CN102129700A - Infrared simulated image platform under ocean background and image generation method thereof - Google Patents
Infrared simulated image platform under ocean background and image generation method thereof Download PDFInfo
- Publication number
- CN102129700A CN102129700A CN 201110057771 CN201110057771A CN102129700A CN 102129700 A CN102129700 A CN 102129700A CN 201110057771 CN201110057771 CN 201110057771 CN 201110057771 A CN201110057771 A CN 201110057771A CN 102129700 A CN102129700 A CN 102129700A
- Authority
- CN
- China
- Prior art keywords
- image
- infrared
- background
- marine
- face
- 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
Images
Abstract
The invention aims at providing an infrared simulated image platform under an ocean background and an image generation method thereof. The infrared simulated image platform comprises an infrared face statistic template generation subsystem, an ocean background infrared image selection subsystem and an infrared simulated image generation subsystem, wherein the infrared face statistic template generation subsystem is used for generating face templates at different distances; the ocean background infrared image selection subsystem takes the charge of managing databases of background images and extracting the ocean background images according to the conditions of weathers and an ocean environment; and the infrared simulated image generation subsystem can generate ocean background infrared simulated images at different detection distances under different ocean conditions and weathers, which take faces as targets. The invention can provide infrared images or videos of artificial targets under an ocean environment background and is used for researching target detection and tracking algorithms in a laboratory environment, thereby providing an experiment research platform for the target detection during maritime search and rescue.
Description
Technical field
The present invention relates to a kind of infrared simulation image platform, specially refer to infrared simulation image platform and image generating method thereof under a kind of marine background.
Background technology
In the marine infrared target detection and tracking algorithm of research, need carry out a large amount of marine ship trials, and ship trial each time all can expend a large amount of man power and materials, financial resources.And, marine infrared prototype testing under some specific conditions is difficult to repeatedly effectively test, in sum because experiment condition is difficult to reach, at the defective of prior art, need infrared simulation image platform and image generating method thereof under a kind of marine background especially.
Summary of the invention
The objective of the invention is to provide the infrared image emulation platform of Weak target in the marine environment for the researchist, this platform can provide under the marine environment background, artificial target infrared image or video are used for goal in research detection and tracking algorithm in laboratory environment.
Technical matters solved by the invention can realize by the following technical solutions:
Infrared simulation image platform under a kind of marine background is characterized in that, described platform comprises that the infrared face statistical mask generates subsystem, the marine background infrared image is chosen subsystem and infrared simulation image generation subsystem; Described infrared face statistical mask generates the face template image that subsystem is used to generate different distance, the infrared database of choosing the management subsystem background image of marine background, according to user's selective extraction marine background image, the infrared simulation image generation subsystem is used for face template image and marine background image are combined.
In one embodiment of the invention, described platform is based on Visual Studio 2008, utilizes C# language to write.
Infrared simulation image generating method under a kind of marine background is characterized in that described method comprises the steps:
1) generation of face simulation template
Because the facial image that photographs is had powerful connections, so at first will intercept the roughly image that contains the people face part by hand, the image that adopts neighborhood averaging adversary work point to cut is again handled, then each pixel of cutting apart good image is done statistics, whether this pixel is belonged to people's face, as the probability of occurrence of this pixel, as the formula (1)
Wherein
For all samples exist
The place is greater than 0 sample number,
Be the sum of image,
Be the statistical mask of being asked, when
Greater than 0.5 o'clock again with all samples
The gray scale at place is averaged, when
Be less than or equal to the gray-scale value zero setting that to put at 0.5 o'clock, obtain new images thus;
2) the marine background image chooses
Take the image of a large amount of marine backgrounds early stage by marine real ship, when background simulation, we are just according to the difference of sea situation, weather, set up different databases, the storage associated picture, when emulation needs,, choose in such cases image as the Background of emulating image according to sea situation and the weather that experimental situation requires;
3) generation of emulating image
The people who generates blushes exterior sheathing, also will be according to the characteristics of marine background image, carry out greyscale transformation, then with face template image and marine background image co-registration, after the image co-registration, more level and smooth for the transition of the edge that makes people's face and background, need further do The disposal of gentle filter, obtain comparatively real image at last.
The invention has the beneficial effects as follows, the image of the marine background infrared simulation under different distance, different sea situation and the weather can be provided, be used for bad border goal in research detection and tracking algorithm in the laboratory.
Description of drawings
Fig. 1 is the structured flowchart of the infrared simulation image platform under the marine background of the present invention.
Embodiment
For technological means, creation characteristic that the present invention is realized, reach purpose and effect is easy to understand, below in conjunction with concrete diagram, further set forth the present invention.
As shown in Figure 1, the infrared simulation image platform under the marine background of the present invention is based on Visual Studio 2008, utilizes C# language to write; This platform comprises that the infrared face statistical mask generates subsystem, the marine background infrared image is chosen subsystem and infrared simulation image generation subsystem; Described infrared face statistical mask generates the face template image that subsystem is used to generate different distance, the infrared database of choosing the management subsystem background image of marine background, according to user's selective extraction marine background image, the infrared simulation image generation subsystem is used for face template image and marine background image are combined.
Below in conjunction with a specific embodiment, further set forth the image generating method of this platform:
Infrared simulation image generating method under a kind of marine background, described method comprises the steps:
1) generation of face simulation template
Because the facial image that photographs is had powerful connections, so people's face need be split from background image.At first manual intercepting contains the roughly image of the image of people face part, this image is averaged again, and the image that promptly adopts neighborhood averaging adversary work point to cut is handled, and gets 3 * 3 neighborhood, as the formula (1),
(1)
Select
The coordinate of middle gray-scale value maximum point
As center that will split image,
In with
For center unified intercepting size is that 9 * 9 facial image is as training image
Again to image
Do threshold process, the people face part is split from background.
Image after cutting apart is obtained by formula (2),
Then each pixel of cutting apart good image is done statistics, statistical mask generates according to the probability of training image, promptly adds up the probability of occurrence of each pixel, finally forms statistical mask.To do statistics through each pixel that formula (2) cut apart good training image, whether this picture element be belonged to people's face, as the probability of occurrence of this picture element.As the formula (3),
Wherein
For all training samples exist
The place is greater than 0 sample number,
Sum for training image.
Be the statistical mask of being asked, when
Greater than 0.5 o'clock again with all training samples
The gray scale at place is averaged, when
Be less than or equal to the gray-scale value zero setting that to put at 0.5 o'clock, obtain new images thus
, promptly
2) the marine background image chooses
Take the image of a large amount of marine backgrounds early stage by marine real ship, when background simulation, we are just according to the difference of sea situation, weather, set up different databases, the storage associated picture, when emulation needs,, choose in such cases image as the Background of emulating image according to sea situation and the weather that experimental situation requires;
3) generation of emulating image
The generation final step of infrared simulation image, the outer image template of exactly people being blushed is embedded in the marine background image.The people who generates blushes outer image template, also needs the marine background feature of image according to reality, carries out greyscale transformation.
1) greyscale transformation
The quantitative formula of greyscale transformation is
Wherein,
The statistical mask image of behaviour face,
For the image after quantizing, right then
Indivedual points that middle gray-scale value crosses the border process, and generate final quantized result
,
With
Minimum and maximum gradation value in the behaviour face statistical mask image,
With
Be minimum in the background image and maximum gradation value [45].
2) people is blushed outer image and marine background image co-registration
The template image of the respective distances that re-quantization is good adopts maximal criterion to be fused in the background image, promptly compares the picture element of template image and background image, selects the big image of gray-scale value for use, suc as formula (7).
Wherein,
For the background image gray scale, work as a little
The gray scale of place's background is less than the analogous diagram picture point
When locating gray scale, point
The gray scale at place is exactly
,
For the final embedding people who generates blushes the extra large background infrared image of outer emulating image.
Through after the greyscale transformation, the gray scale maximal value of facial image equates with true picture, but the intensity profile of template image is too even, has big difference with true picture, therefore needs The disposal of gentle filter.
3) picture smooth treatment
After the image co-registration, more level and smooth for the edge and the background transition that make people's face, need further do Filtering Processing.Select low-pass filtering for use, the high-frequency information at reduction edge.Select for use the low pass spatial filtering method to handle at present.
The specific implementation of mean filter is:
(3.13)
Wherein,
Be the background image of embedding infrared face emulating image,
For behind the mean filter
,
For greater than zero integer,
Be the image buffer storage district, buffer memory be filtered infrared face emulating image,
Be the background image of finally finishing dealing with, wherein c has determined the size of average template, i.e. c=1,3*3 template, c=2,5*5 template.
More than show and described ultimate principle of the present invention and principal character and advantage of the present invention.The technician of the industry should understand; the present invention is not restricted to the described embodiments; that describes in the foregoing description and the instructions just illustrates principle of the present invention; without departing from the spirit and scope of the present invention; the present invention also has various changes and modifications; these changes and improvements all fall in the claimed scope of the invention, and the claimed scope of the present invention is defined by appending claims and equivalent thereof
Claims (3)
1. the infrared simulation image platform under the marine background is characterized in that, described platform comprises that the infrared face statistical mask generates subsystem, the marine background infrared image is chosen subsystem and infrared simulation image generation subsystem; Described infrared face statistical mask generates the face template image that subsystem is used to generate different distance, the infrared database of choosing the management subsystem background image of marine background, situation according to weather, marine environment is extracted the marine background image, and the infrared simulation image generation subsystem is used for face template image and marine background image are combined.
2. the infrared simulation image platform under the marine background as claimed in claim 1 is characterized in that described platform is based on Visual Studio 2008, utilizes C# language to write.
3. the infrared simulation image generating method under the marine background is characterized in that described method comprises the steps:
1) generation of face simulation template
Because the facial image that photographs is had powerful connections, so at first will intercept the roughly image that contains the people face part by hand, the image that adopts neighborhood averaging adversary work point to cut is again handled, then each pixel of cutting apart good image is done statistics, whether this pixel is belonged to people's face, as the probability of occurrence of this pixel, as the formula (1)
Wherein
For all samples exist
The place is greater than 0 sample number,
Be the sum of image,
Be the statistical mask of being asked, when
Greater than 0.5 o'clock again with all samples
The gray scale at place is averaged, when
Be less than or equal to the gray-scale value zero setting that to put at 0.5 o'clock, obtain new images thus;
2) the marine background image chooses
Take the image of a large amount of marine backgrounds early stage by marine real ship, when background simulation, we are just according to the difference of sea situation, weather, set up different databases, the storage associated picture, when emulation needs,, choose in such cases image as the Background of emulating image according to sea situation and the weather that experimental situation requires;
3) generation of emulating image
The people who generates blushes exterior sheathing, also will be according to the characteristics of marine background image, carry out greyscale transformation, then with face template image and marine background image co-registration, after the image co-registration, more level and smooth for the transition of the edge that makes people's face and background, need further do The disposal of gentle filter, obtain comparatively real image at last.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110057771 CN102129700A (en) | 2011-03-11 | 2011-03-11 | Infrared simulated image platform under ocean background and image generation method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110057771 CN102129700A (en) | 2011-03-11 | 2011-03-11 | Infrared simulated image platform under ocean background and image generation method thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102129700A true CN102129700A (en) | 2011-07-20 |
Family
ID=44267774
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 201110057771 Pending CN102129700A (en) | 2011-03-11 | 2011-03-11 | Infrared simulated image platform under ocean background and image generation method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102129700A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102520741A (en) * | 2011-10-24 | 2012-06-27 | 长春理工大学 | Constructed large-scale infrared standard heat source system based on Zigbee wireless network |
CN103186906A (en) * | 2011-12-28 | 2013-07-03 | 中国科学院沈阳自动化研究所 | Real-time infrared dynamic scene simulation method for multiple objects in sea and sky background |
CN107292872A (en) * | 2017-06-16 | 2017-10-24 | 艾松涛 | Image processing method/system, computer-readable recording medium and electronic equipment |
CN108805201A (en) * | 2018-06-08 | 2018-11-13 | 湖南宸瀚信息科技有限责任公司 | Destination image data set creation method and its device |
CN109960742A (en) * | 2019-02-18 | 2019-07-02 | 苏州科达科技股份有限公司 | The searching method and device of local message |
-
2011
- 2011-03-11 CN CN 201110057771 patent/CN102129700A/en active Pending
Non-Patent Citations (3)
Title |
---|
《Proc.of SPIE 62390J-1 》 20061231 Frederic Schwenger, etal 《Sea Surface Simulation in the Infrared Modeling and Validation》 第6239卷, * |
《红外技术》 20070531 李良超 等 《海天背景红外成像仿真系统》 第29卷, 第5期 * |
《红外技术》 20100831 许开宇 等 《基于统计模板的红外人脸仿真图像的实现》 第32卷, 第8期 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102520741A (en) * | 2011-10-24 | 2012-06-27 | 长春理工大学 | Constructed large-scale infrared standard heat source system based on Zigbee wireless network |
CN103186906A (en) * | 2011-12-28 | 2013-07-03 | 中国科学院沈阳自动化研究所 | Real-time infrared dynamic scene simulation method for multiple objects in sea and sky background |
CN107292872A (en) * | 2017-06-16 | 2017-10-24 | 艾松涛 | Image processing method/system, computer-readable recording medium and electronic equipment |
CN108805201A (en) * | 2018-06-08 | 2018-11-13 | 湖南宸瀚信息科技有限责任公司 | Destination image data set creation method and its device |
CN109960742A (en) * | 2019-02-18 | 2019-07-02 | 苏州科达科技股份有限公司 | The searching method and device of local message |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yeh et al. | Lightweight deep neural network for joint learning of underwater object detection and color conversion | |
US11908244B2 (en) | Human posture detection utilizing posture reference maps | |
CN108520503A (en) | A method of based on self-encoding encoder and generating confrontation network restoration face Incomplete image | |
Yin et al. | FD-SSD: An improved SSD object detection algorithm based on feature fusion and dilated convolution | |
Kadam et al. | Detection and localization of multiple image splicing using MobileNet V1 | |
CN111723654A (en) | High-altitude parabolic detection method and device based on background modeling, YOLOv3 and self-optimization | |
CN109472193A (en) | Method for detecting human face and device | |
CN114092833B (en) | Remote sensing image classification method and device, computer equipment and storage medium | |
CN110781882A (en) | License plate positioning and identifying method based on YOLO model | |
CN102129700A (en) | Infrared simulated image platform under ocean background and image generation method thereof | |
CN104063686A (en) | System and method for performing interactive diagnosis on crop leaf segment disease images | |
CN111241924A (en) | Face detection and alignment method and device based on scale estimation and storage medium | |
CN104036296A (en) | Method and device for representing and processing image | |
US11935213B2 (en) | Laparoscopic image smoke removal method based on generative adversarial network | |
CN112861659A (en) | Image model training method and device, electronic equipment and storage medium | |
Zhang et al. | No one can escape: A general approach to detect tampered and generated image | |
CN111476727B (en) | Video motion enhancement method for face-changing video detection | |
CN112800982A (en) | Target detection method based on remote sensing scene classification | |
CN111126155A (en) | Pedestrian re-identification method for generating confrontation network based on semantic constraint | |
CN114926734A (en) | Solid waste detection device and method based on feature aggregation and attention fusion | |
CN110490133A (en) | A method of children's photo being generated by parent's photo based on confrontation network is generated | |
CN113935919A (en) | Image restoration algorithm based on GAN network | |
CN111507276B (en) | Construction site safety helmet detection method based on hidden layer enhanced features | |
CN103093241B (en) | Based on the remote sensing image nonuniformity cloud layer method of discrimination of homogeneity process | |
CN104915641A (en) | Method for obtaining face image light source orientation based on android platform |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20110720 |