treats with a certain discrimination foreground moving target and background, and emphasis is processed foreground moving target, for follow-up transport information intelligent processing method is laid a good foundation.
Accompanying drawing explanation
Fig. 1 is the flow chart of defogging method capable involved in the present invention;
Fig. 2 is the image that application the present invention carries out Traffic Surveillance Video mist elimination processing front and back, (a) is the image before mist elimination, is (b) image after mist elimination;
Fig. 3 is the seesaw color contrast image of automobile of application the present invention and guiding filtering method mist elimination, (a) be the automobile image before mist elimination, (b) for the automobile image after application guiding filtering method mist elimination, (c) for applying the automobile image after mist elimination of the present invention.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention will be further described.
The flow chart of the real-time defogging method capable of Traffic Surveillance Video based on moving target that the present invention proposes as shown in Figure 1, specifically comprises the following steps:
Step 1, carries out mist elimination processing to the first frame of Traffic Surveillance Video.
Step 1.1, estimates atmosphere light intensity.
(1), to there being mist image get the minimum pixel value in tri-Color Channels of RGB and carry out mini-value filtering, obtain dark primary image:
J dark ( x ) = min c ∈ { R , G , B } ( min y ∈ Ω ( x ) ( I c ( y ) ) ) - - - ( 1 )
In formula, J dark(x) be dark primary image; I c(y) for what observe, there is a mist image, y ∈ Ω (x), Ω (x) is a boxed area centered by pixel y.
(2) brightness value of pixel in dark primary image is sorted by the order of successively decreasing, determine that numerical values recited is point residing position in dark primary image of front 0.1%;
(3) find out the maximum of the atmosphere light intensity in the corresponding original mist image-region in these positions, i.e. the valuation of atmosphere light intensity.
Step 1.2, estimates transmissivity.
To there being mist image, get the minimum pixel value in tri-Color Channels of RGB, obtain a width gray level image, with atmosphere light intensity valuation A, deduct the gray value of each point of this image again and the product of attenuation coefficient obtains transmission plot, finally by transmission plot, divided by A, obtain normalized transmissivity:
t ~ ( x ) = 1 - ω min c ∈ { R , G , B } ( I c ( y ) A ) - - - ( 2 )
In formula,
Figure BDA0000456982710000042
for normalized transmissivity valuation; ω is an attenuation coefficient, for controlling the intensity of mist elimination, and 0 < ω≤1, ω gets 0.7 conventionally.
Step 1.3, carries out mist elimination processing.
Image after mist elimination is:
J ( x ) = I ( x ) - A min ( max ( K | I ( x ) - A | | , 1 ) &CenterDot; max ( t ~ ( x ) , t 0 ) , 1 ) + A - - - ( 3 )
In formula, t 0be the lower limit of transmissivity, be conventionally set to 0.1; K is tolerance, and for revising the bright areas that does not meet dark primary a priori assumption, K gets the A value of 0.5-0.6 times conventionally.
Step 2, since the second frame, adopts neighbor frame difference method that frame of video is divided into foreground moving target and background two parts, then to these two parts, adopts respectively different defogging method capables to process.
Step 2.1, the frame that calculates present frame and former frame is poor, is all not more than the part of threshold value T for the three-channel difference of RGB, is judged as background area, and remainder is judged as foreground moving target area.Threshold value T is taken as 2 conventionally.
Step 2.2, if foreground moving target area performs step 1.2,1.3, carries out mist elimination to it; If background area, directly utilizes the mist elimination result of relevant position in previous frame to substitute, no longer carry out defogging.
Step 2.3, repeating step 2, until handle all frame of video.
In order to guarantee that the estimation of atmosphere light intensity A is approached to actual value more, repeated execution of steps 1 and 2, re-starts estimation to A at set intervals.
Shown in Fig. 2 is the Traffic Surveillance Video mist elimination effect contrast figure who adopts the method for the present invention's proposition to obtain.As can be seen from the figure, the method that adopts the present invention to propose, can obtain good mist elimination effect.
For the present invention's mist elimination effect compared with prior art relatively, apply respectively the present invention and guiding filtering method of the prior art carries out mist elimination processing to one section of Traffic Surveillance Video.Fig. 3 is the comparison of two kinds of method mist elimination effects.As can be seen from the figure, adopt the picture contrast after the mist elimination that guides filtering method higher, but the color of automobile is excessively dark, has occurred obvious cross-color.Image after mist elimination of the present invention has retained the true colors of foreground moving target better, for further traffic video intelligent processing method is laid a good foundation.
Application number is that the SD video rate of the patent processing 720 × 576 of CN201110134572.5 can reach for 15 frame/seconds.Experiment shows, the method that the present invention proposes is processed 720 × 576 SD video rate can reach for 25 frame/seconds, met the real-time processing requirements of SD video.The HD video speed of processing 1280 × 720 can reach 13-14 frame/second, and processing speed is very fast.

Claims (2)

1. the real-time defogging method capable of the Traffic Surveillance Video based on moving target, it is characterized in that, according to the feature of Traffic Surveillance Video, the content of frame of video is divided into foreground moving target and background part, to prospect and background, adopt respectively diverse ways to carry out mist elimination processing, comprise the following steps:
Step 1, carries out mist elimination processing to the first frame of Traffic Surveillance Video;
Step 1.1, estimates atmosphere light intensity;
(1), to there being mist image get the minimum pixel value in tri-Color Channels of RGB and carry out mini-value filtering, obtain dark primary image:
J dark ( x ) = min c &Element; { R , G , B } ( min y &Element; &Omega; ( x ) ( I c ( y ) ) )
In formula, J dark(x) be dark primary image; I c(y) for what observe, there is a mist image, y ∈ Ω (x), Ω (x) is a boxed area centered by pixel y;
(2) brightness value of pixel in dark primary image is sorted by the order of successively decreasing, determine that numerical values recited is point residing position in dark primary image of front 0.1%;
(3) find out the max pixel value in the corresponding original mist image-region in these positions, be the valuation A of atmosphere light intensity;
Step 1.2, estimates transmissivity;
To there being mist image, get the minimum pixel value in tri-Color Channels of RGB, obtain a width gray level image, with atmosphere light intensity valuation A, deduct the gray value of each point of this image again and the product of attenuation coefficient obtains transmission plot, finally by transmission plot, divided by A, obtain normalized transmissivity:
t ~ ( x ) = 1 - &omega; min c &Element; { R , G , B } ( I c ( y ) A )
In formula,
Figure FDA0000456982700000013
for normalized transmissivity valuation; ω is an attenuation coefficient, for controlling the intensity of mist elimination, and 0 < ω≤1, ω gets 0.7 conventionally;
Step 1.3, carries out mist elimination processing;
Image after mist elimination is:
J ( x ) = I ( x ) - A min ( max ( K | I ( x ) - A | | , 1 ) &CenterDot; max ( t ~ ( x ) , t 0 ) , 1 ) + A
In formula, t 0be the lower limit of transmissivity, be conventionally set to 0.1; K is tolerance, and for revising the bright areas that does not meet dark primary a priori assumption, K gets the A value of 0.5-0.6 times conventionally;
Step 2, since the second frame, adopts neighbor frame difference method that frame of video is divided into foreground moving target and background two parts, then to these two parts, adopts respectively different defogging method capables to process;
Step 2.1, the frame that calculates present frame and former frame is poor, is all not more than the part of threshold value T for the three-channel difference of RGB, is judged as background area, and remainder is judged as foreground moving target area; Threshold value T gets 2 conventionally;
Step 2.2, if foreground moving target area performs step 1.2,1.3, carries out mist elimination to it; If background area, directly utilizes the mist elimination result of relevant position in previous frame to substitute, no longer carry out defogging;
Step 2.3, repeating step 2, until handle all frame of video.
2. the real-time defogging method capable of a kind of Traffic Surveillance Video based on moving target according to claim 1, it is characterized in that, in order to guarantee that the estimation of atmosphere light intensity A is approached to actual value more, at set intervals between repeated execution of steps 1 and 2, A is re-started to estimation.
CN201410017407.5A 2014-01-15 2014-01-15 A kind of real-time defogging method of the Traffic Surveillance Video based on moving target Expired - Fee Related CN103747213B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410017407.5A CN103747213B (en) 2014-01-15 2014-01-15 A kind of real-time defogging method of the Traffic Surveillance Video based on moving target

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410017407.5A CN103747213B (en) 2014-01-15 2014-01-15 A kind of real-time defogging method of the Traffic Surveillance Video based on moving target

Publications (2)

Publication Number Publication Date
CN103747213A true CN103747213A (en) 2014-04-23
CN103747213B CN103747213B (en) 2017-04-05

Family

ID=50504199

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410017407.5A Expired - Fee Related CN103747213B (en) 2014-01-15 2014-01-15 A kind of real-time defogging method of the Traffic Surveillance Video based on moving target

Country Status (1)

Country Link
CN (1) CN103747213B (en)

Cited By (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104200435A (en) * 2014-08-29 2014-12-10 武汉大学 Single-image defogging method based on fog imaging model
CN104408757A (en) * 2014-11-07 2015-03-11 吉林大学 Method and system for adding haze effect to driving scene video
CN104717400A (en) * 2015-02-03 2015-06-17 北京理工大学深圳研究院 Real-time defogging method of monitoring video
CN104732497A (en) * 2015-03-31 2015-06-24 北京交通大学 Image defogging method, FPGA and defogging system including FPGA
CN105282421A (en) * 2014-07-16 2016-01-27 宇龙计算机通信科技(深圳)有限公司 Defogged image obtaining method, device and terminal
CN105550999A (en) * 2015-12-09 2016-05-04 西安邮电大学 Video image enhancement processing method based on background reuse
CN105635526A (en) * 2015-12-25 2016-06-01 国网重庆市电力公司电力科学研究院 Real-time video defogging method and system applied in video monitoring system
CN105959510A (en) * 2016-04-22 2016-09-21 湖南工学院 Video rapid defogging method
CN106340009A (en) * 2016-08-18 2017-01-18 河海大学常州校区 Parallel-binocular-based power line detection method and system
CN106683052A (en) * 2015-11-06 2017-05-17 奥多比公司 Dehazing photos and videos using visual artifact suppression
CN107194894A (en) * 2017-05-25 2017-09-22 河南师范大学 A kind of video defogging method and its system
CN107277299A (en) * 2017-07-27 2017-10-20 广东欧珀移动通信有限公司 Image processing method, device, mobile terminal and computer-readable recording medium
CN107360344A (en) * 2017-06-27 2017-11-17 西安电子科技大学 Monitor video rapid defogging method
CN107451969A (en) * 2017-07-27 2017-12-08 广东欧珀移动通信有限公司 Image processing method, device, mobile terminal and computer-readable recording medium
CN107454318A (en) * 2017-07-27 2017-12-08 广东欧珀移动通信有限公司 Image processing method, device, mobile terminal and computer-readable recording medium
CN108830803A (en) * 2018-05-17 2018-11-16 昆明理工大学 A kind of traffic video image defogging optimization algorithm
CN108921805A (en) * 2018-07-06 2018-11-30 厦门理工学院 A kind of image and video remove haze method, computer installation and storage medium
CN110852965A (en) * 2019-10-31 2020-02-28 湖北大学 Video illumination enhancement method and system based on generation countermeasure network
CN112750089A (en) * 2020-12-27 2021-05-04 同济大学 Optical remote sensing image defogging method based on local block maximum and minimum pixel prior
CN114638763A (en) * 2022-03-24 2022-06-17 华南理工大学 Image defogging method, system, computer device and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103079062A (en) * 2013-02-05 2013-05-01 武汉科技大学 Intelligent video surveillance system
CN103093202A (en) * 2013-01-21 2013-05-08 信帧电子技术（北京）有限公司 Car logo locating method and car logo locating device
JP2013141210A (en) * 2011-12-30 2013-07-18 Hitachi Ltd Image defogging apparatus, image defogging method, and image processing system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013141210A (en) * 2011-12-30 2013-07-18 Hitachi Ltd Image defogging apparatus, image defogging method, and image processing system
CN103093202A (en) * 2013-01-21 2013-05-08 信帧电子技术（北京）有限公司 Car logo locating method and car logo locating device
CN103079062A (en) * 2013-02-05 2013-05-01 武汉科技大学 Intelligent video surveillance system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
数字图像去雾与超分辨率重建算法研究;侯天峰;《中国优秀硕士学位论文全文数据库（电子期刊）》;20110915;正文第7-21页 *
视频监控图像去雾方法研究;邵长艳;《中国优秀硕士学位论文全文数据库（电子期刊）》;20121015;正文第35-75页 *

Cited By (30)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105282421A (en) * 2014-07-16 2016-01-27 宇龙计算机通信科技(深圳)有限公司 Defogged image obtaining method, device and terminal
CN105282421B (en) * 2014-07-16 2018-08-24 宇龙计算机通信科技(深圳)有限公司 A kind of mist elimination image acquisition methods, device and terminal
CN104200435A (en) * 2014-08-29 2014-12-10 武汉大学 Single-image defogging method based on fog imaging model
CN104408757B (en) * 2014-11-07 2017-11-14 吉林大学 The method and system of haze effect are added in a kind of video to Driving Scene
CN104408757A (en) * 2014-11-07 2015-03-11 吉林大学 Method and system for adding haze effect to driving scene video
CN104717400A (en) * 2015-02-03 2015-06-17 北京理工大学深圳研究院 Real-time defogging method of monitoring video
CN104732497A (en) * 2015-03-31 2015-06-24 北京交通大学 Image defogging method, FPGA and defogging system including FPGA
CN106683052A (en) * 2015-11-06 2017-05-17 奥多比公司 Dehazing photos and videos using visual artifact suppression
CN106683052B (en) * 2015-11-06 2022-03-04 奥多比公司 Defogging photographs and videos using visual artifact suppression
CN105550999A (en) * 2015-12-09 2016-05-04 西安邮电大学 Video image enhancement processing method based on background reuse
CN105635526A (en) * 2015-12-25 2016-06-01 国网重庆市电力公司电力科学研究院 Real-time video defogging method and system applied in video monitoring system
CN105959510A (en) * 2016-04-22 2016-09-21 湖南工学院 Video rapid defogging method
CN105959510B (en) * 2016-04-22 2019-04-26 湖南工学院 A kind of video rapid defogging method
CN106340009A (en) * 2016-08-18 2017-01-18 河海大学常州校区 Parallel-binocular-based power line detection method and system
CN106340009B (en) * 2016-08-18 2018-12-11 河海大学常州校区 A kind of electric power line detecting method and system based on parallel binocular
CN107194894A (en) * 2017-05-25 2017-09-22 河南师范大学 A kind of video defogging method and its system
CN107360344B (en) * 2017-06-27 2020-02-21 西安电子科技大学 Rapid defogging method for monitoring video
CN107360344A (en) * 2017-06-27 2017-11-17 西安电子科技大学 Monitor video rapid defogging method
CN107451969A (en) * 2017-07-27 2017-12-08 广东欧珀移动通信有限公司 Image processing method, device, mobile terminal and computer-readable recording medium
CN107451969B (en) * 2017-07-27 2020-01-10 Oppo广东移动通信有限公司 Image processing method, image processing device, mobile terminal and computer readable storage medium
CN107454318A (en) * 2017-07-27 2017-12-08 广东欧珀移动通信有限公司 Image processing method, device, mobile terminal and computer-readable recording medium
CN107277299B (en) * 2017-07-27 2020-08-18 Oppo广东移动通信有限公司 Image processing method, image processing device, mobile terminal and computer readable storage medium
CN107277299A (en) * 2017-07-27 2017-10-20 广东欧珀移动通信有限公司 Image processing method, device, mobile terminal and computer-readable recording medium
CN108830803A (en) * 2018-05-17 2018-11-16 昆明理工大学 A kind of traffic video image defogging optimization algorithm
CN108921805A (en) * 2018-07-06 2018-11-30 厦门理工学院 A kind of image and video remove haze method, computer installation and storage medium
CN108921805B (en) * 2018-07-06 2020-11-03 厦门理工学院 Image and video haze removing method, computer device and storage medium
CN110852965A (en) * 2019-10-31 2020-02-28 湖北大学 Video illumination enhancement method and system based on generation countermeasure network
CN112750089A (en) * 2020-12-27 2021-05-04 同济大学 Optical remote sensing image defogging method based on local block maximum and minimum pixel prior
CN114638763A (en) * 2022-03-24 2022-06-17 华南理工大学 Image defogging method, system, computer device and storage medium
CN114638763B (en) * 2022-03-24 2024-05-24 华南理工大学 Image defogging method, system, computer device and storage medium

Also Published As

Publication number Publication date
CN103747213B (en) 2017-04-05

Similar Documents

Publication Publication Date Title
CN103747213A (en) Traffic monitoring video real-time defogging method based on moving targets
CN102750674B (en) Video image defogging method based on self-adapting allowance
Jiang et al. Night video enhancement using improved dark channel prior
CN105046677B (en) A kind of enhancing treating method and apparatus for traffic video image
CN103077504B (en) A kind of image defogging method capable based on self-adaptation illumination calculation
CN106251301A (en) A kind of single image defogging method based on dark primary priori
CN103049888A (en) Image/video demisting method based on combination of dark primary color of atmospheric scattered light
CN102637293B (en) Moving image processing device and moving image processing method
CN103985091A (en) Single image defogging method based on luminance dark priori method and bilateral filtering
CN104794688A (en) Single image defogging method and device based on depth information separation sky region
CN102611828A (en) Real-time enhanced processing system for foggy continuous video image
CN110148093B (en) Image defogging improvement method based on dark channel prior
CN104809709A (en) Single-image self-adaptation defogging method based on domain transformation and weighted quadtree decomposition
CN104036466A (en) Video defogging method and system
CN105761230A (en) Single image defogging method based on sky region segmentation processing
Zheng et al. Infrared traffic image enhancement algorithm based on dark channel prior and gamma correction
CN102306307B (en) Positioning method of fixed point noise in color microscopic image sequence
CN107358585A (en) Misty Image Enhancement Method based on fractional order differential and dark primary priori
CN104809700B (en) A kind of low-light (level) video real time enhancing method based on bright passage
CN107360344A (en) Monitor video rapid defogging method
CN104717400A (en) Real-time defogging method of monitoring video
CN111598814B (en) Single image defogging method based on extreme scattering channel
CN103106796A (en) Vehicle detection method and device of intelligent traffic surveillance and control system
CN105046670A (en) Image rain removal method and system
CN108765337B (en) Single color image defogging processing method based on dark channel prior and non-local MTV model

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
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20170405