CN107093179A - Localization method is searched for for the two waveband fire in wide area space - Google Patents
Localization method is searched for for the two waveband fire in wide area space Download PDFInfo
- Publication number
- CN107093179A CN107093179A CN201710132042.4A CN201710132042A CN107093179A CN 107093179 A CN107093179 A CN 107093179A CN 201710132042 A CN201710132042 A CN 201710132042A CN 107093179 A CN107093179 A CN 107093179A
- Authority
- CN
- China
- Prior art keywords
- mrow
- pixel
- pyrotechnics
- mtd
- area
- 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
- 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
- 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
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- 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)
- Closed-Circuit Television Systems (AREA)
Abstract
The two waveband fire search localization method for wide area space is disclosed, including：The infrared image of target area is obtained in real time, and registration is carried out to the infrared image of acquisition；Binary conversion treatment is carried out to the previous frame image of current frame image and current frame image using inter-frame difference algorithm, difference image is obtained；For any one pixel in difference image：If the pixel value of the pixel is more than default segmentation threshold, then it is assumed that the pixel is foreground pixel, otherwise it is background pixel；Zone marker is carried out to the foreground pixel after segmentation, candidate's pyrotechnics area is obtained；Each pixel in candidate's pyrotechnics area is screened according to default pyrotechnics feature, locking pyrotechnics area is obtained；Tracking lock pyrotechnics area, the geographical position that positioning fire occurs.The present invention is that the fire monitoring to wide area space can be achieved without personnel control, fast and accurate for positioning, and real-time and detection efficiency are high, and false alarm rate is low.
Description
Technical field
Positioning side is searched for the present invention relates to technical field of photoelectric detection, more particularly to for the two waveband fire in wide area space
Method.
Background technology
The background of related to the present invention is illustrated below, but these explanations might not constitute the existing of the present invention
Technology.
The content of the invention
It is an object of the invention to propose that one kind can
The present invention searches for localization method for the two waveband fire in wide area space, including：
S1, the infrared image for obtaining target area in real time, and registration is carried out to the infrared image of acquisition；
S2, using inter-frame difference algorithm the previous frame image of current frame image and current frame image is carried out at binaryzation
Reason, obtains difference image；For any one pixel in difference image：If the pixel value of the pixel is more than default point
Cut threshold value, then it is assumed that the pixel is foreground pixel, otherwise be background pixel；Region mark is carried out to the foreground pixel after segmentation
Note, obtains candidate's pyrotechnics area；
S3, according to default pyrotechnics feature each pixel in candidate's pyrotechnics area is screened, locked
Pyrotechnics area；
S4, the tracking locking pyrotechnics area, the geographical position that positioning fire occurs.
Preferably, zone marker is carried out to the foreground pixel after segmentation and obtains candidate's pyrotechnics area, including：
All foreground pixels are marked, each pixel formation formed in some sub-regions, every sub-regions connects
It is non-conterminous between pixel in continuous region, any two subregion；
For every sub-regions of mark, if the size of the subregion exceedes default dimension threshold, by the son
Delete in region；
Candidate's pyrotechnics area is used as using the set of not deleted subregion.
Preferably, the size of subregion exceedes default dimension threshold, is specially：The size of subregion is more than default chi
The very little upper limit；And/or, the size of subregion is less than default lower size limit；And/or, the length-width ratio of subregion exceedes default ratio
Example range threshold.
Preferably, the inter-frame difference algorithm is：
In formula, BW (x, y, t) is the difference image between t and (t-1) moment two field pictures；When I (x, y, t) is t
Carve the registering image obtained, i.e. current frame image；I (x, y, t-1) is the registering image obtained at (t-1) moment, i.e. present frame figure
The previous frame image of picture；(x, y) is pixel point coordinates；T is segmentation threshold.
Preferably,
Wherein,For the average gray value of current frame image.
Preferably, each pixel in candidate's pyrotechnics area is sieved according to default pyrotechnics feature in step S3
Choosing, obtains locking pyrotechnics area, including：
Current frame image is changed into YC from rgb spacebCrSpace, obtains the brightness point of each pixel in candidate's pyrotechnics area
Measure Y, chroma blue component Cb, red chrominance component Cr；
By luminance component Y, the chroma blue component C of each pixel in candidate's pyrotechnics areab, red chrominance component CrWith it is pre-
If pyrotechnics feature contrasted, filter out the pixel for meeting default pyrotechnics feature；
The set of pixel to meet default pyrotechnics feature is used as locking pyrotechnics area.
Preferably for any one pixel in candidate's pyrotechnics area, when it meets following relation, judge that it meets
Default pyrotechnics feature：
Preferably, registration is carried out to the infrared image of acquisition using Gray Projection method in step S1；Wherein,
In formula, row (i) is the projection value of the i-th row, and column (j) is the projection value that jth is arranged, and pic (i, j) is pixel
The gray value at (i, j) place；C (w) is row correlation, and C (p) is row correlation；MwFor the row jitter range of infrared image, unit is
OK；MpFor the row jitter range of infrared image, unit is row；W is line skew amount, and unit is row；P is line displacement amount, and unit is
OK.
The present invention carries out progress inter-frame difference after registration, registration to infrared image and obtains candidate's pyrotechnics area, Ran Hougen first
Each pixel in candidate's pyrotechnics area screen according to default pyrotechnics feature and obtains locking pyrotechnics area, last tracking lock
Pyrotechnics area, the geographical position that positioning fire occurs.The fire search localization method of the present invention can search for fire information, nothing in real time
Personnel control is needed, it is fast and accurate for positioning, and promptness is good, efficiency high；By according to default pyrotechnics feature to candidate's pyrotechnics
Each pixel in area is screened, and can exclude the interference of non-fiery target, further improves the accurate of fire search positioning
Property.
Brief description of the drawings
By the embodiment part of offer referring to the drawings, the features and advantages of the present invention will become more
It is readily appreciated that, in the accompanying drawings：
Fig. 1 is the schematic flow sheet that the present invention searches for localization method for the two waveband fire in wide area space；
Fig. 2 is that the flow for carrying out registration to the infrared image of acquisition using Gray Projection method in the preferred embodiment of the present invention is shown
It is intended to；
Fig. 3 is the positioning schematic diagram of fire location in the preferred embodiment of the present invention.
Embodiment
The illustrative embodiments to the present invention are described in detail with reference to the accompanying drawings.Illustrative embodiments are retouched
State merely for the sake of demonstration purpose, and be definitely not to the present invention and its application or the limitation of usage.
As shown in figure 1, two waveband fire search localization method of the present invention for wide area space, real first in step S1
When obtain the infrared image of target area, and registration is carried out to the infrared image of acquisition.
The essence of sequence of video images is exactly one group of image that consecutive variations occur for gray scale, and gray projection algorithm can be abundant
Using this grey scale change feature of image, a related operation is done for the ranks Gray scale projection curve of image, it is possible to compared with
The motion vector of image is adequately obtained, its operand is small, speed fast, with preferable motion estimation capabilities.Therefore, at some
In embodiment, registration can be carried out to the infrared image of acquisition using Gray Projection method, as shown in Figure 2.Wherein,
In formula, row (i) is the projection value of the i-th row, and column (j) is the projection value that jth is arranged, and pic (i, j) is pixel
The gray value at (i, j) place；C (w) is row correlation, and C (p) is row correlation；MwFor the row jitter range of infrared image, unit is
OK；MpFor the row jitter range of infrared image, unit is row；W is line skew amount, and unit is row；P is line displacement amount, and unit is
OK.
S2, using inter-frame difference algorithm the previous frame image of current frame image and current frame image is carried out at binaryzation
Reason, obtains difference image.Frame differential method is that the athletic meeting based on target is embodied in the change of image sequence, directly compares figure
The method of progress moving object detection based on the relative change occurred as sequence consecutive frame correspondence picture element.This method is simple
Directly, practicality is good.
For any one pixel in difference image：If the pixel value of the pixel is more than default segmentation threshold,
It is foreground pixel then to think the pixel, otherwise is background pixel；Zone marker is carried out to the foreground pixel after segmentation, waited
Select pyrotechnics area.
Preferably inter-frame difference algorithm is：
In formula, BW (x, y, t) is the difference image between t and (t-1) moment two field pictures；When I (x, y, t) is t
Carve the registering image obtained, i.e. current frame image；I (x, y, t-1) is the registering image obtained at (t-1) moment, i.e. present frame figure
The previous frame image of picture；(x, y) is pixel point coordinates；T is segmentation threshold.
In a preferred embodiment of the invention,Wherein,For the average gray value of current frame image.In this way,
The amount of calculation of foreground pixel on the basis of algorithm accuracy is met, can be greatly reduced, the time of inter-frame difference algorithm is reduced
Consumption.
Real time scan of the present invention obtains the infrared image of target area, if fire occurs for target area, according to the present invention's
Fire search localization method is capable of the process of dynamic instrumentation fire generation, i.e., fire letter can be detected at the beginning of fire occurs
Breath.In addition, from the harmfulness and the urgent angle analysis of fire fighting of fire, also requiring that and detecting fire information as early as possible.Due to
The size that the present invention can detect the candidate's pyrotechnics area obtained after fire information, therefore segmentation at the beginning of fire occurs is general not
Can be especially big, if candidate's pyrotechnics area is oversized, probably come from the interference of non-fiery target.Based on this, to dividing
Foreground pixel progress zone marker after cutting, which obtains candidate's pyrotechnics area, to be included：
All foreground pixels are marked, each pixel formation formed in some sub-regions, every sub-regions connects
It is non-conterminous between pixel in continuous region, any two subregion；
For every sub-regions of mark, if the size of the subregion exceedes default dimension threshold, by the son
Delete in region；
Candidate's pyrotechnics area is used as using the set of not deleted subregion.
Default dimension threshold can be that the dimension scale that specific size value or subregion should be met is closed
System, those skilled in the art can set the form and numerical value of dimension threshold according to actual conditions, and the present invention does not do specific to this
Limit.In certain embodiments, the size of subregion is specially more than default dimension threshold：The size of subregion is more than default
Upper dimension bound；And/or, the size of subregion is less than default lower size limit；And/or, the length-width ratio of subregion, which exceedes, to be preset
Proportion threshold value.
The candidate's pyrotechnics area extracted is probably pyrotechnics, it is also possible to some non-fiery targets, large-scale dynamic such as ox, sheep
Thing.Further comprise step S3 after the interference of non-fiery target, step S2 to exclude：According to default pyrotechnics feature to institute
The each pixel stated in candidate's pyrotechnics area is screened, and obtains locking pyrotechnics area.
Preferably, each pixel in candidate's pyrotechnics area is sieved according to default pyrotechnics feature in step S3
Choosing, obtains locking pyrotechnics area, including：Current frame image is changed into YC from rgb spacebCrSpace, obtains each in candidate's pyrotechnics area
Luminance component Y, the chroma blue component C of pixelb, red chrominance component Cr；By the brightness of each pixel in candidate's pyrotechnics area
Component Y, chroma blue component Cb, red chrominance component CrContrasted with default pyrotechnics feature, filter out and meet default cigarette
The pixel of fiery feature；The set of pixel to meet default pyrotechnics feature is used as locking pyrotechnics area.Forest, grassland etc. are wide
In domain space, fire detection only such as is carried out with infrared, is easily disturbed by targets such as ox, sheep or automobiles, produce higher void
Alert rate.Each pixel in candidate's pyrotechnics area is screened using the above method, interference, reduction void can be further eliminated
Alert rate.Preferably for any one pixel in candidate's pyrotechnics area, when it meets following relation, it is possible to determine that it is accorded with
Close default pyrotechnics feature：
S4, the tracking locking pyrotechnics area, the geographical position that positioning fire occurs.Fig. 3 shows that the present invention is preferable to carry out
The positioning schematic diagram of fire location in example.After pyrotechnics target is locked, the azimuth pitch angle of detector is obtained, according to detector
The height of erection, can extrapolate position and the distance of pyrotechnics target, so as to effectively implement rescue.It is possible to further basis
Local electronic map and fire location makes rational rescue route, arranges rescue personnel quickly to dispose fire.
Compared with prior art, the present invention can improve the real-time and detection efficiency of fire search positioning, reduce false-alarm
Rate, realizes the fire monitoring to wide area space.
Although with reference to illustrative embodiments, invention has been described, but it is to be understood that the present invention does not limit to
The embodiment that Yu Wenzhong is described in detail and shown, in the case of without departing from claims limited range, this
Art personnel can make various changes to the illustrative embodiments.
Claims (8)
1. for the two waveband fire search localization method in wide area space, it is characterised in that including：
S1, the infrared image for obtaining target area in real time, and registration is carried out to the infrared image of acquisition；
S2, binary conversion treatment carried out to the previous frame image of current frame image and current frame image using inter-frame difference algorithm,
Obtain difference image；For any one pixel in difference image：If the pixel value of the pixel is more than default segmentation
Threshold value, then it is assumed that the pixel is foreground pixel, on the contrary it is background pixel；Zone marker is carried out to the foreground pixel after segmentation,
Obtain candidate's pyrotechnics area；
S3, according to default pyrotechnics feature each pixel in candidate's pyrotechnics area is screened, obtain locking pyrotechnics
Area；
S4, the tracking locking pyrotechnics area, the geographical position that positioning fire occurs.
2. two waveband fire as claimed in claim 1 searches for localization method, it is characterised in that the foreground pixel after segmentation is entered
Row zone marker obtains candidate's pyrotechnics area, including：
All foreground pixels are marked, each pixel formation continuum formed in some sub-regions, every sub-regions
It is non-conterminous between pixel in domain, any two subregion；
For every sub-regions of mark, if the size of the subregion exceedes default dimension threshold, by the subregion
Delete；
Candidate's pyrotechnics area is used as using the set of not deleted subregion.
3. two waveband fire as claimed in claim 2 searches for localization method, it is characterised in that the size of subregion exceedes default
Dimension threshold, be specially：The size of subregion is more than default upper dimension bound；And/or, the size of subregion is less than default
Lower size limit；And/or, the length-width ratio of subregion exceedes default proportion threshold value.
4. two waveband fire as claimed in claim 3 searches for localization method, it is characterised in that the inter-frame difference algorithm is：
<mrow>
<mi>B</mi>
<mi>W</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>,</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mn>1</mn>
</mtd>
<mtd>
<mrow>
<mi>f</mi>
<mi>o</mi>
<mi>r</mi>
<mi>e</mi>
<mi>g</mi>
<mi>r</mi>
<mi>o</mi>
<mi>u</mi>
<mi>n</mi>
<mi>d</mi>
<mo>,</mo>
</mrow>
</mtd>
<mtd>
<mrow>
<mo>|</mo>
<mi>I</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>,</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mi>I</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>,</mo>
<mi>t</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>|</mo>
<mo>&GreaterEqual;</mo>
<mi>T</mi>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>0</mn>
</mtd>
<mtd>
<mrow>
<mi>b</mi>
<mi>a</mi>
<mi>c</mi>
<mi>k</mi>
<mi>g</mi>
<mi>r</mi>
<mi>o</mi>
<mi>u</mi>
<mi>n</mi>
<mi>d</mi>
<mo>,</mo>
</mrow>
</mtd>
<mtd>
<mrow>
<mo>|</mo>
<mi>I</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>,</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mi>I</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo>,</mo>
<mi>t</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>|</mo>
<mo><</mo>
<mi>T</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
In formula, BW (x, y, t) is the difference image between t and (t-1) moment two field pictures；I (x, y, t) obtains for t
The registering image taken, i.e. current frame image；I (x, y, t-1) is the registering image obtained at (t-1) moment, i.e. current frame image
Previous frame image；(x, y) is pixel point coordinates；T is segmentation threshold.
5. two waveband fire as claimed in claim 4 searches for localization method, it is characterised in that
Wherein,For the average gray value of current frame image.
6. two waveband fire as claimed in claim 1 searches for localization method, it is characterised in that according to default cigarette in step S3
Fiery feature is screened to each pixel in candidate's pyrotechnics area, obtains locking pyrotechnics area, including：
Current frame image is changed into YC from rgb spacebCrSpace, obtain the luminance component Y of each pixel in candidate's pyrotechnics area,
Chroma blue component Cb, red chrominance component Cr；
By luminance component Y, the chroma blue component C of each pixel in candidate's pyrotechnics areab, red chrominance component CrWith it is default
Pyrotechnics feature is contrasted, and filters out the pixel for meeting default pyrotechnics feature；
The set of pixel to meet default pyrotechnics feature is used as locking pyrotechnics area.
7. two waveband fire as claimed in claim 6 searches for localization method, it is characterised in that for appointing in candidate's pyrotechnics area
One pixel of meaning, when it meets following relation, judges that it meets default pyrotechnics feature：
<mrow>
<mfenced open='' close=''>
<mtable>
<mtr>
<mtd>
<mi>Y</mi>
<mo>></mo>
<mn>50</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>C</mi>
<mi>r</mi>
</msub>
<mo>-</mo>
<msub>
<mi>C</mi>
<mi>b</mi>
</msub>
<mo>></mo>
<mn>55</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>.</mo>
</mrow>
1
8. two waveband fire as claimed in claim 1 searches for localization method, it is characterised in that Gray Projection is used in step S1
Method carries out registration to the infrared image of acquisition；Wherein,
<mfenced open = "" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>r</mi>
<mi>o</mi>
<mi>w</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>p</mi>
<mi>i</mi>
<mi>c</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>c</mi>
<mi>o</mi>
<mi>l</mi>
<mi>u</mi>
<mi>m</mi>
<mi>n</mi>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<mi>p</mi>
<mi>i</mi>
<mi>c</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mrow>
<mi>C</mi>
<mrow>
<mo>(</mo>
<mi>w</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<msup>
<mrow>
<mo>&lsqb;</mo>
<mi>c</mi>
<mi>o</mi>
<mi>l</mi>
<mi>u</mi>
<mi>m</mi>
<mi>n</mi>
<mi>x</mi>
<mrow>
<mo>(</mo>
<mi>j</mi>
<mo>+</mo>
<mi>w</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mi>c</mi>
<mi>o</mi>
<mi>l</mi>
<mi>u</mi>
<mi>m</mi>
<mi>n</mi>
<mi>r</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>M</mi>
<mi>w</mi>
</msub>
<mo>+</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
<mrow>
<mi>C</mi>
<mrow>
<mo>(</mo>
<mi>p</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<msup>
<mrow>
<mo>&lsqb;</mo>
<mi>r</mi>
<mi>o</mi>
<mi>w</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>+</mo>
<mi>p</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mi>r</mi>
<mi>o</mi>
<mi>w</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>M</mi>
<mi>p</mi>
</msub>
<mo>+</mo>
<mi>i</mi>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
In formula, row (i) is the projection value of the i-th row, and column (j) is the projection value that jth is arranged, and pic (i, j) is pixel (i, j)
The gray value at place；C (w) is row correlation, and C (p) is row correlation；MwFor the row jitter range of infrared image, unit is row；Mp
For the row jitter range of infrared image, unit is row；W is line skew amount, and unit is row；P is line displacement amount, and unit is row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710132042.4A CN107093179A (en) | 2017-03-07 | 2017-03-07 | Localization method is searched for for the two waveband fire in wide area space |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710132042.4A CN107093179A (en) | 2017-03-07 | 2017-03-07 | Localization method is searched for for the two waveband fire in wide area space |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107093179A true CN107093179A (en) | 2017-08-25 |
Family
ID=59646566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710132042.4A Pending CN107093179A (en) | 2017-03-07 | 2017-03-07 | Localization method is searched for for the two waveband fire in wide area space |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107093179A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009800A (en) * | 2019-03-14 | 2019-07-12 | 北京京东尚科信息技术有限公司 | A kind of recognition methods and equipment |
| CN111145234A (en) * | 2019-12-25 | 2020-05-12 | 沈阳天眼智云信息科技有限公司 | Fire smoke detection method based on binocular vision |
| CN113379628A (en) * | 2021-06-07 | 2021-09-10 | 中国民用航空飞行学院 | Method for detecting thermal runaway of lithium battery based on infrared thermal imager |
| CN113379781A (en) * | 2021-07-29 | 2021-09-10 | 浙江大华技术股份有限公司 | Image processing method and apparatus, storage medium, and electronic device |
| CN115506852A (en) * | 2022-11-04 | 2022-12-23 | 衡水奇佳工程材料有限公司 | Full-automatic protection equipment and protection method for tunnel |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101950419A (en) * | 2010-08-26 | 2011-01-19 | 西安理工大学 | Quick image rectification method in presence of translation and rotation at same time |
| CN103971114A (en) * | 2014-04-23 | 2014-08-06 | 天津航天中为数据***科技有限公司 | Forest fire detection method based on aerial remote sensing |
| CN104616322A (en) * | 2015-02-10 | 2015-05-13 | 山东省科学院海洋仪器仪表研究所 | Onboard infrared target image identifying and tracking method and device |
| CN105447471A (en) * | 2015-12-04 | 2016-03-30 | 国网技术学院 | Infrared detection based device gas leakage identification method and apparatus |
| CN105575034A (en) * | 2014-10-14 | 2016-05-11 | 哈尔滨新光光电科技有限公司 | Image processing and analysis method of double-waveband forest fireproof intelligent monitoring software |
-
2017
- 2017-03-07 CN CN201710132042.4A patent/CN107093179A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101950419A (en) * | 2010-08-26 | 2011-01-19 | 西安理工大学 | Quick image rectification method in presence of translation and rotation at same time |
| CN103971114A (en) * | 2014-04-23 | 2014-08-06 | 天津航天中为数据***科技有限公司 | Forest fire detection method based on aerial remote sensing |
| CN105575034A (en) * | 2014-10-14 | 2016-05-11 | 哈尔滨新光光电科技有限公司 | Image processing and analysis method of double-waveband forest fireproof intelligent monitoring software |
| CN104616322A (en) * | 2015-02-10 | 2015-05-13 | 山东省科学院海洋仪器仪表研究所 | Onboard infrared target image identifying and tracking method and device |
| CN105447471A (en) * | 2015-12-04 | 2016-03-30 | 国网技术学院 | Infrared detection based device gas leakage identification method and apparatus |
Non-Patent Citations (3)
| Title |
|---|
| 李林 等: "周扫条件下的红外运动目标检测", 《红外与激光工程》 * |
| 王进成 等: "可见光与红外的视频火灾探测器设计", 《单片机与嵌入式***应用》 * |
| 郭炜强: "基于运动特征的林火烟雾图像检测技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009800A (en) * | 2019-03-14 | 2019-07-12 | 北京京东尚科信息技术有限公司 | A kind of recognition methods and equipment |
| CN111145234A (en) * | 2019-12-25 | 2020-05-12 | 沈阳天眼智云信息科技有限公司 | Fire smoke detection method based on binocular vision |
| CN113379628A (en) * | 2021-06-07 | 2021-09-10 | 中国民用航空飞行学院 | Method for detecting thermal runaway of lithium battery based on infrared thermal imager |
| CN113379781A (en) * | 2021-07-29 | 2021-09-10 | 浙江大华技术股份有限公司 | Image processing method and apparatus, storage medium, and electronic device |
| CN115506852A (en) * | 2022-11-04 | 2022-12-23 | 衡水奇佳工程材料有限公司 | Full-automatic protection equipment and protection method for tunnel |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107093179A (en) | Localization method is searched for for the two waveband fire in wide area space | |
| CN106096577B (en) | A kind of target tracking method in camera distribution map | |
| Kong et al. | Detecting abandoned objects with a moving camera | |
| CN103366156B (en) | Road structure detect and track | |
| CN103425967B (en) | A kind of based on stream of people's monitoring method of pedestrian detection and tracking | |
| US7982774B2 (en) | Image processing apparatus and image processing method | |
| CN105069429B (en) | A kind of flow of the people analytic statistics methods and system based on big data platform | |
| CN101673396B (en) | Image fusion method based on dynamic object detection | |
| KR100879266B1 (en) | Object tracing and intrusion sensing system | |
| US20110142283A1 (en) | Apparatus and method for moving object detection | |
| CN102567722B (en) | Early-stage smoke detection method based on codebook model and multiple features | |
| CN105354563A (en) | Depth and color image combined human face shielding detection early-warning device and implementation method | |
| US20120070034A1 (en) | Method and apparatus for detecting and tracking vehicles | |
| KR102160591B1 (en) | Fire situation generation system and its optimization method for fire situation detection model | |
| CN105578198B (en) | Based on when inclined feature the homologous Copy-Move detection method of video | |
| JP2008045974A (en) | Object-detecting apparatus | |
| CN106778570B (en) | A kind of pedestrian detection and tracking in real time | |
| CN111161309B (en) | Searching and positioning method for vehicle-mounted video dynamic target | |
| CN104811586A (en) | Scene change video intelligent analyzing method, device, network camera and monitoring system | |
| CN101976436A (en) | Pixel-level multi-focus image fusion method based on correction of differential image | |
| CN106570888A (en) | Target tracking method based on FAST (Features from Accelerated Segment Test) corner point and pyramid KLT (Kanade-Lucas-Tomasi) | |
| CN105869148A (en) | Target detection method and device | |
| CN104867128A (en) | Image blurring detection method and device | |
| CN105469427A (en) | Target tracking method applied to videos | |
| CN107105193A (en) | Robot monitoring system based on human body information |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170825 |