CN109194873B - Image processing method and device - Google Patents
Image processing method and device Download PDFInfo
- Publication number
- CN109194873B CN109194873B CN201811265749.3A CN201811265749A CN109194873B CN 109194873 B CN109194873 B CN 109194873B CN 201811265749 A CN201811265749 A CN 201811265749A CN 109194873 B CN109194873 B CN 109194873B
- Authority
- CN
- China
- Prior art keywords
- image
- preset
- brightness
- acquiring
- infrared light
- 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.)
- Active
Links
Images
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
- H04N23/80—Camera processing pipelines; Components thereof
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses an image processing method and device, relating to the field of artificial intelligence, wherein the method comprises the following steps: judging whether the current moment is the image acquisition moment or not; if yes, acquiring a first image in a low fill-in light brightness scene; acquiring a second image in a scene with high fill-in light brightness; and carrying out fusion processing on the first image and the second image to obtain a target image. In the embodiment of the invention, the first image is collected in the scene with low fill-in light brightness; and acquiring a second image in a scene with high fill-in light brightness. Therefore, the information of the high infrared reflection area in the first image is clear, and the information of the low infrared reflection area in the second image is clear. Therefore, the information of the low infrared reflection area and the information of the high infrared reflection area can be seen clearly in the target image obtained by fusing the first image and the second image.
Description
Technical Field
The invention relates to the field of artificial intelligence of image processing technology, in particular to an image processing method and device.
Background
When carrying out image acquisition, if external light is not enough in the current scene, for example the current scene is the scene at night, in order to guarantee the quality of the image of gathering this moment, need use the light filling lamp to carry out the light filling and handle, when carrying out image acquisition, opens the light filling lamp.
Because the high-brightness visible light supplement lamp is easy to scare a driver in a vehicle when the high-brightness visible light supplement lamp flashes, the infrared light supplement lamp is generally adopted for light supplement in the prior art. The prior art scheme is that in a scene with insufficient external light, when an image is collected, an infrared light supplement lamp is triggered to be turned on, and the infrared light supplement lamp is adopted for supplementing light. With the increasing requirements of users on image quality, the users need to be able to see both information of high infrared reflection areas, such as license plate information of vehicles, and information of low infrared reflection areas, such as face information in vehicles. In the prior art, if the infrared light power of the infrared light supplement lamp is low, the information of a high infrared reflection area can be clearly seen, but the information of a low infrared reflection area cannot be clearly seen; if the infrared light power of the infrared light supplement lamp is high, the information of the low infrared reflection area can be clearly seen, but the information of the high infrared reflection area cannot be clearly seen.
Disclosure of Invention
The embodiment of the invention provides an image processing method and device, which are used for solving the problem that information of a low infrared reflection area and information of a high infrared reflection area cannot be seen clearly in an image at the same time.
The embodiment of the invention provides an image processing method, which comprises the following steps:
judging whether the current moment is the image acquisition moment or not;
if yes, acquiring a first image in a low fill-in light brightness scene; acquiring a second image in a scene with high fill-in light brightness; the optical power of the low fill-in light brightness is not greater than a preset first threshold, and the optical power of the high fill-in light brightness is not less than a preset second threshold, wherein the preset first threshold is less than the preset second threshold;
and carrying out fusion processing on the first image and the second image to obtain a target image.
Further, after the first image and the second image are acquired and before the first image and the second image are fused, the method further comprises:
identifying a high infrared reflection region in the first image and a low infrared reflection region in the second image, respectively;
the fusing the first image and the second image to obtain the target image comprises:
acquiring first coordinate information of each first pixel point in the high-infrared reflection area, and fusing the first image and the second image according to a first pixel value and a preset first weight of each first pixel point corresponding to the first coordinate information in the first image, and a second pixel value and a preset second weight of each second pixel point corresponding to the first coordinate information in the second image to obtain a target image, wherein the preset first weight is greater than the preset second weight; or
Acquiring second coordinate information of each third pixel point in the low infrared reflection area, and fusing the first image and the second image according to a third pixel value and a preset third weight of each third pixel point corresponding to the second coordinate information in the second image, and a fourth pixel value and a preset fourth weight of each fourth pixel point corresponding to the second coordinate information in the first image to obtain a target image, wherein the preset third weight is greater than the preset fourth weight.
Further, the acquiring the first image comprises:
acquiring a first image based on a preset exposure time;
the acquiring a second image comprises:
acquiring a second image based on a preset exposure time;
wherein the preset exposure time is not more than 5 milliseconds.
Further, acquiring a first image in a low fill-in light brightness scene; in a high fill-in luminance scene, acquiring a second image comprises:
controlling a first infrared light supplement lamp to be turned on, and collecting a first image, wherein the brightness of the first infrared light supplement lamp is low supplement brightness; and after a preset time interval, controlling a second infrared light supplement lamp to be turned on, and acquiring a second image, wherein the sum of the brightness of the first infrared light supplement lamp and the brightness of the second infrared light supplement lamp is high supplement brightness.
Further, after the acquiring the second image, the method further comprises:
and controlling the second infrared light supplement lamp to be turned off.
Further, acquiring a first image in a low fill-in light brightness scene; in a high fill-in luminance scene, acquiring a second image comprises:
controlling a third infrared light supplement lamp with high light supplement brightness to be turned on, and collecting a second image; controlling the third infrared light supplement lamp to be turned off, supplementing light by adopting the current brightness of the third infrared light supplement lamp after a preset time interval, and acquiring a first image; and the brightness of the third infrared light supplement lamp after the third infrared light supplement lamp is turned off after a preset time interval is low supplement brightness.
Further, the preset time interval is not more than 5 milliseconds.
In another aspect, an embodiment of the present invention provides an image capturing apparatus, where the apparatus includes:
the judging module is used for judging whether the current moment is the image acquisition moment or not;
the acquisition module is used for acquiring a first image in a low fill-in light brightness scene when the judgment result of the judgment module is yes; acquiring a second image in a scene with high fill-in light brightness; the optical power of the low fill-in light brightness is not greater than a preset first threshold, and the optical power of the high fill-in light brightness is not less than a preset second threshold, wherein the preset first threshold is less than the preset second threshold;
and the fusion module is used for carrying out fusion processing on the first image and the second image to obtain a target image.
Further, the apparatus further comprises:
the identification module is used for respectively identifying a high infrared reflection area in the first image and a low infrared reflection area in the second image;
the fusion module is specifically configured to acquire first coordinate information of each first pixel point in the high-infrared-reflection region, and perform fusion processing on the first image and the second image according to a first pixel value and a preset first weight of each first pixel point corresponding to the first coordinate information in the first image, and a second pixel value and a preset second weight of each second pixel point corresponding to the first coordinate information in the second image to obtain a target image, where the preset first weight is greater than the preset second weight; or acquiring second coordinate information of each third pixel point in the low infrared reflection area, and fusing the first image and the second image according to a third pixel value and a preset third weight of each third pixel point corresponding to the second coordinate information in the second image, and a fourth pixel value and a preset fourth weight of each fourth pixel point corresponding to the second coordinate information in the first image to obtain a target image, wherein the preset third weight is greater than the preset fourth weight.
Further, the acquisition module is specifically configured to acquire a first image based on a preset exposure time; acquiring a second image based on a preset exposure time; wherein the preset exposure time is not more than 5 milliseconds.
Further, the acquisition module is specifically configured to control a first infrared light supplement lamp to be turned on and acquire a first image, where the brightness of the first infrared light supplement lamp is low supplement brightness; and after a preset time interval, controlling a second infrared light supplement lamp to be turned on, and acquiring a second image, wherein the sum of the brightness of the first infrared light supplement lamp and the brightness of the second infrared light supplement lamp is high supplement brightness.
Further, the apparatus further comprises:
and the control module is used for controlling the second infrared light supplement lamp to be turned off.
Further, the acquisition module is specifically configured to control a third infrared light supplement lamp with high light supplement brightness to be turned on, and acquire a second image; controlling the third infrared light supplement lamp to be turned off, supplementing light by adopting the current brightness of the third infrared light supplement lamp after a preset time interval, and acquiring a first image; and the brightness of the third infrared light supplement lamp after the third infrared light supplement lamp is turned off after a preset time interval is low supplement brightness.
The embodiment of the invention provides an image processing method and device, wherein the method comprises the following steps: judging whether the current moment is the image acquisition moment or not; if yes, acquiring a first image in a low fill-in light brightness scene; acquiring a second image in a scene with high fill-in light brightness; the optical power of the low fill-in light brightness is not greater than a preset first threshold, and the optical power of the high fill-in light brightness is not less than a preset second threshold, wherein the preset first threshold is less than the preset second threshold; and carrying out fusion processing on the first image and the second image to obtain a target image.
In the embodiment of the invention, when the image acquisition moment is reached, the first image is acquired under the scene of low fill-in light brightness; and acquiring a second image in a scene with high fill-in light brightness. Therefore, the information of the high infrared reflection area in the first image is clear, and the information of the low infrared reflection area in the second image is clear. Therefore, the information of the low infrared reflection area and the information of the high infrared reflection area can be seen clearly in the target image obtained by fusing the first image and the second image.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic diagram of an image acquisition process provided in embodiment 1 of the present invention;
fig. 2 is an alternative schematic diagram of a frame mode a and a frame mode B provided in embodiment 4 of the present invention;
fig. 3 is a schematic view of an image acquisition process provided in embodiment 4 of the present invention;
FIG. 4 is a schematic diagram of image fusion provided in embodiment 4 of the present invention;
fig. 5 is an alternative schematic diagram of a frame mode C and a frame mode D provided in embodiment 5 of the present invention;
fig. 6 is a schematic view of an image acquisition process provided in embodiment 5 of the present invention;
fig. 7 is a schematic structural diagram of an image capturing device according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the attached drawings, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1:
fig. 1 is a schematic diagram of an image acquisition process provided in an embodiment of the present invention, where the process includes the following steps:
s101: and judging whether the current moment is the image acquisition moment, and if so, performing S102.
The image acquisition method provided by the embodiment of the invention is applied to the image acquisition equipment, the frame rate of image acquisition and the time point of initial image acquisition are preset in the image acquisition equipment, for example, the frame rate is 25 frames/second, and the time point of initial image acquisition is 8-point adjustment. The image acquisition equipment can also comprise a timer, the timer records the current moment in real time, and whether the current moment is the image acquisition moment can be determined according to the preset image acquisition frame rate and the time point of initial image acquisition.
When the current moment is not the image acquisition moment, the image acquisition equipment does not perform the subsequent image acquisition process, and when the current moment is the image acquisition moment, the image acquisition equipment performs the subsequent image acquisition process.
S102: acquiring a first image in a low fill-in luminance scene; acquiring a second image in a scene with high fill-in light brightness; the optical power of the low fill-in light brightness is not greater than a preset first threshold, and the optical power of the high fill-in light brightness is not less than a preset second threshold, wherein the preset first threshold is less than the preset second threshold.
The image acquisition device can generate low light supplement brightness and high light supplement brightness, wherein the light power of the low light supplement brightness is not larger than a preset first threshold value, the light power of the high light supplement brightness is not smaller than a preset second threshold value, and the preset first threshold value is smaller than the preset second threshold value. The preset first threshold and the preset second threshold can be flexibly set according to the distance between the target object and the image acquisition device, when the distance between the target object and the image acquisition device is larger, the first threshold and the second threshold can be set to be larger, and when the distance between the target object and the image acquisition device is smaller, the first threshold and the second threshold can be set to be smaller. Wherein the preset first threshold may be 1 watt, and the preset second threshold may be 10 watts.
In the embodiment of the present invention, the number of the low-brightness fill-in lamps and the number of the high-brightness fill-in lamps in the image capturing device are not limited, as long as the sum of the optical powers of the low-brightness fill-in lamps is not greater than the preset first threshold, and the sum of the optical powers of the high-brightness fill-in lamps is not less than the preset second threshold.
When the current moment is the image acquisition moment, the image acquisition equipment generates low light supplement brightness, acquires a first image in a ground light supplement brightness scene, and acquires a second image in a high light supplement brightness scene. The time interval for acquiring the first image and the second image does not exceed the time interval for acquiring two adjacent frames of images according to the frame rate of the image acquisition equipment.
For example, if the frame rate is 25 frames/second, the time interval between the two adjacent frames of images is 40 milliseconds, and the time interval between the first image and the second image is not more than 40 milliseconds.
In the embodiment of the invention, when the image acquisition moment is reached, the first image is acquired under the scene of low fill-in light brightness; and acquiring a second image in a scene with high fill-in light brightness. Therefore, the information of the high infrared reflection area in the first image is clear, and the information of the low infrared reflection area in the second image is clear. Therefore, the information of the low infrared reflection area and the information of the high infrared reflection area can be seen clearly in the target image obtained by fusing the first image and the second image.
The high infrared reflection area can be a license plate area, and the low infrared reflection area can be a face area in the vehicle.
S103: and carrying out fusion processing on the first image and the second image to obtain a target image.
After acquiring the first image and the second image, the image acquisition device may identify a pixel value of each pixel point in the first image and the second image, respectively. The first image and the second image are two images with the same resolution, so that pixel points in the first image and the second image are in one-to-one correspondence. When the first image and the second image are subjected to fusion processing, for the pixel points in the first image and the pixel points in the second image which correspond to each other one by one, the higher pixel value in the pixel points which correspond to each other one by one can be multiplied by the larger weight, the lower pixel value is multiplied by the lower weight, and then the pixel values of the pixel points which correspond to each other one by one are summed to obtain the target image. For example, the larger weight may be 0.8 and the smaller weight may be 0.2.
In addition, for the pixel points in the edge region, the corresponding larger weight and smaller weight may be different from the larger weight and smaller weight corresponding to other pixel points. For example, the larger weight of the pixel point corresponding to the edge region is 0.6, the smaller weight is 0.4, the larger weight of the other pixel point corresponding to the edge region is 0.8, and the smaller weight is 0.2.
In the embodiment of the invention, when the image acquisition moment is reached, the light is supplemented based on relatively low brightness, the first image is acquired, the light is supplemented based on relatively high brightness, and the second image is acquired. Because the license plate has high reflectivity to infrared light, the license plate in the first image is clear, and the human face in the vehicle in the second image is clear because the human face has low reflectivity to infrared light. Therefore, the first image and the second image are fused, and the obtained target image can see the license plate and the face in the vehicle clearly.
Example 2:
in order to make the license plate and the in-vehicle face in the determined target image clearer, on the basis of the above embodiment, in an embodiment of the present invention, after the first image and the second image are acquired, before the first image and the second image are subjected to fusion processing, the method further includes:
identifying a high infrared reflection region in the first image and a low infrared reflection region in the second image, respectively;
the fusing the first image and the second image to obtain the target image comprises:
acquiring first coordinate information of each first pixel point in the high-infrared reflection area, and fusing the first image and the second image according to a first pixel value and a preset first weight of each first pixel point corresponding to the first coordinate information in the first image, and a second pixel value and a preset second weight of each second pixel point corresponding to the first coordinate information in the second image to obtain a target image, wherein the preset first weight is greater than the preset second weight; or
Acquiring second coordinate information of each third pixel point in the low infrared reflection area, and fusing the first image and the second image according to a third pixel value and a preset third weight of each third pixel point corresponding to the second coordinate information in the second image, and a fourth pixel value and a preset fourth weight of each fourth pixel point corresponding to the second coordinate information in the first image to obtain a target image, wherein the preset third weight is greater than the preset fourth weight.
In the embodiment of the present invention, the high infrared reflection region is a license plate region, and the low infrared reflection region is a human face region in the vehicle.
After acquiring the first image and the second image, the image acquisition device respectively identifies the license plate region in the first image and the in-vehicle face region in the second image, wherein the process of identifying the license plate region and the in-vehicle face region in the images belongs to the prior art, and the process is not repeated herein.
In the embodiment of the invention, the first image and the second image are subjected to fusion processing according to the license plate area and the face area in the vehicle in the first image and the second image to obtain the target image.
In the embodiment of the invention, each pixel point in the license plate area in the first image is used as a first pixel point, and the coordinate information of the first pixel point is used as the first coordinate information. Since the resolutions of the first image and the second image are the same, each second pixel point corresponding to the first coordinate information can be determined in the second image. Because the license plate region in the first image is clear and the license plate in the second image is likely to be overexposed, the first pixel value of each first pixel point corresponding to the first coordinate information in the first image is multiplied by the preset first weight, the second pixel value of each second pixel point corresponding to the first coordinate information in the second image is multiplied by the preset second weight, and then the pixel values of the pixel points corresponding to the license plate region are summed. The preset first weight is greater than the preset second weight, for example, the preset first weight is 0.8, and the preset second weight is 0.2. The license plate region in the target image obtained in the above way is clear, and the in-vehicle face region and the license plate region in the target region obtained in the above way are clear because the in-vehicle face region in the second image is clear.
In addition, in the embodiment of the present invention, each pixel point in the in-vehicle face area in the second image is used as a third pixel point, and the coordinate information of the third pixel point is used as the second coordinate information. Since the resolutions of the first image and the second image are the same, each fourth pixel point corresponding to the second coordinate information can be determined in the first image. Since the in-vehicle face area in the second image is clear, the third pixel value of each third pixel point corresponding to the second coordinate information in the second image is multiplied by the preset third weight, the fourth pixel value of each fourth pixel point corresponding to the second coordinate information in the first image is multiplied by the preset fourth weight, and then the pixel values of the pixel points corresponding to the face area are summed. The preset third weight is greater than the preset fourth weight, the preset third weight and the preset first weight may be the same or different, and the preset fourth weight and the preset second weight may be the same or different, for example, the preset third weight is 0.7, and the preset fourth weight is 0.3. The obtained target image has clear in-vehicle face area, and the license plate area in the first image is clear, so that the in-vehicle face area and the license plate area in the obtained target area are clear.
For pixel values of pixel points in the target image except for the license plate region and the in-vehicle face region, pixel values of corresponding pixel points in the first image may be adopted, pixel values of corresponding pixel points in the second image may also be adopted, or an average value of pixel values of corresponding pixel points in the first image and the second image may also be calculated, or a higher weight may be assigned to a higher pixel value in the corresponding pixel point, and a lower weight may be assigned to a lower pixel value.
Example 3:
in order to reduce the smear phenomenon in the image, on the basis of the above embodiments, in an embodiment of the present invention, acquiring the first image includes:
acquiring a first image based on a preset exposure time;
the acquiring a second image comprises:
acquiring a second image based on a preset exposure time;
wherein the preset exposure time is not more than 5 milliseconds.
For relatively low brightness, although the corresponding light power is small, the license plate is seen clearly under relatively low brightness, and the license plate has high reflectivity to infrared light, so that the license plate can be seen clearly without long-time exposure. For relatively high brightness, the corresponding light power is large, the light supplementing space range is large, and light can be supplemented for a large scene at the same time, so that long-time exposure is not needed, and the face in the vehicle in the image can be seen clearly.
In an embodiment of the invention, the first image and the second image are acquired based on a preset exposure time, wherein the preset exposure time is not more than 5 milliseconds. The higher the optical power, the shorter the required exposure time, and the lower the optical power, the longer the required exposure time.
Example 4:
on the basis of the above embodiments, in the embodiment of the present invention, in order to make a license plate region in the collected first image clear and a face region in a vehicle in the second image clear, the first image is collected in a low fill-in luminance scene; in a high fill-in luminance scene, acquiring a second image comprises:
controlling a first infrared light supplement lamp to be turned on, and collecting a first image, wherein the brightness of the first infrared light supplement lamp is low supplement brightness; and after a preset time interval, controlling a second infrared light supplement lamp to be turned on, and acquiring a second image, wherein the sum of the brightness of the first infrared light supplement lamp and the brightness of the second infrared light supplement lamp is high supplement brightness.
The image acquisition equipment comprises a first infrared light supplementing lamp and a second infrared light supplementing lamp, wherein the brightness of the first infrared light supplementing lamp is low supplementing brightness, and the sum of the brightness of the first infrared light supplementing lamp and the brightness of the second infrared light supplementing lamp is high supplementing brightness. The first infrared light supplement lamp can be an infrared normally-on light supplement lamp, an infrared flashing lamp with low brightness adjusted, a low-brightness infrared light supplement lamp with pulse modulation and the like; the second infrared light filling lamp can be an infrared flashing lamp, and the infrared flashing lamp can be an infrared flashing lamp based on an LED, and also can be an infrared flashing lamp based on a short-pulse infrared laser LD. The infrared flashing lamp based on the LD can obtain larger instantaneous light power and larger supplementary lighting coverage, so that the whole monitoring scene is illuminated.
In the embodiment of the invention, the frame mode A is firstly carried out, namely, a first infrared light supplement lamp is turned on, and a first image is collected in a low light supplement brightness scene. And then, after a preset time interval, performing a frame mode B, namely turning on a second infrared light supplement lamp, and acquiring a second image in a high light supplement brightness scene.
The two frame modes of the above formula are characterized as follows:
| frame mode | Light supplement | Exposure time | Primary target recognition |
| Frame mode A | First infrared light supplement lamp | Short exposure | License plate |
| Frame mode B | Second infrared light patchLight lamp | Short exposure | In-car face |
In the embodiment of the invention, the frame mode A and the frame mode B are alternately carried out in the image acquisition process,
fig. 2 is a schematic diagram illustrating an alternation of a frame mode a and a frame mode B, each image acquisition time in fig. 2 is an image acquisition time determined according to an image acquisition frame rate, when each image acquisition time is reached, the frame mode a is performed first, then the frame mode B is performed, and then a first image obtained in the frame mode a and a second image obtained in the frame mode B are fused to obtain a target image of a current frame.
Fig. 3 is a schematic diagram of an image acquisition process according to an embodiment of the present invention, in a normal exposure mode, determining whether to start a wide dynamic mode, that is, determining whether to start two frame modes to acquire an image, if not, continuing to acquire the image in the normal exposure mode, if so, when an image acquisition time is reached, starting a first infrared light supplement lamp, entering a frame mode a, acquiring a first image in the frame mode a, and then starting a second infrared light supplement lamp, entering a frame mode B, and acquiring a second image in the frame mode B after a preset time interval. And then judging whether the wide dynamic mode is closed, if so, entering a normal exposure mode, otherwise, continuing to execute the wide dynamic mode when the image acquisition time is reached.
Fig. 4 is a schematic diagram of image fusion provided in the embodiment of the present invention, in a wide dynamic mode, a first image acquired in a frame mode a is extracted, a second image acquired in a frame mode B is extracted, and the first image and the second image are fused to obtain a target image and output the target image. And judging whether the image is in the wide dynamic mode, if not, processing the image according to a single frame in the normal exposure mode, and if so, continuing to perform image fusion when the image acquisition time is reached.
To reduce power consumption of the image acquisition device, after acquiring the second image, the method further comprises:
and controlling the second infrared light supplement lamp to be turned off.
The first infrared light supplement lamp is in a normally-on state.
Example 5:
on the basis of the above embodiments, in the embodiment of the present invention, in order to make a license plate region in the collected first image clear and a face region in a vehicle in the second image clear, the first image is collected in a low fill-in luminance scene; in a high fill-in luminance scene, acquiring a second image comprises:
controlling a third infrared light supplement lamp with high light supplement brightness to be turned on, and collecting a second image; controlling the third infrared light supplement lamp to be turned off, supplementing light by adopting the current brightness of the third infrared light supplement lamp after a preset time interval, and acquiring a first image; and the brightness of the third infrared light supplement lamp after the third infrared light supplement lamp is turned off after a preset time interval is low supplement brightness.
The image acquisition equipment further comprises a third infrared light supplement lamp, wherein the brightness of the third infrared light supplement lamp is high supplement brightness. If the optical power corresponding to the brightness of the second infrared light supplement lamp is greater than a preset second threshold, the third infrared light supplement lamp and the second infrared light supplement lamp can be the same.
Because the third infrared light supplement lamp with high supplement brightness still has weak infrared light output within a certain closing time, by utilizing the characteristic, in the embodiment of the invention, when the image is collected, the image is divided into two frame modes, namely a frame mode C and a frame mode D. And then, performing a frame mode D, namely turning off the third infrared light supplement lamp, supplementing light by adopting the current brightness of the third infrared light supplement lamp after a preset time interval, and acquiring a first image. The preset time interval is not more than 5 milliseconds, and the current output low light supplement brightness of the third infrared light supplement lamp can be ensured.
In the embodiment of the invention, the frame mode C and the frame mode D are alternately carried out in the image acquisition process,
fig. 5 is a schematic diagram illustrating an alternation of a frame mode C and a frame mode D, each image acquisition time in fig. 5 is an image acquisition time determined according to an image acquisition frame rate, when each image acquisition time is reached, the frame mode C is performed first, then the frame mode D is performed, and then a second image obtained in the frame mode C and a first image obtained in the frame mode D are fused to obtain a target image of a current frame.
Fig. 6 is a schematic diagram of an image acquisition process according to an embodiment of the present invention, in a normal exposure mode, determining whether to start a wide dynamic mode, that is, determining whether to start two frame modes to acquire an image, if not, continuing to acquire the image in the normal exposure mode, if so, when an image acquisition time is reached, turning on a third infrared light supplement lamp, entering a frame mode C, acquiring a second image in the frame mode C, then turning off the third infrared light supplement lamp, entering a frame mode B, and acquiring a first image after a preset time interval. And then judging whether the wide dynamic mode is closed, if so, entering a normal exposure mode, otherwise, continuing to execute the wide dynamic mode when the image acquisition time is reached.
Fig. 7 is a schematic structural diagram of an image capturing device according to an embodiment of the present invention, where the image capturing device includes:
the judging module 71 is configured to judge whether the current time is an image acquisition time;
the acquisition module 72 is configured to acquire a first image in a low fill-in luminance scene when the determination result of the determination module 71 is yes; acquiring a second image in a scene with high fill-in light brightness; the optical power of the low fill-in light brightness is not greater than a preset first threshold, and the optical power of the high fill-in light brightness is not less than a preset second threshold, wherein the preset first threshold is less than the preset second threshold;
and a fusion module 73, configured to perform fusion processing on the first image and the second image to obtain a target image.
The device further comprises:
an identification module 74 for identifying high infrared reflection areas in the first image and low infrared reflection areas in the second image, respectively;
the fusion module 73 is specifically configured to acquire first coordinate information of each first pixel point in the high-infrared-reflection region, and perform fusion processing on the first image and the second image according to a first pixel value and a preset first weight of each first pixel point corresponding to the first coordinate information in the first image, and a second pixel value and a preset second weight of each second pixel point corresponding to the first coordinate information in the second image, to obtain a target image, where the preset first weight is greater than the preset second weight; or acquiring second coordinate information of each third pixel point in the low infrared reflection area, and fusing the first image and the second image according to a third pixel value and a preset third weight of each third pixel point corresponding to the second coordinate information in the second image, and a fourth pixel value and a preset fourth weight of each fourth pixel point corresponding to the second coordinate information in the first image to obtain a target image, wherein the preset third weight is greater than the preset fourth weight.
The acquisition module 72 is specifically configured to acquire a first image based on a preset exposure time; acquiring a second image based on a preset exposure time; wherein the preset exposure time is not more than 5 milliseconds.
The acquisition module 72 is specifically configured to control a first infrared light supplement lamp to be turned on and acquire a first image, where the brightness of the first infrared light supplement lamp is low supplement brightness; and after a preset time interval, controlling a second infrared light supplement lamp to be turned on, and acquiring a second image, wherein the sum of the brightness of the first infrared light supplement lamp and the brightness of the second infrared light supplement lamp is high supplement brightness.
The device further comprises:
and the control module 75 is configured to control the second infrared light supplement lamp to be turned off.
The acquisition module 72 is specifically configured to control a third infrared light supplement lamp with high light supplement brightness to be turned on, and acquire a second image; controlling the third infrared light supplement lamp to be turned off, supplementing light by adopting the current brightness of the third infrared light supplement lamp after a preset time interval, and acquiring a first image; and the brightness of the third infrared light supplement lamp after the third infrared light supplement lamp is turned off after a preset time interval is low supplement light.
The embodiment of the invention provides an image processing method and device, wherein the method comprises the following steps: judging whether the current moment is the image acquisition moment or not; if yes, acquiring a first image in a low fill-in light brightness scene; acquiring a second image in a scene with high fill-in light brightness; the optical power of the low fill-in light brightness is not greater than a preset first threshold, and the optical power of the high fill-in light brightness is not less than a preset second threshold, wherein the preset first threshold is less than the preset second threshold; and carrying out fusion processing on the first image and the second image to obtain a target image.
In the embodiment of the invention, when the image acquisition moment is reached, the first image is acquired under the scene of low fill-in light brightness; and acquiring a second image in a scene with high fill-in light brightness. Therefore, the information of the high infrared reflection area in the first image is clear, and the information of the low infrared reflection area in the second image is clear. Therefore, the information of the low infrared reflection area and the information of the high infrared reflection area can be seen clearly in the target image obtained by fusing the first image and the second image.
In addition, in the embodiment of the invention, people or objects far away and people or objects near the people or objects can be seen clearly at the same time, wherein people or objects near the first image are clear, people or objects far away are insufficient in light supplement, people or objects near the second image are over-exposed, and people or objects far away are clear. Therefore, the fused target image can see the far people or objects and the near people or objects at the same time.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (11)
1. An image processing method, characterized in that the method comprises:
judging whether the current moment is the image acquisition moment or not;
if yes, acquiring a first image in a low fill-in light brightness scene; acquiring a second image in a scene with high fill-in light brightness; the optical power of the low fill-in light brightness is not greater than a preset first threshold, and the optical power of the high fill-in light brightness is not less than a preset second threshold, wherein the preset first threshold is less than the preset second threshold;
performing fusion processing on the first image and the second image to obtain a target image;
after the first image and the second image are acquired and before the first image and the second image are subjected to fusion processing, the method further comprises the following steps:
identifying a high infrared reflection region in the first image and a low infrared reflection region in the second image, respectively;
the fusing the first image and the second image to obtain the target image comprises:
acquiring first coordinate information of each first pixel point in the high-infrared reflection area, and fusing the first image and the second image according to a first pixel value and a preset first weight of each first pixel point corresponding to the first coordinate information in the first image, and a second pixel value and a preset second weight of each second pixel point corresponding to the first coordinate information in the second image to obtain a target image, wherein the preset first weight is greater than the preset second weight; or
Acquiring second coordinate information of each third pixel point in the low infrared reflection area, and fusing the first image and the second image according to a third pixel value and a preset third weight of each third pixel point corresponding to the second coordinate information in the second image, and a fourth pixel value and a preset fourth weight of each fourth pixel point corresponding to the second coordinate information in the first image to obtain a target image, wherein the preset third weight is greater than the preset fourth weight.
2. The method of claim 1, wherein said acquiring a first image comprises:
acquiring a first image based on a preset exposure time;
the acquiring a second image comprises:
acquiring a second image based on a preset exposure time;
wherein the preset exposure time is not more than 5 milliseconds.
3. The method of claim 1, wherein the first image is acquired in a low fill-in luminance scene; in a high fill-in luminance scene, acquiring a second image comprises:
controlling a first infrared light supplement lamp to be turned on, and collecting a first image, wherein the brightness of the first infrared light supplement lamp is low supplement brightness; and after a preset time interval, controlling a second infrared light supplement lamp to be turned on, and acquiring a second image, wherein the sum of the brightness of the first infrared light supplement lamp and the brightness of the second infrared light supplement lamp is high supplement brightness.
4. The method of claim 3, wherein after the acquiring the second image, the method further comprises:
and controlling the second infrared light supplement lamp to be turned off.
5. The method of claim 1, wherein the first image is acquired in a low fill-in luminance scene; in a high fill-in luminance scene, acquiring a second image comprises:
controlling a third infrared light supplement lamp with high light supplement brightness to be turned on, and collecting a second image; controlling the third infrared light supplement lamp to be turned off, supplementing light by adopting the current brightness of the third infrared light supplement lamp after a preset time interval, and acquiring a first image; and the brightness of the third infrared light supplement lamp after the third infrared light supplement lamp is turned off after a preset time interval is low supplement brightness.
6. A method according to claim 3 or 5, wherein the predetermined time interval is no more than 5 milliseconds.
7. An image processing apparatus, characterized in that the apparatus comprises:
the judging module is used for judging whether the current moment is the image acquisition moment or not;
the acquisition module is used for acquiring a first image in a low fill-in light brightness scene when the judgment result of the judgment module is yes; acquiring a second image in a scene with high fill-in light brightness; the optical power of the low fill-in light brightness is not greater than a preset first threshold, and the optical power of the high fill-in light brightness is not less than a preset second threshold, wherein the preset first threshold is less than the preset second threshold;
the fusion module is used for carrying out fusion processing on the first image and the second image to obtain a target image;
the device further comprises:
the identification module is used for respectively identifying a high infrared reflection area in the first image and a low infrared reflection area in the second image;
the fusion module is specifically configured to acquire first coordinate information of each first pixel point in the high-infrared-reflection region, and perform fusion processing on the first image and the second image according to a first pixel value and a preset first weight of each first pixel point corresponding to the first coordinate information in the first image, and a second pixel value and a preset second weight of each second pixel point corresponding to the first coordinate information in the second image to obtain a target image, where the preset first weight is greater than the preset second weight; or acquiring second coordinate information of each third pixel point in the low infrared reflection area, and fusing the first image and the second image according to a third pixel value and a preset third weight of each third pixel point corresponding to the second coordinate information in the second image, and a fourth pixel value and a preset fourth weight of each fourth pixel point corresponding to the second coordinate information in the first image to obtain a target image, wherein the preset third weight is greater than the preset fourth weight.
8. The apparatus according to claim 7, wherein the acquisition module is specifically configured to acquire the first image based on a preset exposure time; acquiring a second image based on a preset exposure time; wherein the preset exposure time is not more than 5 milliseconds.
9. The apparatus according to claim 7, wherein the acquisition module is specifically configured to control a first infrared light supplement lamp to be turned on and acquire a first image, and a luminance of the first infrared light supplement lamp is a low supplement luminance; and after a preset time interval, controlling a second infrared light supplement lamp to be turned on, and acquiring a second image, wherein the sum of the brightness of the first infrared light supplement lamp and the brightness of the second infrared light supplement lamp is high supplement brightness.
10. The apparatus of claim 9, wherein the apparatus further comprises:
and the control module is used for controlling the second infrared light supplement lamp to be turned off.
11. The apparatus according to claim 7, wherein the collection module is specifically configured to control a third infrared light supplement lamp with high light supplement brightness to be turned on, and collect the second image; controlling the third infrared light supplement lamp to be turned off, supplementing light by adopting the current brightness of the third infrared light supplement lamp after a preset time interval, and acquiring a first image; and the brightness of the third infrared light supplement lamp after the third infrared light supplement lamp is turned off after a preset time interval is low supplement brightness.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811265749.3A CN109194873B (en) | 2018-10-29 | 2018-10-29 | Image processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811265749.3A CN109194873B (en) | 2018-10-29 | 2018-10-29 | Image processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109194873A CN109194873A (en) | 2019-01-11 |
| CN109194873B true CN109194873B (en) | 2021-02-02 |
Family
ID=64944082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811265749.3A Active CN109194873B (en) | 2018-10-29 | 2018-10-29 | Image processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109194873B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7277236B2 (en) * | 2019-04-18 | 2023-05-18 | キヤノン株式会社 | IMAGING DEVICE, IMAGING SYSTEM, PROGRAM, RECORDING MEDIUM, AND CONTROL METHOD |
| CN110493493B (en) * | 2019-05-31 | 2022-04-29 | 杭州海康威视数字技术股份有限公司 | Panoramic detail camera and method for acquiring image signal |
| CN110490041B (en) * | 2019-05-31 | 2022-03-15 | 杭州海康威视数字技术股份有限公司 | Face image acquisition device and method |
| CN110493495B (en) * | 2019-05-31 | 2022-03-08 | 杭州海康威视数字技术股份有限公司 | Image acquisition device and image acquisition method |
| CN110493537B (en) * | 2019-06-14 | 2022-08-02 | 杭州海康威视数字技术股份有限公司 | Image acquisition device and image acquisition method |
| CN112907701B (en) * | 2019-11-19 | 2022-08-05 | 杭州海康威视数字技术股份有限公司 | Method and device for acquiring image, computer equipment and storage medium |
| CN112907454B (en) * | 2019-11-19 | 2023-08-08 | 杭州海康威视数字技术股份有限公司 | Method, device, computer equipment and storage medium for acquiring image |
| CN111064898B (en) * | 2019-12-02 | 2021-07-16 | 联想(北京)有限公司 | Image shooting method and device, equipment and storage medium |
| CN111383206B (en) * | 2020-06-01 | 2020-09-29 | 浙江大华技术股份有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN114095666B (en) * | 2021-08-12 | 2023-09-22 | 荣耀终端有限公司 | Photographing method, electronic device, and computer-readable storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105957042A (en) * | 2016-06-07 | 2016-09-21 | 北京理工大学 | Highlight region eliminating method of endoscopic image |
-
2018
- 2018-10-29 CN CN201811265749.3A patent/CN109194873B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105957042A (en) * | 2016-06-07 | 2016-09-21 | 北京理工大学 | Highlight region eliminating method of endoscopic image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109194873A (en) | 2019-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109194873B (en) | Image processing method and device | |
| CN108460395B (en) | Target detection method and device and fuzzy processing method and device | |
| US9639764B2 (en) | Image recognition system for vehicle for traffic sign board recognition | |
| US20060215882A1 (en) | Image processing apparatus and method, recording medium, and program | |
| JP5435307B2 (en) | In-vehicle camera device | |
| CN105812674A (en) | Signal lamp color correction method, monitoring method, and device thereof | |
| CN106503707B (en) | Licence plate recognition method and device under a kind of infrared lighting condition | |
| JP2013005234A5 (en) | ||
| US9977986B2 (en) | Method and apparatus for switching a region of interest | |
| CN106161984B (en) | Video image highlight suppression, contour and detail enhancement processing method and system | |
| US10129458B2 (en) | Method and system for dynamically adjusting parameters of camera settings for image enhancement | |
| CN113438779A (en) | Method for triggering street lamp illumination intensity adjustment based on image | |
| CN113490316A (en) | Light filling system and light filling lamp | |
| CN115103475A (en) | Street lamp illumination control method, device, equipment and storage medium | |
| DE112018007715T5 (en) | VEHICLE DISPLAY CONTROL DEVICE | |
| CN105034929A (en) | Irradiation apparatus | |
| Mandal et al. | Real-time automotive night-vision system for drivers to inhibit headlight glare of the oncoming vehicles and enhance road visibility | |
| CN109543523A (en) | Image processing method, device, system and storage medium | |
| CN111489558B (en) | License plate recognition method and system | |
| US20230005239A1 (en) | Image capturing method and device, apparatus, and storage medium | |
| CN112752003A (en) | Light supplementing method and device, light supplementing equipment and monitoring equipment | |
| CN112991158A (en) | Image generation method, device, equipment and storage medium | |
| CN116112805A (en) | Method and device for adjusting brightness of light supplementing lamp, electronic device and storage medium | |
| CN116110035A (en) | Image processing method and device, electronic equipment and storage medium | |
| TWI630818B (en) | Dynamic image feature enhancement method and system |
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 |