CN107195021A - The drive recorder of haze interference - Google Patents
The drive recorder of haze interference Download PDFInfo
- Publication number
- CN107195021A CN107195021A CN201710380740.6A CN201710380740A CN107195021A CN 107195021 A CN107195021 A CN 107195021A CN 201710380740 A CN201710380740 A CN 201710380740A CN 107195021 A CN107195021 A CN 107195021A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- haze
- image
- ambient image
- 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
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
- G07C5/085—Registering performance data using electronic data carriers
- G07C5/0866—Registering performance data using electronic data carriers the electronic data carrier being a digital video recorder in combination with video camera
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Studio Devices (AREA)
Abstract
The invention provides the haze ambient image that a kind of drive recorder of haze interference, including camera, image processor, memory and display, the camera are used for before collection vehicle;Described image processor is used to carry out enhancing processing to haze ambient image, obtains high-quality ambient image;The display is used to show high-quality ambient image.The present invention carries out algorithm enhancing processing by the haze ambient image collected to the camera in drive recorder, the image after handling is enabled to overcome the interference of haze environment, the ambient image of traffic information and outputting high quality before clear registration of vehicle, is car owner's raising great convenience in haze environment middle rolling car.
Description
Technical field
The present invention relates to intelligent transportation field, and in particular to a kind of drive recorder of haze interference.
Background technology
With the fast development in city, environmental aspect becomes further severe in city, many cities of PM2.5 severe contaminations China
The air in city, preventing and treating haze becomes the problem that many The Surroundings in Cities departments first have to solve.Haze not only gives health
Influence is brought, the molecule that also collection to outdoor video image is brought in challenge, air causes video capture device
The complexity of residing environment is greatly increased, and atmospheric impurities and haze cause the generation of degraded image, are the accurate inspection of image
Survey and identification brings difficulty, be badly in need of a kind of new image processing method, the image gathered in haze environment is carried out to handle also
It is former.
The content of the invention
In view of the above-mentioned problems, a kind of the present invention is intended to provide drive recorder of haze interference.
The purpose of the present invention is realized using following technical scheme:
A kind of drive recorder of haze interference, including camera, image processor, memory and display, it is described
The haze ambient image that camera is used for before collection vehicle;Described image processor is used to strengthen haze ambient image
Processing, obtains high-quality ambient image;The display is used to show high-quality ambient image.
Beneficial effects of the present invention are:Haze environment of the invention by being collected to the camera in drive recorder
Image carries out algorithm enhancing processing so that the image after processing can be overcome before the interference of haze environment, clear registration of vehicle
Traffic information and outputting high quality ambient image, be haze environment middle rolling car car owner improve greatly facilitate.
Brief description of the drawings
Using accompanying drawing, the invention will be further described, but the embodiment in accompanying drawing does not constitute any limit to the present invention
System, for one of ordinary skill in the art, on the premise of not paying creative work, can also be obtained according to the following drawings
Other accompanying drawings.
Fig. 1 is the frame construction drawing of the present invention;
Fig. 2 is the frame construction drawing of the image processor of the present invention.
Reference:
Camera 1, image processor 2, memory 3, display 4, image local enhancing module 201, image overall enhancing
Module 202 and image detail enhancing module 203.
Embodiment
With reference to following application scenarios, the invention will be further described.
Referring to Fig. 1, a kind of drive recorder of haze interference of the present embodiment, including camera 1, image processor 2,
Memory 3 and display 4, the camera 1 are connected with the cable network of described image processor 2, before collection vehicle
Haze ambient image;Described image processor 2 is used to carry out enhancing processing to haze ambient image, obtains high-quality environment map
Picture;The display 4 is used to show high-quality ambient image.
Preferably, the camera uses camera lens for 5 layers of full glass wide-angle lens.
Preferably, the memory is expansible memory, for being obtained after the processing of described image processor
High-quality ambient image is recorded, and the memory of expanding is Micro SD storage cards or mobile hard disk.
The above embodiment of the present invention, is carried out by the haze ambient image collected to the camera in drive recorder
Algorithm enhancing is handled so that the image after processing can overcome the road conditions before the interference of haze environment, clear registration of vehicle to believe
The ambient image of simultaneously outputting high quality is ceased, is car owner's raising great convenience in haze environment middle rolling car.
Preferably, as shown in Fig. 2 described image processor includes image local enhancing module, image overall enhancing module
Strengthen module with image detail;
The haze ambient image that described image local enhancement module is used for before the vehicle that collects the camera
The brightness value of the adjacent pixel of each pixel is weighted averagely to eliminate illumination change, and uses non-linear S-shaped
Transfer function is combined to realize that haze ambient image is compressed with logarithmic function, is improved haze ambient image local contrast, is recovered
Haze ambient image local color, be specially:
In formula, SaThe brightness value of a-th of the color spectral coverage in (m, n) denotation coordination position (m, n), μhFor h-th of yardstick yardstick pair
The weighted value answered, and weighted value meets normalizing conditionH is yardstick number, is set as 3,Represent to sit
The brightness value of cursor position (m, n) a-th of color spectral coverage, h-th of yardstick, tansig (t) is non-linear S-shaped transfer function, and t is non-
The variable of linear S-shaped transfer function, Pa(m, n) is the pixel of the haze ambient image of a-th of color spectral coverage of coordinate position (m, n)
Value, * represents convolution algorithm, and G (m, n) is that m and n represent haze ambient image abscissa value and ordinate value respectively around function.
The above embodiment of the present invention, replaces traditional by the way of non-linear S-shaped transfer function is combined with logarithmic function
The haze ambient image that camera in vehicular motion is collected is compressed with logarithmic function merely, can be significantly
The compressed capability to haze ambient image in dynamic range is improved, image processor is improved and dynamic haze ambient image is compressed
Efficiency, it is ensured that the good quality of dynamic haze ambient image after being compressed, while avoiding the local face of haze ambient image
Colour distortion, the image for showing display is more nearly real scene image.
Preferably, described image overall situation enhancing module is used for the gray scale to completing the haze ambient image after local enhancement
Grading column hisgram construction, and the gray level sum in the maximum gray scale in histogram and histogram not for 0 is filtered out, then
Conversion process is carried out using the gray level of gray scale transformation function pair haze ambient image, strengthens the global right of haze ambient image
Degree of ratio, it is ensured that the integrity degree of haze ambient image information, be specially:
E (1)=1
In formula, E (a) is the gray level of a-th of color spectral coverage, faThe probability occurred for a-th of color spectral coverage;
In formula, C (a) is gray scale transformation function, and INT () is bracket function, and J ' is haze ambient image gray level
Maximum gray scale in histogram, J be not in the histogram of haze ambient image gray level 0 gray level sum.
The above embodiment of the present invention, is carried out by constructing the method for histogram and gray scale transformation to haze ambient image
Overall enhancing, is conducive to stretching the contrast of haze ambient image, while avoiding haze ambient image being smoothed of details, it is ensured that
The gray level resolution of haze ambient image will not decline, and be conducive to the details in original haze ambient image can be convex well
Show and, the road conditions of more true accurate registration of vehicle vehicle front during moving ahead.
Preferably, described image details enhancing module is according to the change speed of haze ambient image brightness or enriching for details
Degree, is divided into details area, high-contrast edges regional peace skating area domain by piece image, to realize significantly gain haze ring
The edge in border image detail region, smaller gain high-contrast area peaceful skating area domain, gain is changed using Custom Space
Function pair haze ambient image details is handled, the Custom Space that uses change gain function for:
In formula, BaFor the spatial variations gain function of a-th of color spectral coverage,For a-th of coordinate position (m, n)
Value after the brightness normalization of color spectral coverage, byPhenogram is as the size of contrast on border, Sa(m, n) denotation coordination
The brightness value of a-th of the color spectral coverage in position (m, n), m and n represent haze ambient image abscissa value and ordinate value respectively.
The above embodiment of the present invention, the Custom Space of use changes carry out details of the gain function to haze ambient image
Enhancing is handled, and is conducive to avoiding the excessively high-contrast edges regional peace skating area domain of enhancing haze ambient image and is caused image
Details is obscured, while avoiding the amplification to noise, is conducive to the suppression to noise so that the details of haze ambient image is obtained
Preferably reduction, blur effect when weakening haze environment to camera collection vehicle forward image significantly is conducive to image
Clear display.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than to present invention guarantor
The limitation of scope is protected, although being explained with reference to preferred embodiment to the present invention, one of ordinary skill in the art should
Work as understanding, technical scheme can be modified or equivalent substitution, without departing from the reality of technical solution of the present invention
Matter and scope.
Claims (6)
1. a kind of drive recorder of haze interference, it is characterized in that, including camera, image processor, memory and display
Device, the haze ambient image that the camera is used for before collection vehicle;Described image processor is used for haze ambient image
Enhancing processing is carried out, high quality environment image is obtained;The display is used to show high quality environment image.
2. a kind of drive recorder of haze interference according to claim 1, it is characterized in that, the camera uses mirror
Head is 5 layers of full glass wide-angle lens.
3. a kind of drive recorder of haze interference according to claim 1, it is characterized in that, the memory is to expand
Open up memory, for after the processing of described image processor obtained high-quality ambient image record, it is described can
It is Micro SD storage cards or mobile hard disk to expand memory.
4. a kind of drive recorder of haze interference according to claim 1, it is characterized in that, described image processor bag
Include image local enhancing module, image overall enhancing module and image detail enhancing module;
The haze ambient image that described image local enhancement module is used for before the vehicle that collects the camera is each
The brightness value of the adjacent pixel of pixel is weighted averagely to eliminate illumination change, and using the transmission of non-linear S-shaped
The method that function is combined with logarithmic function realizes that haze ambient image is compressed, and improves haze ambient image local contrast, recovers
Haze ambient image local color, be specially:
<mrow>
<msub>
<mi>S</mi>
<mi>a</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>h</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>H</mi>
</munderover>
<msub>
<mi>&mu;</mi>
<mi>h</mi>
</msub>
<msub>
<mi>S</mi>
<msub>
<mi>h</mi>
<mi>a</mi>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mi>S</mi>
<msub>
<mi>h</mi>
<mi>a</mi>
</msub>
</msub>
<mrow>
<mo>(</mo>
<mrow>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
</mrow>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>tan</mi>
<mi>s</mi>
<mi>i</mi>
<mi>g</mi>
<mrow>
<mo>&lsqb;</mo>
<mfrac>
<mrow>
<msub>
<mi>P</mi>
<mi>a</mi>
</msub>
<mrow>
<mo>(</mo>
<mrow>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mi>G</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
</mrow>
<mo>)</mo>
</mrow>
<mo>*</mo>
<msub>
<mi>P</mi>
<mi>a</mi>
</msub>
<mrow>
<mo>(</mo>
<mrow>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>&rsqb;</mo>
</mrow>
<mo>+</mo>
<msub>
<mi>log</mi>
<mn>2</mn>
</msub>
<msub>
<mi>P</mi>
<mi>a</mi>
</msub>
<mrow>
<mo>(</mo>
<mrow>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mi>G</mi>
<mrow>
<mo>(</mo>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mi>m</mi>
</mtd>
<mtd>
<mrow>
<mi>m</mi>
<mo>&le;</mo>
<mn>1</mn>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mn>1</mn>
<mo>+</mo>
<mi>l</mi>
<mi>n</mi>
<mrow>
<mo>(</mo>
<mi>m</mi>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>m</mi>
<mo>></mo>
<mn>1</mn>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
<mrow>
<mi>tan</mi>
<mi>s</mi>
<mi>i</mi>
<mi>g</mi>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>2</mn>
<mrow>
<mn>1</mn>
<mo>+</mo>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<mo>-</mo>
<mn>2</mn>
<mi>t</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>-</mo>
<mn>1</mn>
</mrow>
In formula, SaThe brightness value of a-th of the color spectral coverage in (m, n) denotation coordination position (m, n), μhIt is corresponding for h-th of yardstick yardstick
Weighted value, and weighted value meets normalizing conditionH is yardstick number,Denotation coordination position (m, n)
The brightness value of a-th of color spectral coverage, h-th of yardstick, tansig (t) is non-linear S-shaped transfer function, and t transmits for non-linear S-shaped
The variable of function, Pa(m, n) is the pixel value of the haze ambient image of a-th of color spectral coverage of coordinate position (m, n), and * represents volume
Product computing, G (m, n) is that m and n represent haze ambient image abscissa value and ordinate value respectively around function.
5. a kind of drive recorder of haze interference according to claim 4, it is characterized in that, described image overall situation enhancing
Module is used to enter the gray level for completing the haze ambient image after local enhancement column hisgram construction, and filters out histogram
In maximum gray scale and histogram in for 0 gray level sum, then using gray scale transformation function pair haze environment map
The gray level of picture carries out conversion process, to strengthen the global contrast of haze ambient image, it is ensured that haze ambient image information
Integrity degree, be specially:
E (1)=1
<mrow>
<mi>E</mi>
<mrow>
<mo>(</mo>
<mi>a</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>E</mi>
<mrow>
<mo>(</mo>
<mi>a</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mn>1</mn>
</mrow>
</mtd>
<mtd>
<mrow>
<msub>
<mi>f</mi>
<mi>a</mi>
</msub>
<mo>&NotEqual;</mo>
<mn>0</mn>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>E</mi>
<mrow>
<mo>(</mo>
<mi>a</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
<mtd>
<mrow>
<msub>
<mi>f</mi>
<mi>a</mi>
</msub>
<mo>=</mo>
<mn>0</mn>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
In formula, E (a) is the gray level of a-th of color spectral coverage, and E (a-1) is the gray level of (a-1) individual color spectral coverage, faFor a
The probability that individual color spectral coverage occurs;
<mrow>
<mi>C</mi>
<mrow>
<mo>(</mo>
<mi>a</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>I</mi>
<mi>N</mi>
<mi>T</mi>
<mo>&lsqb;</mo>
<mi>E</mi>
<mrow>
<mo>(</mo>
<mi>a</mi>
<mo>)</mo>
</mrow>
<mfrac>
<msup>
<mi>J</mi>
<mo>&prime;</mo>
</msup>
<mi>J</mi>
</mfrac>
<mo>-</mo>
<mfrac>
<mn>1</mn>
<msup>
<mi>J</mi>
<mo>&prime;</mo>
</msup>
</mfrac>
<mi>E</mi>
<mrow>
<mo>(</mo>
<mi>a</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
</mrow>
In formula, C (a) is gray scale transformation function, and INT () is bracket function, and J ' is the Nogata of haze ambient image gray level
Maximum gray scale in figure, J be not in the histogram of haze ambient image gray level 0 gray level sum.
6. a kind of drive recorder of haze interference according to claim 5, it is characterized in that, the enhancing of described image details
Piece image is divided into details area, height by module according to the change speed or the abundant degree of details of haze ambient image brightness
Contrast fringe region and smooth region, to realize significantly gain haze ambient image details area, high gain pair smaller
Than the edge in degree regional peace skating area domain, using Custom Space change gain function to haze ambient image details at
Reason, use Custom Space change gain function for:
<mrow>
<msub>
<mi>B</mi>
<mi>a</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msup>
<mrow>
<mo>&lsqb;</mo>
<mi>m</mi>
<mfrac>
<mn>1</mn>
<mn>128</mn>
</mfrac>
<msub>
<mover>
<mi>S</mi>
<mo>~</mo>
</mover>
<mi>a</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<mo>-</mo>
<mi>n</mi>
<mfrac>
<msup>
<mrow>
<mo>&lsqb;</mo>
<msub>
<mover>
<mi>S</mi>
<mo>~</mo>
</mover>
<mi>a</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
<mo>&rsqb;</mo>
</mrow>
<mn>2</mn>
</msup>
<mn>256</mn>
</mfrac>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mfrac>
<mrow>
<msub>
<mover>
<mi>S</mi>
<mo>~</mo>
</mover>
<mi>a</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mi>S</mi>
<mi>a</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>+</mo>
<mn>1</mn>
<mo>&rsqb;</mo>
</mrow>
<mfrac>
<mn>229</mn>
<mn>248</mn>
</mfrac>
</msup>
</mrow>
In formula, Ba(m, n) is a-th of color spectral coverage spatial variations gain function,For a-th of face of coordinate position (m, n)
Value after the brightness normalization of chromatogram section, byPhenogram is as the size of contrast on border, Sa(m, n) denotation coordination position
The brightness value of (m, n) a-th of color spectral coverage is put, m and n represent haze ambient image abscissa value and ordinate value respectively.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710380740.6A CN107195021A (en) | 2017-05-25 | 2017-05-25 | The drive recorder of haze interference |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710380740.6A CN107195021A (en) | 2017-05-25 | 2017-05-25 | The drive recorder of haze interference |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107195021A true CN107195021A (en) | 2017-09-22 |
Family
ID=59874475
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710380740.6A Pending CN107195021A (en) | 2017-05-25 | 2017-05-25 | The drive recorder of haze interference |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107195021A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113419257A (en) * | 2021-06-29 | 2021-09-21 | 深圳市路卓科技有限公司 | Positioning calibration method, device, terminal equipment, storage medium and program product |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102014243A (en) * | 2010-12-27 | 2011-04-13 | 杭州华三通信技术有限公司 | Method and device for enhancing images |
CN104065926A (en) * | 2014-06-25 | 2014-09-24 | 中国移动通信集团广东有限公司 | Image enhancement method and system based on wireless high-definition video monitor system |
CN205498761U (en) * | 2016-04-06 | 2016-08-24 | 河南理工大学 | On -vehicle haze detects early warning device |
CN205647815U (en) * | 2016-05-12 | 2016-10-12 | 浙江警察学院 | Self -adaptation haze response monitored control system |
CN107219850A (en) * | 2017-05-25 | 2017-09-29 | 深圳众厉电力科技有限公司 | A kind of automatic Pathfinding system of robot based on machine vision |
CN107220495A (en) * | 2017-05-25 | 2017-09-29 | 上海为然环保科技有限公司 | A kind of health and fitness information analysis system based on medical imaging enhancement |
CN107369210A (en) * | 2017-08-16 | 2017-11-21 | 李松 | A kind of vehicle maintenance and maintenance enterprise VR panorama planning and designing methods |
-
2017
- 2017-05-25 CN CN201710380740.6A patent/CN107195021A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102014243A (en) * | 2010-12-27 | 2011-04-13 | 杭州华三通信技术有限公司 | Method and device for enhancing images |
CN104065926A (en) * | 2014-06-25 | 2014-09-24 | 中国移动通信集团广东有限公司 | Image enhancement method and system based on wireless high-definition video monitor system |
CN205498761U (en) * | 2016-04-06 | 2016-08-24 | 河南理工大学 | On -vehicle haze detects early warning device |
CN205647815U (en) * | 2016-05-12 | 2016-10-12 | 浙江警察学院 | Self -adaptation haze response monitored control system |
CN107219850A (en) * | 2017-05-25 | 2017-09-29 | 深圳众厉电力科技有限公司 | A kind of automatic Pathfinding system of robot based on machine vision |
CN107220495A (en) * | 2017-05-25 | 2017-09-29 | 上海为然环保科技有限公司 | A kind of health and fitness information analysis system based on medical imaging enhancement |
CN107369210A (en) * | 2017-08-16 | 2017-11-21 | 李松 | A kind of vehicle maintenance and maintenance enterprise VR panorama planning and designing methods |
Non-Patent Citations (2)
Title |
---|
赵晓霞: "基于RETINEX理论的视频图像增强系统研究", 《中国博士学位论文全文数据库信息科技辑》 * |
陈炳权: "车载视频图像处理算法的优化与融合研究", 《中国博士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113419257A (en) * | 2021-06-29 | 2021-09-21 | 深圳市路卓科技有限公司 | Positioning calibration method, device, terminal equipment, storage medium and program product |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110009561B (en) | Method and system for mapping surveillance video target to three-dimensional geographic scene model | |
CN110909666B (en) | Night vehicle detection method based on improved YOLOv3 convolutional neural network | |
CN102722868B (en) | Tone mapping method for high dynamic range image | |
CN103020920B (en) | Method for enhancing low-illumination images | |
CN103034983B (en) | A kind of defogging method capable based on anisotropic filtering | |
CN104683767A (en) | Fog penetrating image generation method and device | |
CN102665034A (en) | Night effect removal method for camera-collected video | |
CN104809461A (en) | License plate recognition method and system combining sequence image super-resolution reconstruction | |
CN112949633A (en) | Improved YOLOv 3-based infrared target detection method | |
CN103914820A (en) | Image haze removal method and system based on image layer enhancement | |
CN114898125B (en) | Wheel axle identification method and system based on light field imaging technology and storage medium | |
CN107219850A (en) | A kind of automatic Pathfinding system of robot based on machine vision | |
CN113537211B (en) | Asymmetric IOU-based deep learning license plate frame positioning method | |
CN112560701B (en) | Face image extraction method and device and computer storage medium | |
CN107833182A (en) | The infrared image super resolution ratio reconstruction method of feature based extraction | |
CN109272014B (en) | Image classification method based on distortion adaptive convolutional neural network | |
CN105513025A (en) | Improved rapid demisting method | |
CN115331183A (en) | Improved YOLOv5s infrared target detection method | |
CN102999890A (en) | Method for dynamically calibrating image light intensity on basis of environmental factors | |
CN101739667A (en) | Non-downsampling contourlet transformation-based method for enhancing remote sensing image road | |
CN102254306B (en) | Real-time image defogging method based on image simplified hierachical model | |
CN107195021A (en) | The drive recorder of haze interference | |
CN114387346A (en) | Image recognition and prediction model processing method, three-dimensional modeling method and device | |
WO2024067732A1 (en) | Neural network model training method, vehicle view generation method, and vehicle | |
CN105303544A (en) | Video splicing method based on minimum boundary distance |
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 |
Application publication date: 20170922 |
|
RJ01 | Rejection of invention patent application after publication |