A nighttime low-light imaging system

Abstract

The present invention relates to the field of image processing technology, and in particular to a nighttime low-light imaging system. The system comprises a monitoring device, a server and a fill-light device, wherein the server comprises an image acquisition module, which is used to acquire video surveillance captured by the monitoring device and identify the current ambient brightness according to the video surveillance screen; a gap recognition module, which is preset with a required brightness and is used to identify the current ambient brightness gap according to the ambient brightness and the required brightness; a fill-light control module, which is used to set a first working parameter of the fill-light device according to the brightness gap, and control the fill-light device to work according to the set first working parameter when no vehicle passes by; a vehicle recognition module, which is used to identify vehicle data according to video surveillance when a vehicle passes by, and determine a second working parameter according to the vehicle data and the current first working parameter; and the fill-light control module is also used to control the fill-light device to work according to the second working parameter when a vehicle passes by.

Description

Technical Field

[0001] The invention relates to the technical field of image processing, and in particular to a nighttime low-light imaging system. Background Art

[0002] Vehicle detection plays an important role in traffic information acquisition and safety management. As an important part of the road traffic system, the operation safety and smoothness of highways are crucial to improving transportation efficiency and promoting regional economic development. Due to the large volume of vehicles on highways and the high speed of vehicles, once a traffic accident occurs, it is very easy to cause serious loss of life and property, and the consequences are disastrous. Especially at night, due to factors such as insufficient ambient brightness and obstructed vision of drivers, the probability of traffic accidents on highways is greatly increased, and the consequences of accidents are more serious. Establishing and implementing a reliable highway vehicle detection system will help to capture abnormal behaviors of individual vehicles and abnormal traffic conditions in a timely manner.

[0003] Compared with traditional vehicle detection methods, video-based detection methods have the advantages of simple installation and maintenance, no impact on the life of the road surface, low cost, wide coverage, and rich perception information, and can promote the development of traffic monitoring systems in the direction of energy consumption. However, most of the existing video vehicle detection methods are aimed at daytime scenes with sufficient light and wide field of view. Once in a harsh night scene, the detection effect will be greatly reduced.

[0004] At night, due to the seasonality of ambient brightness and the presence of noise interference, the contrast and visibility of highway monitoring images are extremely poor, and the appearance features and details of vehicles in them are very blurred, which brings great difficulties to vehicle detection. The vehicle detection task in nighttime highway scenes not only has problems such as diverse backgrounds and variable target scales, but also has difficulties such as low target feature recognition and many interference factors. Summary of the invention

[0005] The technical problem solved by the present invention is to provide a nighttime low-light imaging system, which can improve the recognition capability of nighttime monitoring and identification.

[0006] The basic solution provided by the present invention is: a nighttime low-light imaging system, comprising a monitoring device, a server and a fill-light device, wherein the server comprises an image acquisition module, a gap recognition module, a vehicle recognition module and a fill-light control module;

[0007] The image acquisition module is used to obtain the video surveillance captured by the monitoring equipment and identify the current ambient brightness based on the video surveillance screen;

[0008] A gap recognition module is preset with a required brightness and is used to identify the current ambient brightness gap based on the ambient brightness and the required brightness;

[0009] A fill light control module, used to set a first working parameter of the fill light device according to the brightness gap, and control the fill light device to work according to the set first working parameter when no vehicle passes by;

[0010] A vehicle identification module, used to identify vehicle data according to video surveillance when a vehicle passes by, and determine the second operating parameter according to the vehicle data and the current first operating parameter;

[0011] The fill light control module is also used to control the fill light device to work according to the second working parameter when a vehicle passes by.

[0012] The principle and advantage of the present invention are: through the image acquisition module, the video surveillance captured by the monitoring equipment is acquired, and the video image is identified to obtain the current ambient brightness. According to the preset required brightness, the brightness gap is determined according to the current ambient brightness and the required brightness. Then, according to the required brightness, the first working parameter of the fill light device is set, and the required brightness can be set according to the specific road environment. When there is no vehicle passing by, the fill light device is controlled to work according to the set first working parameter to supplement the ambient brightness. When a vehicle passes by, the vehicle data is acquired, and the second working parameter is set according to the vehicle data. When the vehicle passes by, the fill light device is controlled to work according to the second working parameter. Ensure that the image taken of the vehicle is clear and visible.

[0013] Compared with the prior art, in this application, when there is no vehicle passing on the road, a lower illumination is provided to ensure that the road environment can be clearly seen when a vehicle is about to pass. When a vehicle passes, the vehicle data is obtained, and the second working parameter is set according to the vehicle data. When the vehicle passes, the fill light device operates according to the second working parameter. This makes vehicle monitoring clearer. When there is no vehicle passing, the dim illumination is maintained to save electricity.

[0014] Further, the vehicle identification module includes an image extraction module and a reflection identification module;

[0015] An image extraction module is used to mark vehicle images and environment images from video surveillance;

[0016] The reflective recognition module pre-stores the reflectivity of the brightness range of each color. According to the vehicle image, the environmental image and the first working parameter, the brightness range of the vehicle color is identified, and the reflectivity of the vehicle is determined according to the brightness range. According to the reflectivity of the vehicle, the second working parameter is set. The lower the reflectivity of the vehicle, the higher the second working parameter.

[0017] Through video monitoring, the vehicle image is extracted, and then the vehicle color is identified. Different colors have different reflectivity. Under the same lighting, vehicles with high brightness colors appear more clearly in the monitoring screen, while vehicles with low brightness colors appear more blurred in the monitoring screen. When a vehicle appears in the monitoring screen, the fill light device works according to the first working parameter. At this time, the light only supplements the ambient light to facilitate the driver to see the road clearly. At this time, according to the vehicle image in the image screen, the brightness interval of the vehicle color is identified, and then the reflectivity of the vehicle color is determined. The fill light control module sets the most appropriate second working parameter according to the reflectivity of the vehicle. Ensure that the vehicle outline in the monitoring screen is clearly visible.

[0018] Further, the reflective recognition module includes a chromaticity difference recognition module and a reflectivity recognition module;

[0019] Chromatic difference recognition module, used to identify the chromaticity difference between vehicle images and road images in video surveillance;

[0020] The reflectivity recognition module determines the brightness interval of the vehicle's color based on the chromaticity difference and the reflectivity of the road surface under the first working parameter, and determines the reflectivity of the vehicle's color based on the reflectivity of the preset brightness intervals of each color.

[0021] Since the material and color of the road surface are uniform on the highway, and the roughness of the road surface is higher than that of the vehicle surface, the reflectivity of the road surface is lower than that of the vehicle. The difference in reflectivity between the vehicle and the road surface is determined by identifying the color difference between the road surface and the vehicle. The greater the color difference with the road surface, the higher the reflectivity of the vehicle, and therefore the lower the required illumination, and the lower the second working parameter that needs to be set.

[0022] Further, the vehicle identification module also includes a quantity identification module;

[0023] A quantity recognition module is used to recognize the number of vehicles based on vehicle images;

[0024] The fill light control module is used to adjust the second working parameter according to the number of vehicles. The more the number of vehicles, the lower the second working parameter.

[0025] Since the monitoring is done at night, the vehicles will also turn on their lights when they are driving. The more vehicles there are, the higher the brightness of the lights will be. Therefore, the more vehicles there are, the more the second working parameter can be adjusted. The more vehicles appear in the monitoring screen, the lower the second working parameter can be adjusted.

[0026] Further, the server also includes a contour recognition module;

[0027] The contour recognition module is used to extract the vehicle contour from the marked vehicle image, recognize the vehicle contour, and identify whether the vehicle contour is missing;

[0028] The fill light control module is used to adjust the second working parameter when the outline of the vehicle image is missing, indicating that the current lighting cannot meet the monitoring requirements.

[0029] Identify the vehicle outline in the video surveillance.

[0030] Further, the contour recognition module includes a vehicle light recognition module;

[0031] The headlight recognition module is used to identify the position and size of headlights in video surveillance, and determine the vehicle model based on the position and size of the headlights;

[0032] The vehicle model determination module is used to determine whether the vehicle outline is consistent with the vehicle model according to the determined vehicle model and the vehicle outline in the video surveillance. If it is consistent, the vehicle outline is not missing; if it is not consistent, the vehicle outline is missing;

[0033] The fill light control module is further used to adjust the second working parameter according to the degree of contour loss. The more contour loss there is, the greater the adjustment amount of the second working parameter.

[0034] By identifying the position of the headlights in the monitoring screen, the current distance of the vehicle from the monitoring camera can be determined. Combined with the size of the headlights, the size of the headlights of different models will also be different. For example, the headlights of sedans are smaller than those of off-road vehicles, and the headlights of off-road vehicles are smaller than those of trucks. Based on the position and size of the headlights, the vehicle model can be determined. Then, the vehicle outline is determined to be missing based on the vehicle model. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 Schematic diagram of an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following is further described in detail through specific implementation methods:

[0037] The embodiment is basically as shown in the attached Figure 1 As shown:

[0038] A nighttime low-light imaging system includes a monitoring device, a server and a fill-light device, wherein the server includes an image acquisition module, a gap recognition module, a vehicle recognition module and a fill-light control module;

[0039] The image acquisition module is used to obtain the video surveillance captured by the monitoring equipment and identify the current ambient brightness based on the video surveillance screen;

[0040] A gap recognition module is preset with a required brightness and is used to identify the current ambient brightness gap based on the ambient brightness and the required brightness;

[0041] A fill light control module, used to set a first working parameter of the fill light device according to the brightness gap, and control the fill light device to work according to the set first working parameter when no vehicle passes by;

[0042] A vehicle identification module, used to identify vehicle data according to video surveillance when a vehicle passes by, and determine the second operating parameter according to the vehicle data and the current first operating parameter;

[0043] The fill light control module is also used to control the fill light device to work according to the second working parameter when a vehicle passes by.

[0044] Through the image acquisition module, the video surveillance captured by the monitoring equipment is acquired, and the video image is identified to obtain the current ambient brightness. According to the preset required brightness, the brightness gap is determined according to the current ambient brightness and the required brightness. Then, according to the required brightness, the first working parameter of the fill light device is set. The required brightness can be set according to the specific road environment. When there is no vehicle passing by, the fill light device is controlled to work according to the set first working parameter to supplement the ambient brightness. When a vehicle passes by, the vehicle data is acquired, and the second working parameter is set according to the vehicle data. When the vehicle passes by, the fill light device is controlled to work according to the second working parameter. Ensure that the image shot of the vehicle is clear and visible.

[0045] Compared with the prior art, in this application, when there is no vehicle passing on the road, a lower illumination is provided to ensure that the road environment can be clearly seen when a vehicle is about to pass. When a vehicle passes, the vehicle data is obtained, and the second working parameter is set according to the vehicle data. When the vehicle passes, the fill light device operates according to the second working parameter. This makes vehicle monitoring clearer. When there is no vehicle passing, the dim illumination is maintained to save electricity.

[0046] The vehicle recognition module includes an image extraction module and a reflection recognition module;

[0047] An image extraction module is used to mark vehicle images and environment images from video surveillance;

[0048] The reflective recognition module pre-stores the reflectivity of the brightness range of each color. According to the vehicle image, the environmental image and the first working parameter, the brightness range of the vehicle color is identified, and the reflectivity of the vehicle is determined according to the brightness range. According to the reflectivity of the vehicle, the second working parameter is set. The lower the reflectivity of the vehicle, the higher the second working parameter.

[0049] Through video monitoring, the vehicle image is extracted, and then the vehicle color is identified. Different colors have different reflectivity. Under the same lighting, vehicles with high brightness colors appear more clearly in the monitoring screen, while vehicles with low brightness colors appear more blurred in the monitoring screen. When a vehicle appears in the monitoring screen, the fill light device works according to the first working parameter. At this time, the light only supplements the ambient light to facilitate the driver to see the road clearly. At this time, according to the vehicle image in the image screen, the brightness interval of the vehicle color is identified, and then the reflectivity of the vehicle color is determined. The fill light control module sets the most appropriate second working parameter according to the reflectivity of the vehicle. Ensure that the vehicle outline in the monitoring screen is clearly visible.

[0050] The reflective recognition module includes a chromaticity difference recognition module and a reflectivity recognition module;

[0051] Chromatic difference recognition module, used to identify the chromaticity difference between vehicle images and road images in video surveillance;

[0052] The reflectivity recognition module determines the brightness interval of the vehicle's color based on the chromaticity difference and the reflectivity of the road surface under the first working parameter, and determines the reflectivity of the vehicle's color based on the reflectivity of the preset brightness intervals of each color.

[0053] Since the material and color of the road surface are uniform on the highway, and the roughness of the road surface is higher than that of the vehicle surface, the reflectivity of the road surface is lower than that of the vehicle. The difference in reflectivity between the vehicle and the road surface is determined by identifying the color difference between the road surface and the vehicle. The greater the color difference with the road surface, the higher the reflectivity of the vehicle, and therefore the lower the required illumination, and the lower the second working parameter that needs to be set.

[0054] The vehicle identification module also includes a quantity identification module;

[0055] A quantity recognition module is used to recognize the number of vehicles based on vehicle images;

[0056] The fill light control module is used to adjust the second working parameter according to the number of vehicles. The more the number of vehicles, the lower the second working parameter.

[0057] Since the monitoring is done at night, the vehicles will also turn on their lights when they are driving. The more vehicles there are, the higher the brightness of the lights will be. Therefore, the more vehicles there are, the more the second working parameter can be adjusted. The more vehicles appear in the monitoring screen, the lower the second working parameter can be adjusted.

[0058] The server also includes a contour recognition module;

[0059] The contour recognition module is used to extract the vehicle contour from the marked vehicle image, recognize the vehicle contour, and identify whether the vehicle contour is missing;

[0060] The fill light control module is used to adjust the second working parameter when the outline of the vehicle image is missing, indicating that the current lighting cannot meet the monitoring requirements.

[0061] Identify the vehicle outline in the video surveillance.

[0062] The contour recognition module includes a vehicle light recognition module;

[0063] The headlight recognition module is used to identify the position and size of headlights in video surveillance, and determine the vehicle model based on the position and size of the headlights;

[0064] The vehicle model determination module is used to determine whether the vehicle outline is consistent with the vehicle model according to the determined vehicle model and the vehicle outline in the video surveillance. If it is consistent, the vehicle outline is not missing; if it is not consistent, the vehicle outline is missing;

[0065] The fill light control module is further used to adjust the second working parameter according to the degree of contour loss. The more contour loss there is, the greater the adjustment amount of the second working parameter.

[0066] By identifying the position of the headlights in the monitoring screen, the current distance of the vehicle from the monitoring camera can be determined. Combined with the size of the headlights, the size of the headlights of different models will also be different. For example, the headlights of sedans are smaller than those of off-road vehicles, and the headlights of off-road vehicles are smaller than those of trucks. Based on the position and size of the headlights, the vehicle model can be determined. Then, the vehicle outline is determined to be missing based on the vehicle model.

[0067] The above are only embodiments of the present invention. Common knowledge such as the known specific structures and characteristics in the scheme is not described in detail here. Ordinary technicians in the relevant field know all the common technical knowledge in the technical field to which the invention belongs before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply conventional experimental means before that date. Ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the scope of protection of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A nighttime low-light imaging system, characterized in that: It includes monitoring equipment, a server and a fill light equipment, wherein the server includes an image acquisition module, a gap recognition module, a vehicle recognition module and a fill light control module; The image acquisition module is used to obtain the video surveillance captured by the monitoring equipment and identify the current ambient brightness based on the video surveillance screen; A gap recognition module is preset with a required brightness and is used to identify the current ambient brightness gap based on the ambient brightness and the required brightness; A fill light control module, used to set a first working parameter of the fill light device according to the brightness gap, and control the fill light device to work according to the set first working parameter when no vehicle passes by; A vehicle identification module, used to identify vehicle data according to video surveillance when a vehicle passes by, and determine the second operating parameter according to the vehicle data and the current first operating parameter; The vehicle recognition module includes an image extraction module and a reflection recognition module; An image extraction module is used to mark vehicle images and environment images from video surveillance; A reflective recognition module pre-stores the reflectivity of the brightness interval of each color, identifies the brightness interval of the vehicle color according to the vehicle image, the environment image and the first working parameter, determines the reflectivity of the vehicle according to the brightness interval, and sets the second working parameter according to the reflectivity of the vehicle. The lower the reflectivity of the vehicle, the higher the second working parameter. The reflective recognition module includes a chromaticity difference recognition module and a reflectivity recognition module; Chromatic difference recognition module, used to identify the chromaticity difference between vehicle images and road images in video surveillance; A reflectivity recognition module determines the brightness interval of the color of the vehicle according to the chromaticity difference and the reflectivity of the road surface under the first working parameter, and determines the reflectivity of the color of the vehicle according to the reflectivity of the preset brightness intervals of each color; The fill light control module is also used to control the fill light device to work according to the second working parameter when a vehicle passes by.

2. A nighttime low-light imaging system according to claim 1, characterized in that: The vehicle identification module also includes a quantity identification module; A quantity recognition module is used to recognize the number of vehicles based on vehicle images; The fill light control module is used to adjust the second working parameter according to the number of vehicles. The more the number of vehicles, the lower the second working parameter.

3. The nighttime low-light imaging system according to claim 1, characterized in that: The server also includes a contour recognition module; The contour recognition module is used to extract the vehicle contour from the marked vehicle image, recognize the vehicle contour, and identify whether the vehicle contour is missing; The fill light control module is used to increase the second working parameter when the outline of the vehicle image is missing.

4. A nighttime low-light imaging system according to claim 3, characterized in that: The contour recognition module includes a vehicle light recognition module; The headlight recognition module is used to identify the position and size of headlights in video surveillance, and determine the vehicle model based on the position and size of the headlights; The vehicle model determination module is used to determine whether the vehicle outline is consistent with the vehicle model according to the determined vehicle model and the vehicle outline in the video surveillance. If it is consistent, the vehicle outline is not missing; if it is not consistent, the vehicle outline is missing; The fill light control module is further used to adjust the second working parameter according to the degree of contour loss. The more contour loss there is, the greater the adjustment amount of the second working parameter.

Images