CN111027494A - Matrix vehicle lamp identification method based on computer vision - Google Patents
Matrix vehicle lamp identification method based on computer vision Download PDFInfo
- Publication number
- CN111027494A CN111027494A CN201911287058.8A CN201911287058A CN111027494A CN 111027494 A CN111027494 A CN 111027494A CN 201911287058 A CN201911287058 A CN 201911287058A CN 111027494 A CN111027494 A CN 111027494A
- Authority
- CN
- China
- Prior art keywords
- image
- vehicle
- car
- brightness
- lamp
- 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
- 238000000034 method Methods 0.000 title claims abstract description 19
- 239000011159 matrix material Substances 0.000 title claims abstract description 16
- 238000003708 edge detection Methods 0.000 claims abstract description 13
- 238000001514 detection method Methods 0.000 claims description 17
- 238000001914 filtration Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 206010039203 Road traffic accident Diseases 0.000 abstract description 3
- 235000019557 luminance Nutrition 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/10024—Color image
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30236—Traffic on road, railway or crossing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Abstract
The invention provides a matrix vehicle lamp identification method based on computer vision, which comprises the following steps: acquiring road vehicle image video information through a camera; carrying out image binarization processing; carrying out image edge detection; obtaining vehicle lamp distance information; sending the processed distance information to a lower computer; the lower computer adjusts the brightness of the car lamp according to the distance information, and the invention automatically acquires the road vehicle image, analyzes and processes the image, and adjusts the brightness of the car lamp according to the processing result, thereby realizing the automatic adjustment of the car lamp according to the road vehicle condition and preventing traffic accidents.
Description
Technical Field
The invention relates to the technical field of automobile lamps, in particular to a matrix automobile lamp identification method based on computer vision.
Background
With the increasing living standard of people, the automobile is an indispensable vehicle for people to go out. The demand of people for automobiles is increased, and the requirements for driving comfort and functions are also continuously improved. For the aspect of vehicle lamp control, a well-documented driving illumination scheme is needed. At present, most of automobile matrix car light control technologies rely on photosensitive sensors, ultrasonic sensors and the like, only can detect information such as ambient brightness and the like under a large environment around an automobile, and have limited capacity in the aspect of judgment of the information, because a night road image contains a lot of interference information, for example, a street lamp, a reflecting guideboard, reflecting road surface accumulated water and the like can cause interference to the identification of car lights when meeting at night, further vehicle identification requirements cannot be met, and great potential safety hazards are caused.
In order to solve the above technical problems, a method for controlling a high beam during a night meeting is disclosed in a patent document having a chinese patent application No. 201810810013.3 and a bulletin date 2018.12.28, and a system and a computer readable storage medium thereof, wherein the method comprises the steps of: acquiring a road vehicle image; acquiring the brightness value of the HSL image pixel according to the road vehicle image; judging whether the brightness value of the HSL image pixel is within a preset vehicle lamp brightness threshold value range or not, and if so, matching the road vehicle image with a preset image mask; if the matching is successful, acquiring the position information of the road vehicle according to the road vehicle image; and controlling the high beam in the corresponding area to be closed according to the position information of the road vehicle.
However, according to the technical solution disclosed in this document, matching is performed through a road vehicle image and a preset image mask, specifically, through matching luminance values, vehicle lamp adjustment is performed after matching is successful, but since different vehicle luminances are different and there is a deviation in the luminances acquired at different positions, and the luminances of vehicle lamps detected on some roads are also affected by the luminance of one side of a road, it is impossible to truly judge whether the vehicle is closer to the vehicle, and inaccurate control occurs.
Disclosure of Invention
The invention provides a matrix vehicle lamp identification method based on computer vision, which has high vehicle distance identification accuracy, and can adjust the brightness of a vehicle lamp according to the distance between the vehicle lamp and a road vehicle when meeting at night to prevent safety accidents.
In order to achieve the purpose, the matrix vehicle lamp identification method based on computer vision comprises the following steps:
1) acquiring road vehicle image video information through a camera;
2) carrying out image binarization processing on a vehicle image in the vehicle image video information;
3) preprocessing the image: removing image noise through Gaussian filtering to obtain a denoised image;
4) carrying out image edge detection: detecting whether the car light of the target car exists on the image, and if the image after denoising is detected to have two areas with similar sizes and the distance between the two areas is within a threshold range, judging that the car light exists in the image after denoising; if the vehicle lamp exists on the image after denoising is detected, calculating the area of the connected region according to the detection result to obtain the maximum area of the connected region, describing the contour and obtaining the maximum area contour; utilizing Hough circle detection to obtain a maximum closed circle on the maximum area contour; obtaining an ROI rectangular region according to the obtained parameters of the sum radius of the center of the maximum closed circle, and taking the obtained ROI region as a vehicle lamp region to be tracked in the next step;
5) acquiring distance information from a target vehicle: carrying out back projection on the car lamp area identified in the step 4) to obtain a back projection view; performing camshift algorithm iteration according to the obtained reverse projection drawing and the outline of the car lamp, and iteratively outputting the central coordinates of the ROI rectangular region of the next frame of image according to the previous frame of image and the camshift algorithm; obtaining the distance between the distance and the target vehicle through a formula AB = ((X + P2) × F)/K, wherein AB is the distance between the distance and the target vehicle, X is the central coordinate of the previous frame image output, P2 is the central coordinate of the current frame image output, F is a super parameter, and K is an adjusting parameter;
6) sending the processed distance information to a lower computer;
7) the lower computer adjusts the brightness of the car lamp according to the distance information from the target car, and adjusts the voltage of the LED lamp through the output voltage of the control circuit, so that the brightness of the car lamp is adjusted.
According to the arrangement, video information of a road vehicle image is automatically acquired through a camera, binarization processing is carried out on the vehicle image, denoising processing is carried out on the image, edge detection is determined to determine whether vehicle lights exist or not and then outline determination is carried out on the vehicle lights, meanwhile, a maximum closed circle is determined through the edge detection and then a region of interest (ROI) is determined, namely a key region, so that the areas before and after the movement of the vehicle lights are determined, distance information between the two vehicles is determined according to the difference of area parameters, because the detection vehicle and the target vehicle move, the distance between the detection vehicle and the target vehicle can be determined according to the difference of the areas between the previous frame image and the current frame image of the detected vehicle image, the brightness of the detection vehicle is adjusted according to the distance, the safety of driving at night is ensured, and meanwhile, the movement distance determined according to the mode cannot be, the accuracy is high, the maximum closed circle is determined after edge detection, then the ROI is determined, the data processing amount can be saved, and the key information area can be determined through the ROI, so that the accuracy is improved.
Further, the image edge detection of 4) is laplacian image detection. The method is simple and reliable.
Further, the lower computer adjusts the brightness of the car lamp according to the processed distance information, the closer the distance is, the smaller the brightness of the car lamp is, and the situation that the driver of the road vehicle is dazzled due to too high brightness of the car lamp is prevented, so that traffic accidents are avoided. According to the arrangement, the closer the distance is, the higher the brightness is, the more dangerous the distance is, so that the brightness information is adjusted according to the distance information, and the driving safety is ensured when vehicles meet at night.
Further, 7) the lower computer adjusts the brightness of the car lamp according to the distance information, specifically, the lower computer determines the brightness information according to the distance information and the preset relation table between the distance information and the brightness, and the brightness can be adjusted more accurately according to the distance information and the preset relation table between the distance information and the brightness, so that the accuracy of adjusting the brightness of the car lamp is improved.
Further, the image binarization processing of the vehicle image in the step 2) specifically includes: the vehicle image is converted into the RGB color space, then binarization processing is carried out on the RGB color space, the vehicle image is converted into the RGB color space, then binarization processing is carried out, processing is convenient, and processing speed is high.
Drawings
Fig. 1 is a schematic flow chart of a matrix vehicle lamp identification method based on computer vision according to the present invention.
Fig. 2 is a picture after denoising an image according to the matrix vehicle light recognition method based on computer vision.
Fig. 3 is a picture after the edge detection is performed on the image by the matrix vehicle lamp identification method based on computer vision according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
The invention discloses a matrix vehicle lamp identification method based on computer vision, which comprises the following steps as shown in figure 1:
1) acquiring road vehicle image video information through a camera;
2) carrying out image binarization processing on a vehicle image in the vehicle image video information;
3) preprocessing the image: removing image noise through Gaussian filtering to obtain a denoised image;
4) carrying out image edge detection: as shown in fig. 3, detecting whether the car light of the target car exists on the image, and if it is detected that the de-noised image has two regions with similar sizes and the distance between the two regions is within a threshold range, determining that the car light exists in the de-noised image; if the vehicle lamp exists on the image after denoising is detected, calculating the area of the connected region according to the detection result to obtain the maximum area of the connected region, describing the contour and obtaining the maximum area contour; utilizing Hough circle detection to obtain a maximum closed circle on the maximum area contour; obtaining an ROI rectangular region according to the obtained parameters of the center and the radius of the maximum closed circle, and taking the obtained ROI region as a vehicle lamp region to be tracked in the next step; in this embodiment, hough circle transformation in OpenMV is used for hough circle detection.
5) Acquiring distance information from a target vehicle: acquiring distance information from a target vehicle: carrying out back projection on the car lamp area identified in the step 4) to obtain a back projection view; performing camshift algorithm iteration according to the obtained reverse projection drawing and the outline of the car lamp, and iteratively outputting the area S1 of the ROI region of the previous frame image and the area S2 of the ROI rectangular region of the current frame image according to the camshift algorithm; obtaining the distance between the distance and the target vehicle through a formula AB = (S2-S1)/K, wherein AB is the distance between the distance and the target vehicle, and K is an adjusting parameter; the area of the ROI rectangular region can be calculated by determining the center and radius parameters of the maximum closed circle through Hough circle detection, wherein the ROI rectangular region is the maximum inscribed circle of the maximum closed circle, and the area can be obtained through the square of 4 times of the radius parameters due to the determination of the radius parameters of the inscribed circle;
determining the distance between two vehicles after the difference value between the ROI area S1 of the previous frame image and the ROI rectangular area S2 of the current frame image is adjusted;
6) sending the processed distance information to a lower computer;
7) the lower computer adjusts the brightness of the car lamp according to the distance information from the target car, and adjusts the voltage of the LED lamp through the output voltage of the control circuit, so that the brightness of the car lamp is adjusted.
In this embodiment, the image edge detection of 4) is laplacian image detection.
The lower computer adjusts the brightness of the car lamp according to the processed distance information from the target car, the closer the distance from the target car is, the smaller the brightness of the car lamp is, specifically, the brightness information is determined according to the distance information from the target car and a preset relation table between the distance information from the target car and the brightness, the brightness of the car lamp is adjusted according to the distance information from the target car, and the situation that the car lamp brightness is too high to cause dazzling to road vehicle drivers is prevented, so that traffic accidents are caused.
In this embodiment, the image binarization processing on the vehicle image in the step 2) specifically includes: converting the vehicle image into an RGB color space, and then carrying out binarization processing on the RGB color space;
automatically acquiring video information of a road vehicle image through a camera, then carrying out binarization processing on the vehicle image, carrying out denoising processing on the image, then determining whether the edge detection determines that the car light exists or not and then carrying out contour determination on the car light, simultaneously determining a maximum closed circle through the edge detection and then determining an ROI (region of interest) which is a key region, further determining the areas of the lamps before and after movement, then determining the distance information between the two vehicles according to the difference of the area parameters, because the detection vehicle and the target vehicle move, the distance between the detection vehicle and the target vehicle can be determined according to the area difference between the previous frame image and the current frame image of the detected vehicle image, then, the brightness of the detection vehicle is adjusted according to the distance, the safety of driving at night is ensured, meanwhile, the moving distance determined according to the mode cannot be influenced by the brightness of the external environment, and the accuracy is high.
Claims (5)
1. A matrix vehicle lamp identification method based on computer vision is characterized by comprising the following steps:
1) acquiring road vehicle image video information through a camera;
2) carrying out image binarization processing on a vehicle image in the vehicle image video information;
3) preprocessing the image: removing image noise through Gaussian filtering to obtain a denoised image;
4) carrying out image edge detection: detecting whether the car light of the target car exists on the image, and if the image after denoising is detected to have two areas with similar sizes and the distance between the two areas is within a threshold range, judging that the car light exists in the image after denoising; if the vehicle lamp exists on the image after denoising is detected, calculating the area of the connected region according to the detection result to obtain the maximum area of the connected region, describing the contour and obtaining the maximum area contour; utilizing Hough circle detection to obtain a maximum closed circle on the maximum area contour; obtaining an ROI rectangular region according to the obtained parameters of the sum radius of the center of the maximum closed circle, and taking the obtained ROI region as a vehicle lamp region to be tracked in the next step;
5) acquiring distance information from a target vehicle: carrying out back projection on the car lamp area identified in the step 4) to obtain a back projection view; performing camshift algorithm iteration according to the obtained reverse projection drawing and the outline of the car lamp, and iteratively outputting the area S1 of the ROI region of the previous frame image and the area S2 of the ROI rectangular region of the current frame image according to the camshift algorithm; obtaining the distance between the distance and the target vehicle through a formula AB = (S2-S1)/K, wherein AB is the distance between the distance and the target vehicle, and K is an adjusting parameter;
6) sending the processed distance information to a lower computer;
7) the lower computer adjusts the brightness of the car lamp according to the distance information from the target car, and adjusts the voltage of the LED lamp through the output voltage of the control circuit, so that the brightness of the car lamp is adjusted.
2. The matrix vehicle lamp identification method based on computer vision according to claim 1, characterized in that: the image edge detection of 4) is laplacian image detection.
3. The matrix vehicle lamp identification method based on computer vision according to claim 1, characterized in that: and the lower computer adjusts the brightness of the car lamp according to the processed distance information from the target car, wherein the closer the distance from the target car is, the smaller the brightness of the car lamp is.
4. The matrix vehicle lamp identification method based on computer vision according to claim 3, characterized in that: and 7) the lower computer adjusts the brightness of the car lamp according to the distance information, and specifically comprises the step of determining the brightness information according to the distance information of the target car and a preset relation table between the distance information of the target car and the brightness.
5. The matrix vehicle lamp identification method based on computer vision according to claim 1, characterized in that: the image binarization processing of the vehicle image in the step 2) specifically comprises the following steps: the vehicle image is converted into an RGB color space, and then binarization processing is performed on the RGB color space.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911287058.8A CN111027494B (en) | 2019-12-14 | 2019-12-14 | Matrix car lamp identification method based on computer vision |
PCT/CN2020/116242 WO2021114799A1 (en) | 2019-12-14 | 2020-09-18 | Computer vision-based matrix vehicle light identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911287058.8A CN111027494B (en) | 2019-12-14 | 2019-12-14 | Matrix car lamp identification method based on computer vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111027494A true CN111027494A (en) | 2020-04-17 |
CN111027494B CN111027494B (en) | 2023-09-05 |
Family
ID=70210845
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911287058.8A Active CN111027494B (en) | 2019-12-14 | 2019-12-14 | Matrix car lamp identification method based on computer vision |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN111027494B (en) |
WO (1) | WO2021114799A1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112927502A (en) * | 2021-01-21 | 2021-06-08 | 广州小鹏自动驾驶科技有限公司 | Data processing method and device |
WO2021114799A1 (en) * | 2019-12-14 | 2021-06-17 | 华南理工大学广州学院 | Computer vision-based matrix vehicle light identification method |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110450706A (en) * | 2019-08-22 | 2019-11-15 | 哈尔滨工业大学 | A kind of adaptive distance light lamp control system and image processing algorithm |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105303160A (en) * | 2015-09-21 | 2016-02-03 | 中电海康集团有限公司 | Method for detecting and tracking vehicles at night |
CN109094451A (en) * | 2018-07-23 | 2018-12-28 | 华南师范大学 | Night meeting high beam control method and its system, computer readable storage medium |
CN111027494B (en) * | 2019-12-14 | 2023-09-05 | 华南理工大学广州学院 | Matrix car lamp identification method based on computer vision |
-
2019
- 2019-12-14 CN CN201911287058.8A patent/CN111027494B/en active Active
-
2020
- 2020-09-18 WO PCT/CN2020/116242 patent/WO2021114799A1/en active Application Filing
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110450706A (en) * | 2019-08-22 | 2019-11-15 | 哈尔滨工业大学 | A kind of adaptive distance light lamp control system and image processing algorithm |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021114799A1 (en) * | 2019-12-14 | 2021-06-17 | 华南理工大学广州学院 | Computer vision-based matrix vehicle light identification method |
CN112927502A (en) * | 2021-01-21 | 2021-06-08 | 广州小鹏自动驾驶科技有限公司 | Data processing method and device |
Also Published As
Publication number | Publication date |
---|---|
CN111027494B (en) | 2023-09-05 |
WO2021114799A1 (en) | 2021-06-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Alcantarilla et al. | Night time vehicle detection for driving assistance lightbeam controller | |
US8924078B2 (en) | Image acquisition and processing system for vehicle equipment control | |
JP5809785B2 (en) | Vehicle external recognition device and light distribution control system using the same | |
US9384401B2 (en) | Method for fog detection | |
JP5823661B2 (en) | How to detect events that obstruct the field of view of an automobile | |
US8903603B2 (en) | Environment recognizing device for a vehicle and vehicle control system using the same | |
JP2006343322A (en) | Method for detecting nighttime fog, and system for implementing the same | |
US10634317B2 (en) | Dynamic control of vehicle lamps during maneuvers | |
JP4863951B2 (en) | Traffic light recognition device | |
EP2618304B1 (en) | Imaging apparatus, vehicle system having the same, and image-processing method | |
Choi et al. | Vision-based fusion of robust lane tracking and forward vehicle detection in a real driving environment | |
KR101511853B1 (en) | Night-time vehicle detection and positioning system and method using multi-exposure single camera | |
WO2006109398A1 (en) | Image processing device and method, program, and recording medium | |
CN106778534B (en) | Method for identifying ambient light during vehicle running | |
JP2014515893A (en) | Method and apparatus for evaluating an image taken by a camera of a vehicle | |
CN110688907B (en) | Method and device for identifying object based on night road light source | |
CA2609533A1 (en) | Vehicle and road sign recognition device | |
CN110084111B (en) | Rapid night vehicle detection method applied to self-adaptive high beam | |
CN111027494B (en) | Matrix car lamp identification method based on computer vision | |
Lin et al. | Adaptive IPM-based lane filtering for night forward vehicle detection | |
JP2016196233A (en) | Road sign recognizing device for vehicle | |
CN110979156B (en) | Automobile headlamp brightness self-adaptive adjusting device and method based on ambient light detection | |
KR101859201B1 (en) | Developed automobile high-beam automatic control system based on camera sensor and its method | |
CN111046741A (en) | Method and device for identifying lane line | |
CN111688568B (en) | Brightness detection method, vehicle lamp control method, system thereof and storage medium |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |