CN104751138A - Vehicle mounted infrared image colorizing assistant driving system - Google Patents
Vehicle mounted infrared image colorizing assistant driving system Download PDFInfo
- Publication number
- CN104751138A CN104751138A CN201510141721.9A CN201510141721A CN104751138A CN 104751138 A CN104751138 A CN 104751138A CN 201510141721 A CN201510141721 A CN 201510141721A CN 104751138 A CN104751138 A CN 104751138A
- Authority
- CN
- China
- Prior art keywords
- infrared image
- infrared
- image
- digital processing
- vehicle
- 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.)
- Granted
Links
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a vehicle mounted infrared image colorizing assistant driving system comprising an infrared thermal imaging device mounted on a vehicle. The device is connected to a digital processing unit mounted on the vehicle and acquires infrared images in real time to transmit to the digital processing unit, and infrared images are processed through the digital processing unit before being displayed through a display unit of the vehicle. According to the system, an infrared image colorizing scheme in a night vision environment is provided, the problem that pure infrared gray images are difficult to recognize in the prior art is overcome, the ability of a driver acquiring road information at night is improved, an important reference is provided for night driving, and the traffic accidents can be reduced greatly.
Description
Technical field
The present invention relates to a kind of colorize system of vehicle mounted infrared night vision DAS (Driver Assistant System), particularly vehicle mounted infrared night vision image.
Background technology
Along with the strengthening day by day of the fast development of automobile market and security protection consciousness, the requirement of people to automotive safety safeguards technique is more and more higher, and vehicle mounted infrared auxiliary drive system also slowly enters our life.It can obtain the infrared image of the scenes such as the trees building in road and roadside at night, but infrared image does not have colour, is a gray level image and shadow-free, and contrast is low, therefore for human eye, resolution is low, and visual effect is fuzzy.The color levels can differentiated due to human eye is the hundred times of gray shade scale, therefore, if by vehicle mounted infrared image colorization, will greatly improve the visual analysis effect of image, help driver to make rapidly correct understanding and judgement to picture material, and then improve night running safety.
Summary of the invention
The object of this invention is to provide a kind of can by the system of vehicle mounted infrared image colorization.
In order to achieve the above object, technical scheme of the present invention there is provided a kind of vehicle mounted infrared image colorization DAS (Driver Assistant System), comprise the infrared thermal imaging device be loaded on vehicle body, this infrared thermal imaging device is connected with the digital processing element be loaded on vehicle body, digital processing element is transferred to by after infrared thermal imaging device Real-time Collection infrared image, infrared image after digital processing element process is by the display unit display on vehicle body, it is characterized in that, digital processing element is handled as follows the infrared image received:
Step 1, Image semantic classification is carried out to infrared image, while removing the noise on infrared image, increase the contrast of infrared image;
Step 2, utilize watershed algorithm to carry out background segment to pretreated infrared image, the background segment of infrared image is become zones of different, utilizes the distinctive texture information in each region to give corresponding region by the color of correspondence;
Step 3, the object having a higher heat are positioned at the prospect of infrared image, process the prospect of infrared image, the object detection having higher heat is out given the color specifically with warning function by principle afterwards that utilize statistics with histogram to combine with dynamic threshold;
Step 4, background and prospect are all composed coloured colorize infrared image shown by display unit.
Preferably, in described step 2, watershed algorithm is utilized to the concrete steps that pretreated infrared image carries out background segment to be:
Step 2.1, utilize priori to remove the irrelevant marginal information of infrared image, infrared image background content be divided into following three regions, the above be sky areas, be below region, road surface, the right and left is trees regions;
Step 2.2, watershed algorithm is utilized to calculate regional, the computation process of water ridge algorithm is an iteration annotation process, concrete steps are: first sort from low to high to the gray level of pixel each in each region, then realize flooding in process from low to high, adopt first in first out structure judge and mark each local minimum in the domain of influence of h rank height.
Preferably, in described step 3, the object detection concrete steps out having higher heat are by the principle utilizing statistics with histogram to combine with dynamic threshold:
Step 3.1, set an initial threshold according to priori, give dynamic threshold variable by this initial threshold, the first frame infrared image is set to present frame infrared image;
Step 3.2, with dynamic threshold variable, binary conversion treatment is carried out to present frame infrared image, pixel higher than threshold value is referred to as the coordinate range of pedestrian, meanwhile, present frame infrared image is carried out to the statistics with histogram of gray scale, find the gray-scale value that the frequency of occurrences is maximum, give dynamic threshold variable using it as new threshold value;
Step 3.3, next frame infrared image is set to present frame infrared image after, return step 3.2 and re-execute, until all infrared images are all disposed.
Compared with prior art, the invention has the beneficial effects as follows provide a kind of under overnight sight by the scheme of infrared image colorize, infrared hybrid optical system simple before compensate for is difficult to the difficulty distinguished, enhancing driver obtains road information ability at night, is the important reference of nighttime driving.The incidence of vehicle at night accident can be reduced greatly.
Accompanying drawing explanation
Fig. 1 is system framework figure provided by the invention;
Fig. 2 is colorize algorithm flow chart of the present invention.
Embodiment
For making the present invention become apparent, hereby with preferred embodiment, and accompanying drawing is coordinated to be described in detail below.
A kind of vehicle mounted infrared auxiliary drive system fundamental purpose provided by the invention is the security improving running car, obtained the information of vehicle, condition of road surface and pedestrian's situation by the infrared camera be arranged on vehicle, the colorize result figure that native system finally realizes is that driver provides effective information.
As shown in Figure 1, system architecture provided by the invention mainly comprises: FLIRA615 on-vehicle night vision instrument, digital processing unit DSP DM642, Vehicular screen, power supply etc.
The image capture module utilizing FLIR A615 infrared thermography and DSP DM642 to form carries out real-time image acquisition, and data are uploaded to DSPDM642 by Transmission Control Protocol and twisted-pair feeder by data fast that collect.DSP DM642 is a new generation of TI company is the chip that field of video applications designs specially, and its powerful computing power becomes the first-selection of various video process application with equipment in abundant sheet.
By DSP DM642 processing unit, Image semantic classification is carried out to collected infrared picture after collection, utilize the noise etc. on the method removal infrared image of image filtering, strengthen the contrast of infrared image simultaneously.Utilize the colorize algorithm based on Iamge Segmentation after the pre-service obtained, the process flow diagram of algorithm as shown in Figure 2.
First this algorithm needs the segmentation and the colorize that background image are carried out to background.Partitioning algorithm is based on the watershed segmentation methods of mathematical morphology, it is a kind of very outstanding and cutting techniques be widely applied, in essence, it belongs to a kind of dividing method increased based on region, but the border of target that what it obtained is, and be continuously, the closed but border that pixel is wide.For eliminating the over-segmentation that watershed algorithm produces, we utilize priori to remove irrelevant marginal information.Image content is divided into following three major types, the above be sky, be below road surface, the right and left be tree.The computation process of watershed divide is an iteration annotation process.This algorithm divides two steps, and one is sequencer procedure, and one is the process of flooding.First the gray level of each pixel is sorted from low to high, then realize flooding in process from low to high, adopt first in first out structure judge and mark each local minimum in the domain of influence of h rank height.Different colors is given to each several part of image background after Iamge Segmentation is complete.
Secondly algorithm processes the prospect of infrared image.Due to pedestrian, the higher gray-scale value on image of animal equitemperature is comparatively large, uses the Target Recognition Algorithms based on statistics with histogram.Its ultimate principle is added up the frequency of occurrences of 256 gray levels.An initial threshold is set according to priori.With this threshold process first two field picture, namely binary conversion treatment is carried out to image.Meanwhile carry out the statistics with histogram of gray scale, find the gray-scale value that the frequency of occurrences is maximum, give dynamic threshold variable using it as new threshold value.This dynamic threshold just can be utilized afterwards to carry out binaryzation to image, and the pixel higher than threshold value is referred to as the coordinate range of pedestrian, improves the arithmetic speed of algorithm.
New threshold value processes as the threshold value of next frame new images, and continuation said method upgrades new threshold value simultaneously.Circular treatment like this.When the advantage of this algorithm can be saved and calculate dynamic threshold, first to the process of all pixels of global image, and the binarization segmentation after statistics is put into, improve the real-time performance of system.
Then find the coordinate range of pedestrian in the image after watershed segmentation, give colored, the prospect of infrared images whole like this and background after being all combined into piece image by colorize export entire image.Just abundant road information can be provided when night, road was dim to driver.
Claims (3)
1. a vehicle mounted infrared image colorization DAS (Driver Assistant System), comprise the infrared thermal imaging device be loaded on vehicle body, this infrared thermal imaging device is connected with the digital processing element be loaded on vehicle body, digital processing element is transferred to by after infrared thermal imaging device Real-time Collection infrared image, infrared image after digital processing element process is by the display unit display on vehicle body, it is characterized in that, digital processing element is handled as follows the infrared image received:
Step 1, Image semantic classification is carried out to infrared image, while removing the noise on infrared image, increase the contrast of infrared image;
Step 2, utilize watershed algorithm to carry out background segment to pretreated infrared image, the background segment of infrared image is become zones of different, utilizes the distinctive texture information in each region to give corresponding region by the color of correspondence;
Step 3, the object having a higher heat are positioned at the prospect of infrared image, process the prospect of infrared image, the object detection having higher heat is out given the color specifically with warning function by principle afterwards that utilize statistics with histogram to combine with dynamic threshold;
Step 4, background and prospect are all composed coloured colorize infrared image shown by display unit.
2. a kind of vehicle mounted infrared image colorization DAS (Driver Assistant System) as claimed in claim 1, is characterized in that, in described step 2, utilizes watershed algorithm to the concrete steps that pretreated infrared image carries out background segment to be:
Step 2.1, utilize priori to remove the irrelevant marginal information of infrared image, infrared image background content be divided into following three regions, the above be sky areas, be below region, road surface, the right and left is trees regions;
Step 2.2, watershed algorithm is utilized to calculate regional, the computation process of water ridge algorithm is an iteration annotation process, concrete steps are: first sort from low to high to the gray level of pixel each in each region, then realize flooding in process from low to high, adopt first in first out structure judge and mark each local minimum in the domain of influence of h rank height.
3. a kind of vehicle mounted infrared image colorization DAS (Driver Assistant System) as claimed in claim 1, is characterized in that, in described step 3, the object detection concrete steps out having higher heat are by the principle utilizing statistics with histogram to combine with dynamic threshold:
Step 3.1, set an initial threshold according to priori, give dynamic threshold variable by this initial threshold, the first frame infrared image is set to present frame infrared image;
Step 3.2, with dynamic threshold variable, binary conversion treatment is carried out to present frame infrared image, pixel higher than threshold value is referred to as the coordinate range of pedestrian, meanwhile, present frame infrared image is carried out to the statistics with histogram of gray scale, find the gray-scale value that the frequency of occurrences is maximum, give dynamic threshold variable using it as new threshold value;
Step 3.3, next frame infrared image is set to present frame infrared image after, return step 3.2 and re-execute, until all infrared images are all disposed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510141721.9A CN104751138B (en) | 2015-03-27 | 2015-03-27 | A kind of vehicle mounted infrared image colorization DAS (Driver Assistant System) |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510141721.9A CN104751138B (en) | 2015-03-27 | 2015-03-27 | A kind of vehicle mounted infrared image colorization DAS (Driver Assistant System) |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104751138A true CN104751138A (en) | 2015-07-01 |
| CN104751138B CN104751138B (en) | 2018-02-23 |
Family
ID=53590795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510141721.9A Expired - Fee Related CN104751138B (en) | 2015-03-27 | 2015-03-27 | A kind of vehicle mounted infrared image colorization DAS (Driver Assistant System) |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104751138B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105787906A (en) * | 2016-03-25 | 2016-07-20 | 北京环境特性研究所 | Method and system for rejecting bright noises from infrared image |
| CN108566523A (en) * | 2018-05-16 | 2018-09-21 | 深圳市科纳实业有限公司 | A kind of vehicle-mounted obstacle identification optical projection system |
| CN112233023A (en) * | 2020-09-27 | 2021-01-15 | 轩辕智驾科技（深圳）有限公司 | Vehicle-mounted infrared camera and dimming method and device thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101286239A (en) * | 2008-04-22 | 2008-10-15 | 北京航空航天大学 | Aerial shooting traffic video frequency vehicle rapid checking method |
| CN201325373Y (en) * | 2008-12-16 | 2009-10-14 | 武汉高德红外股份有限公司 | Driven infravision automotive auxiliary driving system based on image intelligent treatment |
| US7672481B2 (en) * | 2004-11-30 | 2010-03-02 | Honda Motor Co., Ltd. | Image information processing system, image information processing method, image information processing program, and automobile |
| CN102840853A (en) * | 2012-07-25 | 2012-12-26 | 中国航空工业集团公司洛阳电光设备研究所 | Obstacle detection and alarm method for vehicle-mounted night vision system |
| CN103310006A (en) * | 2013-06-28 | 2013-09-18 | 电子科技大学 | ROI extraction method in auxiliary vehicle driving system |
-
2015
- 2015-03-27 CN CN201510141721.9A patent/CN104751138B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7672481B2 (en) * | 2004-11-30 | 2010-03-02 | Honda Motor Co., Ltd. | Image information processing system, image information processing method, image information processing program, and automobile |
| CN101286239A (en) * | 2008-04-22 | 2008-10-15 | 北京航空航天大学 | Aerial shooting traffic video frequency vehicle rapid checking method |
| CN201325373Y (en) * | 2008-12-16 | 2009-10-14 | 武汉高德红外股份有限公司 | Driven infravision automotive auxiliary driving system based on image intelligent treatment |
| CN102840853A (en) * | 2012-07-25 | 2012-12-26 | 中国航空工业集团公司洛阳电光设备研究所 | Obstacle detection and alarm method for vehicle-mounted night vision system |
| CN103310006A (en) * | 2013-06-28 | 2013-09-18 | 电子科技大学 | ROI extraction method in auxiliary vehicle driving system |
Non-Patent Citations (4)
| Title |
|---|
| SUN SHAO-YUAN: "Color Estimation for Thermal Infrared Imagery Based on Kernel PCA and Sparse Representation", 《JOURNAL OF DONGHUA UNIVERSITY》 * |
| 苏晓倩 等: "《车载红外图像的行人检测与跟踪技术》", 《激光与红外》 * |
| 范德营 等: "车载红外视频图像快速彩色化技术研究", 《华东交通大学学报》 * |
| 许真 等: "基于纹理特征库的微光图像色彩纹理传递", 《红外技术》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105787906A (en) * | 2016-03-25 | 2016-07-20 | 北京环境特性研究所 | Method and system for rejecting bright noises from infrared image |
| CN108566523A (en) * | 2018-05-16 | 2018-09-21 | 深圳市科纳实业有限公司 | A kind of vehicle-mounted obstacle identification optical projection system |
| CN112233023A (en) * | 2020-09-27 | 2021-01-15 | 轩辕智驾科技（深圳）有限公司 | Vehicle-mounted infrared camera and dimming method and device thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104751138B (en) | 2018-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101783076B (en) | Method for quick vehicle type recognition under video monitoring mode | |
| CN101739827B (en) | Vehicle detecting and tracking method and device | |
| CN102938057B (en) | A kind of method for eliminating vehicle shadow and device | |
| TWI607901B (en) | Image inpainting system area and method using the same | |
| CN107862290A (en) | Method for detecting lane lines and system | |
| CN104657735A (en) | Lane line detection method and system, as well as lane departure early warning method and system | |
| CN111369541A (en) | Vehicle detection method for intelligent automobile under severe weather condition | |
| CN103034843B (en) | Method for detecting vehicle at night based on monocular vision | |
| CN202134079U (en) | Unmanned vehicle lane marker line identification and alarm device | |
| CN112215306A (en) | Target detection method based on fusion of monocular vision and millimeter wave radar | |
| CN104881661B (en) | Vehicle checking method based on structural similarity | |
| CN103020914A (en) | Rapid image defogging method based on spatial continuity principle | |
| CN110450706A (en) | A kind of adaptive distance light lamp control system and image processing algorithm | |
| CN115311241B (en) | Underground coal mine pedestrian detection method based on image fusion and feature enhancement | |
| CN104616258A (en) | Rapid defogging method for road image | |
| CN104766071A (en) | Rapid traffic light detection algorithm applied to pilotless automobile | |
| CN104992160B (en) | A kind of heavy truck night front vehicles detection method | |
| Cheng et al. | Visibility enhancement of single hazy images using hybrid dark channel prior | |
| Mandal et al. | Real-time automotive night-vision system for drivers to inhibit headlight glare of the oncoming vehicles and enhance road visibility | |
| CN103020930A (en) | Nighttime monitoring video enhancing method | |
| CN104751138B (en) | A kind of vehicle mounted infrared image colorization DAS (Driver Assistant System) | |
| CN104822055A (en) | Infrared thermal image monitoring system against fog days and method | |
| Hautiere et al. | Meteorological conditions processing for vision-based traffic monitoring | |
| CN105787456A (en) | Method for detecting pedestrians in night far infrared images | |
| CN103065145A (en) | Vehicle movement shadow eliminating method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180223 Termination date: 20210327 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |