CN105469394B - A kind of Intelligent target tracking based on complex environment - Google Patents
A kind of Intelligent target tracking based on complex environment Download PDFInfo
- Publication number
- CN105469394B CN105469394B CN201510805380.0A CN201510805380A CN105469394B CN 105469394 B CN105469394 B CN 105469394B CN 201510805380 A CN201510805380 A CN 201510805380A CN 105469394 B CN105469394 B CN 105469394B
- Authority
- CN
- China
- Prior art keywords
- gauss model
- pixel
- current time
- complex environment
- stream data
- 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.)
- Active
Links
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 230000003044 adaptive effect Effects 0.000 claims abstract description 6
- 238000001914 filtration Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 230000006978 adaptation Effects 0.000 claims description 3
- 230000000052 comparative effect Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims 1
- 230000009466 transformation Effects 0.000 abstract description 12
- 238000001556 precipitation Methods 0.000 abstract description 6
- 238000007664 blowing Methods 0.000 abstract description 4
- 238000000034 method Methods 0.000 abstract description 3
- 238000012544 monitoring process Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
Abstract
The invention discloses a kind of Intelligent target tracking based on complex environment, gather the video stream data at current time, each frame video image in video stream data is analyzed successively, starts mixed Gauss model, establishes background Gauss model and prospect Gauss model, filter the action interference in video, sleet fringes noise is removed by wavelet transformation and Fourier transformation, lock onto target, starts to perform tracking operation, during tracking, noise removal process is persistently carried out.The present invention effectively filters the various motion artifacts of picture in complex environment based on mixed Gauss model adaptive analysis algorithm is passed through, and the leaf as caused by blowing shakes etc., and the precipitation noise in picture can be effectively filtered out with reference to wavelet transformation and Fourier transformation.
Description
Technical field
The present invention relates to field of video monitoring, more particularly to a kind of Intelligent target tracking based on complex environment.
Background technology
With reaching its maturity with perfect for the technologies such as computer, network, communication, Streaming Media, video is lived in social production
In application it is increasingly extensive.In the computer vision systems such as intelligent video monitoring, navigation, remote sensing, Car license recognition, video is most
Main information source.But these systemic-functions are typically all to consider design based on normal weather condition, although outdoor
The application field of video monitoring system is very extensive, but it is due to play its well in the bad weathers such as rain, snow
Effect., also can normally work under the mal-conditions such as sleet in order to ensure that outdoor monitoring system can adapt to various weather conditions
Make, so being highly desirable to be removed research to the sleet in air, the image of acquisition is repaired, eliminate weather conditions
Interference, improve the stability of system.
The content of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of Intelligent target tracking based on complex environment
Method, based on by mixed Gauss model adaptive analysis algorithm, the various motion artifacts of picture in complex environment are effectively filtered,
Leaf shake etc., the precipitation noise in picture can be effectively filtered out with reference to wavelet transformation and Fourier transformation as caused by blowing.
The purpose of the present invention is achieved through the following technical solutions:A kind of Intelligent target tracking based on complex environment
Method, comprise the following steps:
S1, the video stream data for gathering current time, divide each frame video image in video stream data successively
Analysis, determines whether abnormal two field picture, if the progress Exception Type detection in the presence of if;
S2, start mixed Gauss model, each pixel of every frame video image in video stream data is established X high
This model;
S3, according to the weight of Gauss model the X Gauss model is ranked up, and accumulative summation is carried out to weight, if
The weight of top n Gauss model and more than predetermined threshold value, then be set to background pixel point by the top n Gauss model, establish background
Gauss model, rear X-N Gauss model is set to foreground pixel point, establishes prospect Gauss model;
S4, according to the average and variance of current time pixel and the history pixel of the pixel it is each pixel
Corresponding Gauss model is matched, the absolute value of the difference of current time pixel and the average of its history pixel is calculated, if this is exhausted
Preset matching threshold value is less than to the ratio being worth with the variance of the history pixel of the pixel, then by the current time pixel and
The Gauss model of background pixel point is matched, if the ratio is not less than preset matching threshold value, by current time pixel with
The Gauss model of foreground pixel point is matched;
Comparative result in S5, background change and S4 in video stream data, mixed Gauss model adaptive updates
Model parameter, the weights of X Gauss model are updated, draw matching degree highest background Gauss model parameter, complete complex background
Modeling;
S6, the foreground image matched the progress small echo direct transform processing by prospect Gauss model, if foreground image is coloured silk
Color image, then wavelet analysis processing is carried out to it respectively by R, G, B triple channel, obtain approximate diagram LL, the level of foreground image
Direction detail view HL, vertical direction detail view LH and diagonal detail view HH, vertical direction detail view is extracted, to Vertical Square
Fourier's direct transform is carried out to detail view, and the HFS for deleting its default frequency range completes high-frequency filtering;
Reduce to obtain new vertical direction detail view by Fourier inversion after S7, high-frequency filtering processing, then by small
Ripple inverse transformation reconstructs foreground image, if former foreground image is coloured image, then is merged by R, G, B triple channel after obtaining filtering
Foreground image.
S8, by Morphological scale-space, extract independent motion target area, lock onto target, start to perform tracking operation,
During target following, step S1-S7 is repeated.
Further, described small echo direct transform is lifting wavelet transform.
Further, described default frequency range adjusts according to sleet size adaptation.
The beneficial effects of the invention are as follows:The present invention is based on mixed Gauss model adaptive analysis algorithm is passed through, effectively filtering
The various motion artifacts of picture in complex environment, leaf shake etc. as caused by blowing, with reference to wavelet transformation and Fourier transformation
The precipitation noise and other noises in picture can be effectively filtered out, and by Morphological scale-space, extracts independent moving target area
Domain, lock onto target, start to perform tracking operation.
Brief description of the drawings
Fig. 1 is schematic flow sheet of the present invention.
Embodiment
Technical scheme is described in further detail below in conjunction with the accompanying drawings, but protection scope of the present invention is not limited to
It is as described below.
As shown in figure 1, This embodiment describes a kind of Intelligent target tracking based on complex environment, it includes following
Multiple steps.
S1, the video stream data for gathering current time, divide each frame video image in video stream data successively
Analysis, determines whether abnormal two field picture, if the progress Exception Type detection in the presence of if.
S2, start mixed Gauss model, each pixel of every frame video image in video stream data is established X high
This model.
S3, according to the weight of Gauss model the X Gauss model is ranked up, and accumulative summation is carried out to weight, if
The weight of top n Gauss model and more than predetermined threshold value, then be set to background pixel point by the top n Gauss model, establish background
Gauss model, rear X-N Gauss model is set to foreground pixel point, establishes prospect Gauss model.
S4, according to the average and variance of current time pixel and the history pixel of the pixel it is each pixel
Corresponding Gauss model is matched, the absolute value of the difference of current time pixel and the average of its history pixel is calculated, if this is exhausted
Preset matching threshold value is less than to the ratio being worth with the variance of the history pixel of the pixel, then by the current time pixel and
The Gauss model of background pixel point is matched, if the ratio is not less than preset matching threshold value, by current time pixel with
The Gauss model of foreground pixel point is matched.
Comparative result in S5, background change and S4 in video stream data, mixed Gauss model adaptive updates
Model parameter, the weights of X Gauss model are updated, draw matching degree highest background Gauss model parameter, complete complex background
Modeling, the various motion artifacts of picture in complex environment can be effectively filtered, the leaf as caused by blowing shakes etc..
Further, because in the video pictures of sleety weather, sleet normally behaves as nicking form, therefore, this hair
It is bright to be handled by combining wavelet transformation and Fourier transformation, the precipitation noise and other noises in picture can be effectively filtered out.
S6, the foreground image matched the progress small echo direct transform processing by prospect Gauss model, if foreground image is coloured silk
Color image, then wavelet analysis processing is carried out to it respectively by R, G, B triple channel, obtain approximate diagram LL, the level of foreground image
Direction detail view HL, vertical direction detail view LH and diagonal detail view HH, vertical direction detail view is extracted, to Vertical Square
Fourier's direct transform is carried out to detail view, and the HFS for deleting its default frequency range completes high-frequency filtering.
Reduce to obtain new vertical direction detail view by Fourier inversion after S7, high-frequency filtering processing, then by small
Ripple inverse transformation reconstructs foreground image, if former foreground image is coloured image, then is merged by R, G, B triple channel after obtaining filtering
Foreground image, remove complex environment in picture sleet fringes noise and other fringes noises.
S8, by Morphological scale-space, extract independent motion target area, lock onto target, start to perform tracking operation,
During target following, step S1-S7 is repeated, realizes the picture relaying after motion artifacts and precipitation noise is removed
Continuous tracking target.
In the present invention, described small echo direct transform can use lifting wavelet transform.
In the present invention, described default frequency range adjusts according to sleet size adaptation, in the case of filtering out the different forces of rain
Precipitation noise.
Describe a kind of Intelligent target based on complex environment according to the present invention in an illustrative manner above with reference to accompanying drawing
Tracking.It will be understood by those skilled in the art, however, that proposed for the invention described above a kind of based on complex environment
Intelligent target tracking, various improvement can also be made on the basis of present invention is not departed from, or to which part
Technical characteristic carries out equivalent substitution, within the spirit and principles of the invention, any modification, equivalent substitution and improvements made
Deng should be included in the scope of the protection.Therefore, protection scope of the present invention should be by appended claims
Content determine.
Claims (3)
1. a kind of Intelligent target tracking based on complex environment, it is characterised in that comprise the following steps:
S1, the video stream data for gathering current time, analyze each frame video image in video stream data, sentence successively
It is disconnected whether to have abnormal two field picture, if in the presence of to the progress Exception Type detection of abnormal two field picture;
S2, start mixed Gauss model, X Gaussian mode is established to each pixel of every frame video image in video stream data
Type;
S3, according to the weight of Gauss model the X Gauss model is ranked up, and accumulative summation is carried out to weight, if top n
The weight of Gauss model and more than predetermined threshold value, then be set to background pixel point by the top n Gauss model, establish background Gaussian mode
Type, rear X-N Gauss model is set to foreground pixel point, establishes prospect Gauss model;
S4, according to the average and variance of current time pixel and the history pixel of the pixel it is each pixel Point matching
Corresponding Gauss model, the absolute value of the difference of current time pixel and the average of its history pixel is calculated, if the absolute value
It is less than preset matching threshold value with the ratio of the variance of the history pixel of the pixel, then by the current time pixel and background
The Gauss model of pixel is matched, if the ratio is not less than preset matching threshold value, by current time pixel and prospect
The Gauss model of pixel is matched;
Comparative result in S5, background change and S4 in video stream data, utilizes mixed Gauss model adaptive updates
Model parameter, the weight of X Gauss model is updated, draw matching degree highest background Gauss model parameter, complete complex background
Modeling;
S6, the foreground image matched the progress small echo direct transform processing by prospect Gauss model, if foreground image is cromogram
Picture, then wavelet analysis processing is carried out to it respectively by R, G, B triple channel, obtain approximate diagram LL, the horizontal direction of foreground image
Detail view HL, vertical direction detail view LH and diagonal detail view HH, vertical direction detail view is extracted, it is thin to vertical direction
Section figure carries out Fourier's direct transform, and the HFS for deleting its default frequency range completes high-frequency filtering;
Reduce to obtain new vertical direction detail view by Fourier inversion after S7, high-frequency filtering processing, then it is anti-by small echo
Conversion reconstruct foreground image, if former foreground image is coloured image, then merged by R, G, B triple channel filtered after before
Scape image;
S8, by Morphological scale-space, extract independent motion target area, lock onto target, start to perform tracking operation, in mesh
During mark tracking, step S1-S7 is repeated.
A kind of 2. Intelligent target tracking based on complex environment according to claim 1, it is characterised in that:Described
Small echo direct transform is lifting wavelet transform.
A kind of 3. Intelligent target tracking based on complex environment according to claim 1, it is characterised in that:Described
Default frequency range adjusts according to sleet size adaptation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510805380.0A CN105469394B (en) | 2015-11-20 | 2015-11-20 | A kind of Intelligent target tracking based on complex environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510805380.0A CN105469394B (en) | 2015-11-20 | 2015-11-20 | A kind of Intelligent target tracking based on complex environment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105469394A CN105469394A (en) | 2016-04-06 |
CN105469394B true CN105469394B (en) | 2018-01-19 |
Family
ID=55607053
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510805380.0A Active CN105469394B (en) | 2015-11-20 | 2015-11-20 | A kind of Intelligent target tracking based on complex environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105469394B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106023175B (en) * | 2016-05-13 | 2018-11-23 | 哈尔滨工业大学(威海) | The method of catic water line thermal wake is differentiated based on three-dimensional pattern |
CN107462884A (en) * | 2017-07-25 | 2017-12-12 | 上海航征测控系统有限公司 | A kind of moving target detecting method and system based on frequency modulated continuous wave radar |
CN114594533A (en) * | 2022-05-10 | 2022-06-07 | 武汉大学 | Video rainfall monitoring method and device based on self-adaptive Gaussian mixture algorithm |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104933728A (en) * | 2015-07-13 | 2015-09-23 | 天津理工大学 | Mixed motion target detection method |
CN105023248A (en) * | 2015-06-25 | 2015-11-04 | 西安理工大学 | Low-SNR (signal to noise ratio) video motion target extraction method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6975753B2 (en) * | 2000-09-13 | 2005-12-13 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, program for implementing said method, and storage medium therefor |
-
2015
- 2015-11-20 CN CN201510805380.0A patent/CN105469394B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105023248A (en) * | 2015-06-25 | 2015-11-04 | 西安理工大学 | Low-SNR (signal to noise ratio) video motion target extraction method |
CN104933728A (en) * | 2015-07-13 | 2015-09-23 | 天津理工大学 | Mixed motion target detection method |
Non-Patent Citations (2)
Title |
---|
An Algorithm of the Target Detection and Tracking of the Video;Min Huang 等;《Paroo/c Perdoiac eEdniag iEnneegrininege》;20121231;第2567-2571页 * |
一种基于多特征融合的目标跟踪新方法;郑宇杰 等;《信息化研究》;20150630;第41卷(第3期);第14-17,62页 * |
Also Published As
Publication number | Publication date |
---|---|
CN105469394A (en) | 2016-04-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106296612B (en) | A kind of stagewise monitor video sharpening system and method for image quality evaluation and weather conditions guidance | |
CN107240084B (en) | Method and device for removing rain from single image | |
CN108564597B (en) | Video foreground object extraction method fusing Gaussian mixture model and H-S optical flow method | |
CN110148093B (en) | Image defogging improvement method based on dark channel prior | |
CN109635758B (en) | Intelligent building site video-based safety belt wearing detection method for aerial work personnel | |
CN104616290A (en) | Target detection algorithm in combination of statistical matrix model and adaptive threshold | |
CN105184743B (en) | A kind of image enchancing method based on non-linear Steerable filter | |
CN105469394B (en) | A kind of Intelligent target tracking based on complex environment | |
CN104200437A (en) | Image defogging method | |
CN105869174B (en) | A kind of Sky Scene image partition method | |
CN102663702A (en) | Natural image denoising method based on regional division | |
CN106446905A (en) | Surface crack texture extraction method based on fusion of seepage algorithm and adaptive Canny algorithm | |
CN108765327A (en) | A kind of image rain removing method based on the depth of field and sparse coding | |
CN103473547A (en) | Vehicle target recognizing algorithm used for intelligent traffic detecting system | |
CN107248148A (en) | Image denoising method and system | |
Xue et al. | Motion robust rain detection and removal from videos | |
CN111325688B (en) | Unmanned aerial vehicle image defogging method for optimizing atmosphere light by fusion morphology clustering | |
CN110276318A (en) | Nighttime road rains recognition methods, device, computer equipment and storage medium | |
CN107784639B (en) | Improved multilateral filtering denoising method for remote sensing image of unmanned aerial vehicle | |
CN109118440A (en) | Single image to the fog method based on transmissivity fusion with the estimation of adaptive atmosphere light | |
CN109255799A (en) | A kind of method for tracking target and system based on spatially adaptive correlation filter | |
CN105719254A (en) | Image denoising method and system | |
CN108009480A (en) | A kind of image human body behavioral value method of feature based identification | |
CN110111268B (en) | Single image rain removing method and device based on dark channel and fuzzy width learning | |
CN105023257B (en) | Image de-noising method based on N Smoothlets |
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 |