CN106384351A - Infrared image background recognition method based on infrared image histogram - Google Patents
Infrared image background recognition method based on infrared image histogram Download PDFInfo
- Publication number
- CN106384351A CN106384351A CN201610721274.9A CN201610721274A CN106384351A CN 106384351 A CN106384351 A CN 106384351A CN 201610721274 A CN201610721274 A CN 201610721274A CN 106384351 A CN106384351 A CN 106384351A
- Authority
- CN
- China
- Prior art keywords
- infrared image
- infrared
- image
- histogram
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
-
- 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
-
- 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
- G06T2207/20032—Median filtering
Abstract
The invention discloses an infrared image background recognition method based on an infrared image histogram. The infrared image background recognition method comprises the steps of performing histogram statistics on an infrared image to acquire a grayscale histogram of the infrared image; classifying the grayscale histogram of the infrared image into a known infrared histogram image model; performing matching calculation according to the infrared histogram image model so as to work out a background area of the infrared image. The infrared image background recognition method can effectively recognize the effective background in the infrared image according to the particularity of the infrared image, and achieves a purpose of eliminating background noises through suppressing the recognized background, thereby having an effect of removing background noises in the infrared image.
Description
Technical field
The present invention relates to infrared image processing technology field, more particularly to a kind of histogrammic infrared based on infrared image
Image background recognition methods.
Background technology
Because non-refrigeration infrared image sensor is less in current application, and to infrared image background recognition detection technology
Research does not almost have.But the particularity due to infrared image, infrared image detection device is generally used for object observing and environment
There is the scene of certain temperature difference, therefore to environment(Background)Identification critically important, after recognizing the background of video, be conducive to carrying out figure
The target identification of picture judges, can be by the target of image and background separation, such that it is able to targetedly carry out to graphic object
Strengthen, suppress image background, to reduce the impact to image for the ambient noise.Existing technology great majority are just for still image
Process, and be not suitable for many scene process of Infrared video processing, because the diversity of infrared video scene is so that Background Recognition
Algorithm must assure that and can be applied to all occasions, and therefore, the versatility of algorithm is particularly important.
Content of the invention
It is an object of the invention to overcoming the deficiencies in the prior art, one kind is provided to be based on the histogrammic infrared figure of infrared image
As Background Recognition method, can reliably identify the effective background in infrared image.
The purpose of the present invention is achieved through the following technical solutions:Based on the infrared image histogrammic infrared image back of the body
Scape recognition methods, including:The grey level histogram that statistics with histogram obtains infrared image is carried out to infrared image;By described infrared figure
The grey level histogram of picture be categorized as known to infrared histogram image model;Entered according to described infrared histogram image model
Row matching primitives, match the background area of described infrared image.
Described infrared video Background Recognition method also includes the step that the grey level histogram of described infrared image is filtered
Suddenly.
Described it is filtered into LPF.
The acquisition methods of the grey level histogram of described infrared image are:Open and take a memory headroom, made with each pixel value
For the address of data preservation, input infrared picture data, when input pixel reaches every time, the value of this address is read out and adds
One, then again the value after changing is saved in described address.
By the grey level histogram of described infrared image be categorized as known to infrared histogram image model method bag
Include:By multilevel iudge infrared histogram image aspect of model known to each to input infrared image corresponding spy
Levy, the histogram model of the infrared image inputting the most at last is categorized in known infrared histogram image model.
Described known infrared histogram image model includes but is not limited to unimodal model, bimodal model, multimodal model and U
Shape model.
Matching primitives are carried out according to described infrared histogram image model, matches the background area of described infrared image
Method includes:Calculate all maximum of described infrared histogram image model;Calculate described all maximum positive and negative pre- at it
If the quantity sum of the grey level histogram of the infrared image in scope;When described quantity sum is in infrared histogram image model
Infrared image grey level histogram sum ratio be more than threshold value when, this region be infrared image background area;Obtain red
The bound threshold value of the background area of outer image, thus obtain the background area of infrared image.
Described threshold value is 50%.
The invention has the beneficial effects as follows:Method in the present invention, according to the particularity of infrared image, can efficiently identify
Effective background in infrared image, and by suppressing recognized background, and reach the purpose eliminating ambient noise, thus
Possesses the effect removing the ambient noise in infrared image;Additionally, the method in the present invention is based on infrared histogrammic process
Mode, if be applied in the hardware processor of infrared image processing such that it is able to reach the effect of real time processed images.
Brief description
Fig. 1 is the schematic flow sheet of one embodiment of the present of invention.
Specific embodiment
Below in conjunction with the accompanying drawings technical scheme is described in further detail, but protection scope of the present invention is not limited to
Described below.
As shown in figure 1, being based on infrared image histogrammic infrared image background recognition methods, including:
Step one, the grey level histogram that statistics with histogram obtains infrared image is carried out to infrared image.Will original infrared image
According to original scale, the invalid half-tone information in image histogram is removed, the final grey level histogram to infrared image.
The acquisition methods of the grey level histogram of described infrared image are:Open and take a memory headroom, made with each pixel value
For the address of data preservation, input infrared picture data, when input pixel reaches every time, the value of this address is read out and adds
One, then again the value after changing is saved in described address.
Step 2, the grey level histogram to described infrared image carry out Neighborhood Filtering(Mean filter or medium filtering), lead to
Cross and be filtered, the accuracy of detection can be improved.
Described it is filtered into LPF.
Step 3, by the grey level histogram of described infrared image be categorized as known to infrared histogram image model.
By the grey level histogram of described infrared image be categorized as known to infrared histogram image model method bag
Include:By multilevel iudge infrared histogram image aspect of model known to each to input infrared image corresponding spy
Levy, the histogram model of the infrared image inputting the most at last is categorized in known infrared histogram image model.
Described known infrared histogram image model includes but is not limited to unimodal model, bimodal model, multimodal model and U
Shape model.
Step 4, matching primitives are carried out according to described infrared histogram image model, match the back of the body of described infrared image
Scene area.
Matching primitives are carried out according to described infrared histogram image model, matches the background area of described infrared image
Method includes:Calculate all maximum of described infrared histogram image model;Calculate described all maximum positive and negative pre- at it
If the quantity sum of the grey level histogram of the infrared image in scope;When described quantity sum is in infrared histogram image model
Infrared image grey level histogram sum ratio be more than 50% when, this region be infrared image background area;Obtain infrared
The bound threshold value of the background area of image, thus obtain the background area of infrared image.
Although the background model species of infrared image is more, the background model of all Infrared video image all has phase
Same characteristic value, that is, according to normal distribution to the middle feature assembled, the present embodiment is used as judgement ginseng by selected threshold to background
Examine, before implementing algorithm, by being modeled to background, thus improving accuracy during Background matching.
The above be only the preferred embodiment of the present invention it should be understood that the present invention be not limited to described herein
Form, is not to be taken as the exclusion to other embodiment, and can be used for various other combinations, modification and environment, and can be at this
In the described contemplated scope of literary composition, it is modified by the technology or knowledge of above-mentioned teaching or association area.And those skilled in the art are entered
The change of row and change, then all should be in the protection domains of claims of the present invention without departing from the spirit and scope of the present invention
Interior.
Claims (8)
1. it is based on infrared image histogrammic infrared image background recognition methods it is characterised in that including:
The grey level histogram that statistics with histogram obtains infrared image is carried out to infrared image;
By the grey level histogram of described infrared image be categorized as known to infrared histogram image model;
Matching primitives are carried out according to described infrared histogram image model, matches the background area of described infrared image.
2. according to claim 1 based on infrared image histogrammic infrared image background recognition methods it is characterised in that:
Described infrared video Background Recognition method also includes the step that the grey level histogram of described infrared image is filtered.
3. according to claim 2 based on infrared image histogrammic infrared image background recognition methods it is characterised in that:
Described it is filtered into LPF.
4. according to claim 1 based on infrared image histogrammic infrared image background recognition methods it is characterised in that:
The acquisition methods of the grey level histogram of described infrared image are:
Open and take a memory headroom, the address being preserved as data using each pixel value, input infrared picture data, input every time
When pixel reaches, the value of this address is read out and Jia one, then again the value after changing is saved in described address.
5. according to claim 1 based on infrared image histogrammic infrared image background recognition methods it is characterised in that:
By the grey level histogram of described infrared image be categorized as known to the method for infrared histogram image model include:By than
Relatively judge the infrared histogram image aspect of model known to each and the infrared image of input individual features, the most defeated
The histogram model of the infrared image entering is categorized in known infrared histogram image model.
6. according to claim 1 based on infrared image histogrammic infrared image background recognition methods it is characterised in that:
Described known infrared histogram image model includes but is not limited to unimodal model, bimodal model, multimodal model and U-shaped model.
7. according to claim 1 based on infrared image histogrammic infrared image background recognition methods it is characterised in that:
Matching primitives are carried out according to described infrared histogram image model, matches the method bag of the background area of described infrared image
Include:
Calculate all maximum of described infrared histogram image model;
Calculate the quantity sum of the grey level histogram of infrared image in its positive and negative preset range for the described all maximum;
When the ratio of the grey level histogram sum of infrared image in infrared histogram image model for the described quantity sum is more than
During threshold value, this region is the background area of infrared image;
Obtain the bound threshold value of the background area of infrared image, thus obtaining the background area of infrared image.
8. according to claim 7 based on infrared image histogrammic infrared image background recognition methods it is characterised in that:
Described threshold value is 50%.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610721274.9A CN106384351A (en) | 2016-08-25 | 2016-08-25 | Infrared image background recognition method based on infrared image histogram |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610721274.9A CN106384351A (en) | 2016-08-25 | 2016-08-25 | Infrared image background recognition method based on infrared image histogram |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106384351A true CN106384351A (en) | 2017-02-08 |
Family
ID=57916959
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610721274.9A Pending CN106384351A (en) | 2016-08-25 | 2016-08-25 | Infrared image background recognition method based on infrared image histogram |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106384351A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108062508A (en) * | 2017-10-13 | 2018-05-22 | 西安科技大学 | The extracting method of equipment in substation's complex background infrared image |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1400806A (en) * | 2001-07-31 | 2003-03-05 | 佳能株式会社 | Adaptive two-valued image processing method and equipment |
CN101105862A (en) * | 2007-08-02 | 2008-01-16 | 宁波大学 | Medical image window parameter self-adaptive regulation method |
CN101359373A (en) * | 2007-08-03 | 2009-02-04 | 富士通株式会社 | Method and device for recognizing degraded character |
JP2010237874A (en) * | 2009-03-30 | 2010-10-21 | Honda Motor Co Ltd | Vehicle surroundings monitoring device |
CN102693531A (en) * | 2012-01-11 | 2012-09-26 | 河南科技大学 | Adaptive double-platform based infrared image enhancement method |
CN102737238A (en) * | 2011-04-01 | 2012-10-17 | 洛阳磊石软件科技有限公司 | Gesture motion-based character recognition system and character recognition method, and application thereof |
CN103530847A (en) * | 2013-09-24 | 2014-01-22 | 电子科技大学 | Infrared image enhancing method |
CN104952060A (en) * | 2015-03-19 | 2015-09-30 | 杭州电子科技大学 | Adaptive segmentation extraction method for infrared pedestrian region of interests |
CN105354842A (en) * | 2015-10-22 | 2016-02-24 | 武汉康美华医疗投资管理有限公司 | Contour key point registration and identification method based on stable area |
US20160225126A1 (en) * | 2008-09-26 | 2016-08-04 | Google Inc. | Method for image processing using local statistics convolution |
-
2016
- 2016-08-25 CN CN201610721274.9A patent/CN106384351A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1400806A (en) * | 2001-07-31 | 2003-03-05 | 佳能株式会社 | Adaptive two-valued image processing method and equipment |
CN101105862A (en) * | 2007-08-02 | 2008-01-16 | 宁波大学 | Medical image window parameter self-adaptive regulation method |
CN101359373A (en) * | 2007-08-03 | 2009-02-04 | 富士通株式会社 | Method and device for recognizing degraded character |
US20160225126A1 (en) * | 2008-09-26 | 2016-08-04 | Google Inc. | Method for image processing using local statistics convolution |
JP2010237874A (en) * | 2009-03-30 | 2010-10-21 | Honda Motor Co Ltd | Vehicle surroundings monitoring device |
CN102737238A (en) * | 2011-04-01 | 2012-10-17 | 洛阳磊石软件科技有限公司 | Gesture motion-based character recognition system and character recognition method, and application thereof |
CN102693531A (en) * | 2012-01-11 | 2012-09-26 | 河南科技大学 | Adaptive double-platform based infrared image enhancement method |
CN103530847A (en) * | 2013-09-24 | 2014-01-22 | 电子科技大学 | Infrared image enhancing method |
CN104952060A (en) * | 2015-03-19 | 2015-09-30 | 杭州电子科技大学 | Adaptive segmentation extraction method for infrared pedestrian region of interests |
CN105354842A (en) * | 2015-10-22 | 2016-02-24 | 武汉康美华医疗投资管理有限公司 | Contour key point registration and identification method based on stable area |
Non-Patent Citations (3)
Title |
---|
孙淑琪 主编: "《高等学校教材 接口与通信》", 31 October 1998 * |
孙长燕 等: "基于直方图极大值准则可变参数图像阈值分割方法", 《现代电子技术》 * |
李俊山 等编著: "《数字图像处理》", 30 November 2013 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108062508A (en) * | 2017-10-13 | 2018-05-22 | 西安科技大学 | The extracting method of equipment in substation's complex background infrared image |
CN108062508B (en) * | 2017-10-13 | 2019-06-04 | 西安科技大学 | The extracting method of equipment in substation's complex background infrared image |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108230252B (en) | Image processing method and device and electronic equipment | |
WO2019237567A1 (en) | Convolutional neural network based tumble detection method | |
Hao et al. | Improved self-adaptive edge detection method based on Canny | |
CN111340716B (en) | Image deblurring method for improving double-discrimination countermeasure network model | |
CN106023204A (en) | Method and system for removing mosquito noise based on edge detection algorithm | |
CN112784712B (en) | Missing child early warning implementation method and device based on real-time monitoring | |
CN104268595B (en) | general object detection method and system | |
CN107256543A (en) | Image processing method, device, electronic equipment and storage medium | |
CN112150371A (en) | Image noise reduction method, device, equipment and storage medium | |
CN105719254B (en) | Image noise reduction method and system | |
CN111612741A (en) | Accurate non-reference image quality evaluation method based on distortion recognition | |
Radzi et al. | Extraction of moving objects using frame differencing, ghost and shadow removal | |
CN108122209B (en) | License plate deblurring method based on countermeasure generation network | |
CN106384351A (en) | Infrared image background recognition method based on infrared image histogram | |
CN112634288A (en) | Equipment area image segmentation method and device | |
Yu et al. | Skin detection for adult image identification | |
CN108288041B (en) | Preprocessing method for removing false detection of pedestrian target | |
Jeong et al. | Fast fog detection for de-fogging of road driving images | |
CN110728692A (en) | Image edge detection method based on Scharr operator improvement | |
CN111163332A (en) | Video pornography detection method, terminal and medium | |
CN111275642A (en) | Low-illumination image enhancement method based on significant foreground content | |
CN116205802A (en) | Image denoising method and device, storage medium and electronic equipment | |
CN115908802A (en) | Camera shielding detection method and device, electronic equipment and readable storage medium | |
JP2013156676A (en) | Image processing device, method, and program | |
CN113128505A (en) | Method, device, equipment and storage medium for detecting local visual confrontation sample |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170208 |
|
RJ01 | Rejection of invention patent application after publication |