CN105744156A - System and method for improving object identification in image - Google Patents
System and method for improving object identification in image Download PDFInfo
- Publication number
- CN105744156A CN105744156A CN201610066335.2A CN201610066335A CN105744156A CN 105744156 A CN105744156 A CN 105744156A CN 201610066335 A CN201610066335 A CN 201610066335A CN 105744156 A CN105744156 A CN 105744156A
- Authority
- CN
- China
- Prior art keywords
- frame image
- present frame
- image
- data set
- exposed
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/73—Circuitry for compensating brightness variation in the scene by influencing the exposure time
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/62—Control of parameters via user interfaces
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Image Input (AREA)
Abstract
The invention is suitable for the field of traffic safety early-warning systems, and provides a system for improving object identification in an image. The system comprises a camera module, an image acquisition module, an image analysis module and a control module. The camera module shoots all objects in front of the current car to obtain a first current frame image. The image acquisition module obtains the first current frame image. The image analysis module analyzes the first current frame image and computes the overexposure or underexposure degree of the first current frame image. The control module adjusts exposure parameters of the camera module according to the overexposure or underexposure degree. The camera module shoots again according to the adjusted exposure parameters in order to obtain a second current frame image. The image acquisition module obtains the second current frame image. The image analysis module analyzes the second current frame image and computes all objects of the second current frame image to establish a data set of all the objects. The data set of all the objects can be used for analytical calculation of traffic safety early-warning. The invention also provides a method for improving object identification in the image.
Description
Technical field
The invention belongs to traffic safety early warning system field, particularly relate to a kind of raising and image improves in the system of object identification the system and method for object identification in image.
Background technology
A large amount of along with private car popularize, and increasing vehicle on the way travels, and the complexity of road is also increasingly severe, and traffic safety has just become an important problem.The system of object identification in image that improves being now based on vision is method most effective, safest.The system of object identification in image that improves yet with view-based access control model is easily subject to the impact of surrounding light intensity.If light is too dark, the image exposure captured by photographic head is not enough, and the color of the object in the image of shooting differs too little with the color of background, causes that improving the system of object identification in image is difficult to identify whole objects in Current vehicle front.If light is too strong, the image exposure captured by photographic head is excessive, and the system of object identification in raising image that also results in is difficult to identify whole objects in Current vehicle front.Although the light intensity of surrounding is normal sometimes, but the Some vehicles in Current vehicle front is by the shadow occlusion of building (such as overpass), so the system of object identification in raising image that still results in is difficult to identify whole objects in Current vehicle front.Therefore in above-mentioned multiple situation, how all can effectively recognize whole objects in Current vehicle front, reformed into problem demanding prompt solution.
Summary of the invention
The technical problem to be solved is in that providing a kind of improves the system and method for object identification in image, it is intended to can effectively identify whole objects in Current vehicle front.
The present invention is achieved in that and a kind of improves the system of object identification in image, and it includes photographing module, image acquiring module, image analysing computer module and controls module.This photographing module is for shooting whole objects in a Current vehicle front, to obtain a first present frame image.This image acquiring module is used for obtaining this first present frame image.This image analysing computer module, for being exposed this first present frame image analyzing, if to belong to overall exposing abnormal for this first present frame image, then calculate this first present frame image overexposure or owes the degree exposed.This control module adjusts the exposure parameter of this photographing module according to this first present frame image overexposure or the deficient degree exposed.This photographing module shoots whole objects in this Current vehicle front again according to the exposure parameter after adjusting, to obtain the second present frame image.This image acquiring module is used for obtaining this second present frame image.This image analysing computer module is additionally operable to be exposed this second present frame image analyzing, if this second present frame image overall exposing is normal, then it is analyzed the whole objects in this second present frame image calculating, to build entire object volumetric data set so that the security early-warning analysis module in a traffic safety early warning system can carry out the analytical calculation of traffic safety early warning according to this entire object volumetric data set.
Present invention also offers and a kind of improve the method for object identification in image, its whole objects comprising the steps: to use one Current vehicle front of a photographing module shooting, to obtain a first present frame image；Obtain this first present frame image；It is exposed this first present frame image analyzing；If it is abnormal that this first present frame image belongs to overall exposing, then calculate this first present frame image entirety overexposure or owe the degree exposed；The exposure parameter of this photographing module is adjusted according to this first present frame image entirety overexposure or the deficient degree exposed；This photographing module shoots whole objects in this Current vehicle front again according to the exposure parameter after adjusting, and obtains a second present frame image；It is exposed this second present frame image analyzing；If it is normal that this second present frame image belongs to overall exposing, then being analyzed the whole objects in this second present frame image calculating, to build entire object volumetric data set, this entire object volumetric data set can be used the analytical calculation of traffic safety early warning.
The present invention compared with prior art, has the beneficial effects that: the present invention improves the system and method for object identification in image, it is possible to effectively identify whole objects in Current vehicle front, better driver to be protected.
Accompanying drawing explanation
Fig. 1 is the functional block diagram of the system of object identification in the raising image that present pre-ferred embodiments provides.
Fig. 2 and Fig. 3 is the flow chart of the method for object identification in the raising image that present pre-ferred embodiments provides.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein is only in order to explain the present invention, is not intended to limit the present invention.
As it is shown in figure 1, a kind of system 100 improving object identification in image that present pre-ferred embodiments provides, it includes photographing module 101, image acquiring module 10, image analysing computer module 20 and controls module 30.
This photographing module 101 is for shooting whole objects in a Current vehicle front, to obtain a first present frame image.In the present embodiment, this photographing module 101 is a video camera.
This image acquiring module 10 is used for obtaining this first present frame image.
This image analysing computer module 20 electrically connects with this image acquiring module 10; for being exposed this first present frame image analyzing; to judge that this first present frame image exposure normally still exposes abnormal (namely over-exposed or under-exposed, to be called for short overexposure or owe to expose).If this first present frame image exposure is normal, then the whole objects in this first present frame image are directly analyzed calculating by this image analysing computer module 20, to build entire object volumetric data set.This entire object volumetric data set can be used the analytical calculation of traffic safety early warning.
If the exposure of this first current image is abnormal, then this image analysing computer module 20 judges that this first present frame image belongs to that overall exposing is abnormal or subregion exposure is abnormal.If it is abnormal that this first present frame image belongs to overall exposing, then this image analysing computer module 20 calculates this first present frame image entirety overexposure or owes the degree exposed.If this first present frame image belongs to subregion, exposure is abnormal, then this image analysing computer module 20 calculates the overexposure exposing abnormal region in this first present frame image or owes the degree exposed, and be analyzed calculating to the object exposing normal region in this first present frame image, build the object data set D1 of Part I.In the present embodiment, all points in this first present frame image are carried out analytical calculation by gray scale or histogrammic mode by this image analysing computer module 20, to be exposed this first present frame image analyzing.
This image analysing computer module 20 is additionally operable to send control signal to this control module 30 according to this first present frame image region overexposure in whole or in part or the deficient degree exposed.This control module 30 electrically connects with this image analysing computer module 20, for the control signal according to this image analysing computer module 20, the exposure parameter of this photographing module 101 is adjusted.
Concrete, (1) if this first present frame image entirety overexposure, then this control module 30 adjusts the exposure parameters such as aperture and the time of exposure of this photographing module 101, to reduce light-inletting quantity；(2) if this first present frame image entirety owes to expose, then this control module 30 adjusts the exposure parameters such as aperture and the time of exposure of this photographing module 101, to improve light-inletting quantity；(3) if the subregion overexposure in this first present frame image, then this control module 30 adjusts the exposure parameters such as aperture and the time of exposure of this photographing module 101, to reduce light-inletting quantity, before so causing, the regional exposure of overexposure is normal, and the region of normal exposure is then under-exposed before；(4) if the subregion in this first present frame image owes to expose, then this control module 30 adjusts the exposure parameters such as aperture and the time of exposure of this photographing module 101, to improve light-inletting quantity, the regional exposure owing before to expose so being caused normal, the region of normal exposure is then over-exposed before.
This photographing module 101 shoots whole objects in this Current vehicle front again according to the exposure parameter after the adjustment of this control module 30, to obtain the second present frame image.
This image acquiring module 10 is additionally operable to obtain this second present frame image.
Concrete, for the abnormal first present frame image of overall exposing, after adjusting exposure parameter, this second present frame image overall exposing is normal；Abnormal first present frame image is exposed for subregion, after adjusting exposure parameter, this the first present frame image exposes abnormal region in the second present frame image, becomes exposure normal region, this first present frame image exposes normal region in the second present frame image, becomes the abnormal region of exposure.
This image analysing computer module 20 is additionally operable to be exposed this second present frame image analyzing, to judge that this second present frame image is that overall exposing is normal or subregion exposure is normal.This image analysing computer module 20 is additionally operable to build entire object volumetric data set.
Concrete, if to be overall exposing normal for this second present frame image, then the whole objects in this second present frame image are analyzed calculating by this image analysing computer module 20, to build entire object volumetric data set.This entire object volumetric data set can be used the analytical calculation of traffic safety early warning.
If this second present frame image is subregion, exposure is normal, then this image analysing computer module 20 is analyzed calculating to exposing the object in normal region in this second present frame image, build the object data set D2 of Part II, then adopting and be added with the object data set D2 of this Part II by the object data set D1 of this Part I, namely the mode of D1+D2 obtains entire object volumetric data set.This entire object volumetric data set can be used the analytical calculation of traffic safety early warning.
As shown in Figures 2 and 3, what present pre-ferred embodiments provided a kind of improves the method for object identification in image, and it comprises the steps:
S0: utilize a photographing module (such as video camera) to shoot whole objects in a Current vehicle front, to obtain a first present frame image.
S1: obtain this first present frame image.
S2: be exposed this first present frame image analyzing, to judge that this first present frame image exposure normally still exposes abnormal (namely over-exposed or under-exposed, to be called for short overexposure or owe to expose).
S3: if this first present frame image exposure is normal, then be analyzed the whole objects in this first present frame image calculating, and to build entire object volumetric data set, this entire object volumetric data set can be used the analytical calculation of traffic safety early warning.
S4: if this first present frame image exposure is abnormal, then judge that this first present frame image belongs to that overall exposing is abnormal or subregion exposure is abnormal.
S5: if to belong to overall exposing abnormal for this first present frame image, then calculate this first present frame image entirety overexposure or owe the degree exposed.
S6: adjust the exposure parameter of this photographing module according to this first present frame image entirety overexposure or the deficient degree exposed, control this photographing module and again take pictures, obtain a second present frame image, then proceed to step S9.
S7: exposure is abnormal if this first present frame image belongs to subregion, then calculate the exposure abnormal region overexposure in this first present frame image or owe the degree exposed, and be analyzed calculating to the object exposing normal region in this first present frame image, build the object data set D1 of Part I.
S8: adjust the exposure parameter of this photographing module according to the degree exposing abnormal region overexposure or deficient exposure in this first present frame image, control this photographing module and again shoot whole objects in this Current vehicle front, obtain a second present frame image, then proceed to step S9.
S9: obtain this second present frame image from this photographing module.
S10: be exposed this second present frame image analyzing is normal to judge that this second present frame image belongs to the normal still subregion exposure of overall exposing.
S11: if this second present frame image belongs to overall exposing normally, then being analyzed the whole objects in this second present frame image calculating, to build entire object volumetric data set, this entire object volumetric data set can be used the analytical calculation of traffic safety early warning.
S12: exposure is normal if this second present frame image is subregion, then be analyzed calculating to exposing the object in normal region in this second present frame image, build the object data set D2 of Part II.
S13: adopting and be added with the object data set D2 of this Part II by the object data set D1 of this Part I, namely the mode of D1+D2 builds entire object volumetric data set, and this entire object volumetric data set can be used the analytical calculation of traffic safety early warning.
Compared with prior art, the system and method for object identification in the raising image of the present invention, it is possible to effectively identify whole objects in Current vehicle front, better driver to be protected.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all any amendment, equivalent replacement and improvement etc. made within the spirit and principles in the present invention, should be included within protection scope of the present invention.
Claims (10)
1. improving a system for object identification in image, it includes photographing module, image acquiring module, image analysing computer module and controls module, and this photographing module is for shooting whole objects in a Current vehicle front, to obtain a first present frame image；This image acquiring module is used for obtaining this first present frame image, this image analysing computer module is for being exposed this first present frame image analyzing, if it is abnormal that this first present frame image belongs to overall exposing, then calculate this first present frame image overexposure or owe the degree exposed；This control module adjusts the exposure parameter of this photographing module according to this first present frame image overexposure or the deficient degree exposed；This photographing module shoots whole objects in this Current vehicle front again according to the exposure parameter after adjusting, to obtain the second present frame image；This image acquiring module is used for obtaining this second present frame image；This image analysing computer module is additionally operable to be exposed this second present frame image analyzing, if this second present frame image overall exposing is normal, then is analyzed the whole objects in this second present frame image calculating, to build entire object volumetric data set；This entire object volumetric data set can be used the analytical calculation of traffic safety early warning.
2. the system of object identification in raising image as claimed in claim 1, it is characterized in that, if this first present frame image entirety overexposure, then this control module adjusts the exposure parameter of this photographing module, to reduce light-inletting quantity, this second present frame image is made to become overall exposing normal；If this first present frame image entirety owes to expose, then this control module adjusts the exposure parameter of this photographing module, to improve light-inletting quantity, makes this second present frame image become overall exposing normal.
3. the system of object identification in raising image as claimed in claim 1, it is characterized in that, if this first present frame image belongs to subregion, exposure is abnormal, then the object exposing normal region in this first present frame image is also analyzed calculating by this image analysing computer module, builds the object data set of Part I；If this second present frame image belongs to subregion, exposure is normal, then this image analysing computer module also is analyzed calculating to exposing the object in normal region in this second present frame image, builds the object data set of Part II；This image analysing computer module adopts and the mode that the object data set of Part I is added with the object data set of Part II is obtained entire object volumetric data set.
4. the system of object identification in raising image as claimed in claim 3, it is characterized in that, if the subregion overexposure in this first present frame image, then this control module adjusts the exposure parameter of this photographing module, to reduce light-inletting quantity, the region of overexposure in this first current frame image is exposed normally in this second current frame image, this first current frame image exposes normal region under-exposed in this second current frame image；If the subregion in this first present frame image owes to expose, then this control module adjusts this photographing module optical parameter, to improve light-inletting quantity, the region owing in this first current frame image to expose is exposed normally in this second current frame image, this first current frame image exposes normal region over-exposed in this second current frame image.
5. the system of object identification in raising image as claimed in claim 1, it is characterized in that, all points in this first present frame image are carried out analytical calculation by gray scale or histogrammic mode by this image analysing computer module, to be exposed this first present frame image analyzing.
6. the system of object identification in raising image as claimed in claim 1, it is characterized in that, if this first present frame image exposure is normal, then the whole objects in this first present frame image are directly analyzed calculating by this image analysing computer module, to build entire object volumetric data set, this entire object volumetric data set can be used the analytical calculation of traffic safety early warning.
7. improving a method for object identification in image, its whole objects comprising the steps: to use one Current vehicle front of a photographing module shooting, to obtain a first present frame image；Obtain this first present frame image；It is exposed this first present frame image analyzing；If it is abnormal that this first present frame image belongs to overall exposing, then calculate this first present frame image entirety overexposure or owe the degree exposed；The exposure parameter of this photographing module is adjusted according to this first present frame image entirety overexposure or the deficient degree exposed；This photographing module shoots whole objects in this Current vehicle front again according to the exposure parameter after adjusting, and obtains a second present frame image；It is exposed this second present frame image analyzing；If it is normal that this second present frame image belongs to overall exposing, then being analyzed the whole objects in this second present frame image calculating, to build entire object volumetric data set, this entire object volumetric data set can be used the analytical calculation of traffic safety early warning.
8. the method for object identification in raising image as claimed in claim 7, it is characterized in that, " if this first present frame image belongs to subregion, exposure is abnormal; then calculates and exposes abnormal region overexposure in this first present frame image or owe the degree exposed; and be analyzed the object exposing normal region in this first present frame image calculating, and builds the object data set of Part I also to include step after step " this first present frame image is exposed analyze "；The exposure parameter of this photographing module is adjusted according to the degree exposing abnormal region overexposure or deficient exposure in this first present frame image；This photographing module shoots whole objects in this Current vehicle front again according to the exposure parameter after adjusting, and obtains a second present frame image；It is exposed this second present frame image analyzing；If this second present frame image belongs to subregion, exposure is normal, then be analyzed calculating to exposing the object in normal region in this second present frame image, build the object data set of Part II；Adopting and the mode that the object data set of Part I is added with the object data set of this Part II is obtained entire object volumetric data set, this entire object volumetric data set can be used the analytical calculation of traffic safety early warning ".
9. the method for object identification in raising image as claimed in claim 7, it is characterized in that, step is also included this first present frame image " if this first present frame image exposure is normal; be then directly analyzed the whole objects in this first present frame image calculating; to build entire object volumetric data set, this entire object volumetric data set can be used the analytical calculation of traffic safety early warning after step " being exposed analyzing ".
10. the method for object identification in raising image as claimed in claim 7, it is characterized in that, all points in this first present frame image and this second present frame image are carried out analytical calculation by gray scale or histogrammic mode by step " being exposed this first present frame image analyzing " and step " being exposed this second present frame image analyzing ", to be exposed this first present frame image and this second present frame image analyzing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610066335.2A CN105744156A (en) | 2016-01-29 | 2016-01-29 | System and method for improving object identification in image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610066335.2A CN105744156A (en) | 2016-01-29 | 2016-01-29 | System and method for improving object identification in image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105744156A true CN105744156A (en) | 2016-07-06 |
Family
ID=56247083
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610066335.2A Pending CN105744156A (en) | 2016-01-29 | 2016-01-29 | System and method for improving object identification in image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105744156A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107786815A (en) * | 2016-08-30 | 2018-03-09 | 比亚迪股份有限公司 | Active night vision adpative exposure method, system and vehicle |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030206241A1 (en) * | 1997-11-21 | 2003-11-06 | Matsushita Electric Industrial Co., Ltd. | Imaging apparatus with dynamic range expanded, a video camera including the same, and a method of generating a dynamic range expanded video signal |
| CN101119439A (en) * | 2007-08-22 | 2008-02-06 | 东风汽车有限公司 | Automatic control method for clear lane image shooting by vehicle-mounted camera |
| CN101483721A (en) * | 2008-01-08 | 2009-07-15 | 华晶科技股份有限公司 | Video processing method and video capturing apparatus applying the method |
| CN101646021A (en) * | 2008-08-08 | 2010-02-10 | 株式会社电装 | Exposure determining device and image processing apparatus |
-
2016
- 2016-01-29 CN CN201610066335.2A patent/CN105744156A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030206241A1 (en) * | 1997-11-21 | 2003-11-06 | Matsushita Electric Industrial Co., Ltd. | Imaging apparatus with dynamic range expanded, a video camera including the same, and a method of generating a dynamic range expanded video signal |
| CN101119439A (en) * | 2007-08-22 | 2008-02-06 | 东风汽车有限公司 | Automatic control method for clear lane image shooting by vehicle-mounted camera |
| CN101483721A (en) * | 2008-01-08 | 2009-07-15 | 华晶科技股份有限公司 | Video processing method and video capturing apparatus applying the method |
| CN101646021A (en) * | 2008-08-08 | 2010-02-10 | 株式会社电装 | Exposure determining device and image processing apparatus |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107786815A (en) * | 2016-08-30 | 2018-03-09 | 比亚迪股份有限公司 | Active night vision adpative exposure method, system and vehicle |
| CN107786815B (en) * | 2016-08-30 | 2020-02-21 | 比亚迪股份有限公司 | Active night vision self-adaptive exposure method and system and vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107358593B (en) | Image forming method and apparatus | |
| WO2017028587A1 (en) | Vehicle monitoring method and apparatus, processor, and image acquisition device | |
| JP5435307B2 (en) | In-vehicle camera device | |
| US7925152B2 (en) | Exposure control method | |
| CN109146906B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| EP3115930A1 (en) | Malfunction diagnosis apparatus | |
| JP2013005234A5 (en) | ||
| CN110231018B (en) | Structured light distance measuring method and device and computer readable storage medium | |
| CN111917991B (en) | Image quality control method, device, equipment and storage medium | |
| US20190139198A1 (en) | Image Optimization Method and Device, and Terminal | |
| CN111881917A (en) | Image preprocessing method and device, computer equipment and readable storage medium | |
| CN112769877A (en) | Group fog early warning method, cloud server, vehicle and medium | |
| CN110199318B (en) | Driver state estimation device and driver state estimation method | |
| CN107343154B (en) | Method, device and system for determining exposure parameters of camera device | |
| CN111626958A (en) | Exposure adjusting method, exposure adjusting device, computer-readable storage medium and electronic equipment | |
| US20120128211A1 (en) | Distance calculation device for vehicle | |
| CN105744156A (en) | System and method for improving object identification in image | |
| CN105049704A (en) | Shooting method and equipment | |
| CN110428411B (en) | Backlight plate detection method and system based on secondary exposure | |
| CN116524877A (en) | Vehicle-mounted screen brightness adjustment method and device, electronic equipment and storage medium | |
| TWI630818B (en) | Dynamic image feature enhancement method and system | |
| CN105721773A (en) | Video acquisition system and method | |
| CN107786815B (en) | Active night vision self-adaptive exposure method and system and vehicle | |
| JP2008112349A (en) | Moving object detection device | |
| CN113723282B (en) | Vehicle driving prompting method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160706 |
|
| RJ01 | Rejection of invention patent application after publication |