CN107103609B - Niblack power equipment Infrared Image Segmentation based on particle group optimizing - Google Patents
Niblack power equipment Infrared Image Segmentation based on particle group optimizing Download PDFInfo
- Publication number
- CN107103609B CN107103609B CN201710249006.6A CN201710249006A CN107103609B CN 107103609 B CN107103609 B CN 107103609B CN 201710249006 A CN201710249006 A CN 201710249006A CN 107103609 B CN107103609 B CN 107103609B
- Authority
- CN
- China
- Prior art keywords
- infrared image
- threshold value
- neighborhood
- particle
- rectangular
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T2207/10048—Infrared image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Transforming Light Signals Into Electric Signals (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of Niblack power equipment Infrared Image Segmentation based on particle group optimizing, the following steps are included: 1) obtain infrared image, the infrared image is divided into q nonoverlapping Continuous Rectangular neighborhoods, calculates the gray average and grey scale variance of each rectangular neighborhood；2) it is directed to each rectangular neighborhood, a threshold value optimizing section for corresponding to the rectangular neighborhood is obtained according to setting step-length, form q dimension population solution space, and using inter-class variance as particle swarm algorithm fitness function, automatic searching corresponds to the optimum segmentation threshold value T of each rectangular neighborhood in q dimension population solution space*, the optimum segmentation threshold value T*So that inter-class variance is maximum；3) optimum segmentation threshold value of each rectangular neighborhood obtained according to step 2) carries out binary conversion treatment to each rectangular neighborhood.Compared with prior art, the present invention solves the problems, such as to cause infrared image over-segmentation using traditional global threshold dividing method.
Description
Technical field
The present invention relates to a kind of image processing methods, more particularly, to a kind of Niblack electric power based on particle group optimizing
Equipment Infrared Image Segmentation.
Background technique
In recent years, Transformer Substation Online Monitoring System is widely applied, and thermal infrared imager, visible light camera shooting are set
Standby visible light and infrared image send back to master control room and carry out manual analysis, although this method reduces the labour of artificial acquisition data
Amount, but be the failure to get rid of the dependence to Artificial Diagnosis.With the continuous development of artificial intelligence and image processing techniques, intelligent diagnostics
Technology starts to be applied to Fault Diagnosis for Electrical Equipment.Intelligent diagnosing method is broadly divided into three steps, looks for from infrared image first
Device target region out, i.e. area-of-interest (ROI), then extract relevant information from region, finally to the letter extracted
Breath classification is to complete Fault Diagnosis for Electrical Equipment.Can wherein a step of most critical be the acquisition of ROI, accurately obtain ROI
Determine to a certain extent power equipment temperature field information extract it is accurate whether.Generally obtained using threshold segmentation method
ROI, this method have many advantages, such as that easy to operate, arithmetic speed is fast.Domestic and foreign scholars have done numerous studies to it, as Otsu is proposed
One-dimensional maximum variance between clusters, the minimal error threshold values based on Bayes minimal error sorting criterion of the propositions such as Kittler
Method, the Threshold segmentation innovatory algorithm based on maximum entropy that Kapur etc. is provided, Kennedy and Eberhart propose jointly based on
Particle swarm optimization algorithm of group collaboration, and the Optimal improvements image segmentation algorithm based on particle swarm algorithm, etc..Above-mentioned calculation
Method is mostly based on global threshold, and infrared image big for noise, that contrast is low, uniformity is poor is difficult to target device well
It is distinguished with background.
Summary of the invention
It is excellent based on population that it is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide one kind
The Niblack power equipment Infrared Image Segmentation of change.
The purpose of the present invention can be achieved through the following technical solutions:
A kind of Niblack power equipment Infrared Image Segmentation based on particle group optimizing, comprising the following steps:
1) infrared image is obtained, the infrared image is divided into q nonoverlapping Continuous Rectangular neighborhoods, calculates each square
The gray average and grey scale variance of shape neighborhood；
2) it is directed to each rectangular neighborhood, obtains a threshold value optimizing section for corresponding to the rectangular neighborhood according to setting step-length
{T1,T2,...,Ti,...,Tn, it forms a q and ties up population solution space, and using inter-class variance as particle swarm algorithm fitness letter
Number, automatic searching corresponds to the optimum segmentation threshold value T of each rectangular neighborhood in q dimension population solution space*, described optimal
Segmentation threshold T*So that inter-class variance is maximum, wherein Ti=m+kiS, i=1,2 ..., n, m are that the gray scale of current rectangle neighborhood is equal
Value, s are the grey scale variance of current rectangle neighborhood, kiFor according to equidistant i-th of the value in set interval of setting step-length,
N is value number；
3) optimum segmentation threshold value of each rectangular neighborhood obtained according to step 2) carries out binary conversion treatment to each rectangular neighborhood.
In the step 1), before the infrared image is divided into several nonoverlapping rectangular neighborhoods, infrared image is carried out
Continuation processing.
In the step 2), step-length is set as 0.05, set interval is [- 1,1].
In the step 2), the pixel grey scale of rectangular neighborhood is divided into D1=[0 ..., T], D2=[T+1 ..., L-1] two
Class, by inter-class variance formula is defined as:
Wherein, σ2It (T) is inter-class variance,Respectively indicate D1Picture in class
The probability and D that plain gray scale occurs1The gray average of class, pjIndicate that pixel grey scale is the probability of the pixel of j；
Threshold value in the threshold value optimizing section of each rectangular neighborhood is successively substituted into the inter-class variance formula, passes through population
Algorithm search obtains the optimum segmentation threshold value of each rectangular neighborhood.
In the step 2), during searching optimum segmentation threshold value using particle swarm algorithm,
Particle i is { T in the position mark of q dimension population solution spacei,1,Ti,2,…,Ti,q, each particle according to
Lower formula updates the position and speed of oneself, and particle is with speed Vi(t+1) from current location Ti(t) it is moved to the next position Ti(t+
1):
Vi(t+1)=ω × Vi(t)+c1×r1[Pbesti-Ti(t)]+c2×r2[Gbesti-Ti(t)]
Ti(t+1)=Ti(t)+Vi(t+1)
Wherein, ViAnd TiSpeed and position of i-th of particle in solution space are respectively indicated, it is optimal that t indicates that population is searched
Current iteration number in threshold process, c1、c2For aceleration pulse, r1、r2For the random number between [0,1], ω indicates particle
Inertia weight, PbestiFor current optimal value, GbestiFor global optimum.
The inertia weight ω passes through following formula adaptive change:
Wherein, ωmax、ωminThe maximum value and minimum value of inertia weight are respectively indicated, G indicates maximum number of iterations.
Compared with prior art, the invention has the following advantages that
1) present invention uses fitness function of the inter-class variance as particle swarm algorithm, schemes in automatic searching Niblack method
As the optimum segmentation threshold value of not overlapping rectangles neighborhood, and it is used for the binarization segmentation of current neighborhood, solved using tradition
Global threshold dividing method causes infrared image over-segmentation problem；
2) present invention is split threshold value optimizing based on pixel grey scale, greatly reduces non-homogeneous background to each equipment
The influence of infrared thermal imaging figure segmentation effect, the integrality for improving target area.
Detailed description of the invention
Fig. 1 is flow diagram of the invention；
Fig. 2 is the schematic diagram of five infrared original images of power equipment；
Fig. 3 is segmentation result schematic diagram corresponding with Fig. 2.
Specific embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention
Premised on implemented, the detailed implementation method and specific operation process are given, but protection scope of the present invention is not limited to
Following embodiments.
As shown in Figure 1, the present embodiment provides a kind of Niblack power equipment infrared Image Segmentation based on particle group optimizing
Method, comprising the following steps:
1) infrared image is obtained, the infrared image is divided into q nonoverlapping Continuous Rectangular neighborhoods, calculates each square
The gray average and grey scale variance of shape neighborhood.
In the present embodiment, importing resolution ratio is the infrared original image g (x, y) of 320 × 240 power equipments, as shown in Fig. 2, as neighbour
Domain pixel takes 90 × 80, Neighborhood Number measure be 4 column, 3 row totally 12 pieces not overlapping rectangles neighborhood when (to infrared original image horizontal boundary
Each 20 pixel symmetric extensions around being done, so that original image becomes neighborhood horizontal pixel integral multiple) segmentation effect is preferable.
2) it is directed to each rectangular neighborhood, obtains a threshold value optimizing section for corresponding to the rectangular neighborhood according to setting step-length
{T1,T2,...,Ti,...,Tn, it forms a q and ties up population solution space, and using inter-class variance as particle swarm algorithm fitness letter
Number, automatic searching corresponds to the optimum segmentation threshold value T of each rectangular neighborhood in q dimension population solution space*, described optimal
Segmentation threshold T*So that inter-class variance is maximum, wherein Ti=m+kiS, i=1,2 ..., n, m are that the gray scale of current rectangle neighborhood is equal
Value, s are the grey scale variance of current rectangle neighborhood, kiFor according to equidistant i-th of the value in set interval of setting step-length,
N is value number.
In the present embodiment, set interval is [- 1,1], set step-length as 0.05, then available 41 k values, can be calculated with this
Each rectangular neighborhood all has one 41 dimension threshold value optimizing section { T out1,T2,...,Ti,...,T41}.Therefore, population is at 12 pieces
Threshold value optimizing section on rectangular partition neighborhood, i.e. population 12 are tieed up solution space and are indicated are as follows:
Select maximum kind of the inter-class variance formula (2) as population fitness function by PSO method 12 neighborhoods of search
Between varianceAnd its corresponding optimum segmentation threshold value
The pixel grey scale of rectangular neighborhood is divided into D1=[0 ..., T], D2Two class of=[T+1 ..., L-1], by inter-class variance public affairs
Formula is defined as:
Wherein, σ2It (T) is inter-class variance,Respectively indicate D1Picture in class
The probability and D that plain gray scale occurs1The gray average of class, pjIndicate that pixel grey scale is the probability of the pixel of j；
Threshold value in the threshold value optimizing section of each rectangular neighborhood is successively substituted into the inter-class variance formula, passes through population
Algorithm search obtains the optimum segmentation threshold value of each rectangular neighborhood.
In particle swarm algorithm, for 41 this small dimension threshold value optimizing sections of dimension, group's population is set as 10.Particle i exists
The position mark of solution space is { Ti,1,Ti,2,…,Ti,12}.Each particle updates position and the speed of oneself according to formula (3), (4)
Degree, particle is with speed Vi(t+1) from current location Ti(t) it is moved to the next position Ti(t+1)。
Vi(t+1)=ω × Vi(t)+c1×r1[Pbesti-Ti(t)]+c2×r2[Gbesti-Ti(t)] (3)
Ti(t+1)=Ti(t)+Vi(t+1) (4)
Wherein, ViAnd TiSpeed and position of i-th of particle in solution space are respectively indicated, it is optimal that t indicates that population is searched
Current iteration number in threshold process, c1、c2For aceleration pulse, in the present embodiment, c1=c2=2, r1、r2Between [0,1]
Random number, ω indicate particle inertia weight,ωmax、ωminRespectively indicate inertia weight
Maximum value and minimum value, in the present embodiment, ωmax=0.95, ωmin=0.4, G indicate maximum number of iterations, the present embodiment
In, G=25, PbestiFor current optimal value, GbestiFor global optimum.
It is denoted as by the optimum segmentation threshold value that above-mentioned particle swarm algorithm obtains each neighborhood:
3) optimum segmentation threshold value of each rectangular neighborhood obtained according to step 2) carries out binary conversion treatment to each rectangular neighborhood,
As a result as shown in Figure 3.
The preferred embodiment of the present invention has been described in detail above.It should be appreciated that those skilled in the art without
It needs creative work according to the present invention can conceive and makes many modifications and variations.Therefore, all technologies in the art
Personnel are available by logical analysis, reasoning, or a limited experiment on the basis of existing technology under this invention's idea
Technical solution, all should be within the scope of protection determined by the claims.
Claims (6)
1. a kind of Niblack power equipment Infrared Image Segmentation based on particle group optimizing, which is characterized in that including following
Step:
1) infrared image is obtained, the infrared image is divided into q nonoverlapping Continuous Rectangular neighborhoods, it is adjacent to calculate each rectangle
The gray average and grey scale variance in domain；
2) it is directed to each rectangular neighborhood, obtains a threshold value optimizing section { T for corresponding to the rectangular neighborhood according to setting step-length1,
T2,...,Ti,...,Tn, it forms a q and ties up population solution space, and using inter-class variance as particle swarm algorithm fitness function,
Automatic searching corresponds to the optimum segmentation threshold value T of each rectangular neighborhood in q dimension population solution space*, the most optimal sorting
Cut threshold value T*So that inter-class variance is maximum, wherein Ti=m+kiS, i=1,2 ..., n, m are that the gray scale of current rectangle neighborhood is equal
Value, s are the grey scale variance of current rectangle neighborhood, kiFor according to equidistant i-th of the value in set interval of setting step-length,
N is value number；
3) optimum segmentation threshold value of each rectangular neighborhood obtained according to step 2) carries out binary conversion treatment to each rectangular neighborhood.
2. the Niblack power equipment Infrared Image Segmentation according to claim 1 based on particle group optimizing, special
Sign is, in the step 1), before the infrared image is divided into several nonoverlapping rectangular neighborhoods, prolongs to infrared image
Open up processing.
3. the Niblack power equipment Infrared Image Segmentation according to claim 1 based on particle group optimizing, special
Sign is, in the step 2), sets step-length as 0.05, set interval is [- 1,1].
4. the Niblack power equipment Infrared Image Segmentation according to claim 1 based on particle group optimizing, special
Sign is, in the step 2), the pixel grey scale of rectangular neighborhood is divided into D1=[0 ..., T], D2Two class of=[T+1 ..., L-1],
By inter-class variance formula is defined as:
Wherein, σ2It (T) is inter-class variance,Respectively indicate D1Pixel ash in class
Spend the probability and D occurred1The gray average of class, pjIndicate that pixel grey scale is the probability of the pixel of j；
Threshold value in the threshold value optimizing section of each rectangular neighborhood is successively substituted into the inter-class variance formula, passes through particle swarm algorithm
Search the optimum segmentation threshold value for obtaining each rectangular neighborhood.
5. the Niblack power equipment Infrared Image Segmentation according to claim 1 based on particle group optimizing, special
Sign is, in the step 2), during searching optimum segmentation threshold value using particle swarm algorithm,
Particle i is { T in the position mark of q dimension population solution spacei,1,Ti,2,…,Ti,q, each particle is according to following public affairs
Formula updates the position and speed of oneself, and particle is with speed Vi(t+1) from current location Ti(t) it is moved to the next position Ti(t+1):
Vi(t+1)=ω × Vi(t)+c1×r1[Pbesti-Ti(t)]+c2×r2[Gbesti-Ti(t)]
Ti(t+1)=Ti(t)+Vi(t+1)
Wherein, ViAnd TiSpeed and position of i-th of particle in solution space are respectively indicated, t indicates that population searches optimal threshold
Current iteration number in the process, c1、c2For aceleration pulse, r1、r2For the random number between [0,1], ω indicates the inertia of particle
Weight, PbestiFor current optimal value, GbestiFor global optimum.
6. the Niblack power equipment Infrared Image Segmentation according to claim 5 based on particle group optimizing, special
Sign is that the inertia weight ω passes through following formula adaptive change:
Wherein, ωmax、ωminThe maximum value and minimum value of inertia weight are respectively indicated, G indicates maximum number of iterations.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710249006.6A CN107103609B (en) | 2017-04-17 | 2017-04-17 | Niblack power equipment Infrared Image Segmentation based on particle group optimizing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710249006.6A CN107103609B (en) | 2017-04-17 | 2017-04-17 | Niblack power equipment Infrared Image Segmentation based on particle group optimizing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107103609A CN107103609A (en) | 2017-08-29 |
| CN107103609B true CN107103609B (en) | 2019-06-11 |
Family
ID=59675836
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710249006.6A Active CN107103609B (en) | 2017-04-17 | 2017-04-17 | Niblack power equipment Infrared Image Segmentation based on particle group optimizing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107103609B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111161300B (en) * | 2019-12-05 | 2023-03-21 | 西安工程大学 | Niblack image segmentation method based on improved Otsu method |
| CN111583272B (en) * | 2020-04-17 | 2023-03-03 | 西安工程大学 | Improved Niblack infrared image segmentation method combining maximum entropy |
| CN111489317B (en) * | 2020-05-12 | 2021-09-14 | 江西天境精藏科技有限公司 | Intelligent cinerary casket storage system |
| CN111561771A (en) * | 2020-06-16 | 2020-08-21 | 重庆大学 | Intelligent air conditioner temperature adjusting method |
| CN111899250B (en) * | 2020-08-06 | 2021-04-02 | 朗森特科技有限公司 | Remote disease intelligent diagnosis system based on block chain and medical image |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496156A (en) * | 2011-11-17 | 2012-06-13 | 西安电子科技大学 | Medical image segmentation method based on quantum-behaved particle swarm cooperative optimization |
| CN103914831A (en) * | 2014-03-10 | 2014-07-09 | 西安电子科技大学 | Two-dimensional dual-threshold SAR image segmentation method based on quantum particle swarm optimization |
-
2017
- 2017-04-17 CN CN201710249006.6A patent/CN107103609B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496156A (en) * | 2011-11-17 | 2012-06-13 | 西安电子科技大学 | Medical image segmentation method based on quantum-behaved particle swarm cooperative optimization |
| CN103914831A (en) * | 2014-03-10 | 2014-07-09 | 西安电子科技大学 | Two-dimensional dual-threshold SAR image segmentation method based on quantum particle swarm optimization |
Non-Patent Citations (3)
| Title |
|---|
| An Image Enhancement Method Using the Quantum-Behaved Particle Swarm Optimization with an Adaptive Strategy;Xiaoping Su et al.;《Mathematical Problems in Engineerin》;20131231;第1-15页 |
| 基于PSO和LM的信号稀疏分解快速算法;王菊 等;《激光与红外》;20121231;第42卷(第2期);第76-79页 |
| 手背静脉图像分割及细化算法研究;蔡超峰 等;《图形图像》;20140630;第227-230页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107103609A (en) | 2017-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107103609B (en) | Niblack power equipment Infrared Image Segmentation based on particle group optimizing | |
| Zhang et al. | Deep convolutional neural networks for forest fire detection | |
| Cong et al. | Does thermal really always matter for RGB-T salient object detection? | |
| Song et al. | MSFYOLO: Feature fusion-based detection for small objects | |
| Lu et al. | Cga-net: Category guided aggregation for point cloud semantic segmentation | |
| CN104992452B (en) | Airbound target automatic tracking method based on thermal imaging video | |
| Ren et al. | A novel squeeze YOLO-based real-time people counting approach | |
| CN109360232A (en) | The indoor scene layout estimation method and device of confrontation network are generated based on condition | |
| Huang et al. | Motion detection with pyramid structure of background model for intelligent surveillance systems | |
| Huang et al. | Domain adaptive attention learning for unsupervised person re-identification | |
| Dai et al. | Oamatcher: An overlapping areas-based network for accurate local feature matching | |
| Wang et al. | The obtainment and recognition of raw silk defects based on machine vision and image analysis | |
| Mu et al. | Salient object detection in low contrast images via global convolution and boundary refinement | |
| Cheng et al. | Water quality monitoring method based on TLD 3D fish tracking and XGBoost | |
| Zhai et al. | Scale-context perceptive network for crowd counting and localization in smart city system | |
| Zhang | [Retracted] Sports Action Recognition Based on Particle Swarm Optimization Neural Networks | |
| Phan et al. | A Novel Approach for PV Cell Fault Detection using YOLOv8 and Particle Swarm Optimization | |
| CN108241837B (en) | Method and device for detecting remnants | |
| Hu et al. | A detecting algorithm for occlusion on the surface of photovoltaic modules based on improved YOLOv5 | |
| Du et al. | Infrared small target detection and tracking method suitable for different scenes | |
| Dong et al. | CCTwins: A Weakly-Supervised Transformer-based Crowd Counting Method with Adaptive Scene Consistency Attention | |
| Zhang et al. | Video anomaly detection using open data filter and domain adaptation | |
| Nishimura et al. | Weakly supervised cell-instance segmentation with two types of weak labels by single instance pasting | |
| Zhao et al. | SSN: Shift Suppression Network for Endogenous Shift of Photovoltaic Defect Detection | |
| Otamendi et al. | A scalable framework for annotating photovoltaic cell defects in electroluminescence images |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |