WO2020181469A1 - 一种图像处理方法、设备、***及存储介质 - Google Patents

一种图像处理方法、设备、***及存储介质 Download PDF

Info

Publication number
WO2020181469A1
WO2020181469A1 PCT/CN2019/077702 CN2019077702W WO2020181469A1 WO 2020181469 A1 WO2020181469 A1 WO 2020181469A1 CN 2019077702 W CN2019077702 W CN 2019077702W WO 2020181469 A1 WO2020181469 A1 WO 2020181469A1
Authority
WO
WIPO (PCT)
Prior art keywords
color
multiple images
feature points
image
same name
Prior art date
Application number
PCT/CN2019/077702
Other languages
English (en)
French (fr)
Inventor
张明磊
梁家斌
Original Assignee
深圳市大疆创新科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳市大疆创新科技有限公司 filed Critical 深圳市大疆创新科技有限公司
Priority to CN201980002930.1A priority Critical patent/CN110785772A/zh
Priority to PCT/CN2019/077702 priority patent/WO2020181469A1/zh
Publication of WO2020181469A1 publication Critical patent/WO2020181469A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/10Terrestrial scenes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/46Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/462Salient features, e.g. scale invariant feature transforms [SIFT]

Definitions

  • the present invention relates to the field of image processing technology, in particular to an image processing method, equipment, system and storage medium.
  • an image acquisition device acquires multiple images with the same image area under different environments (such as different lighting), the color, brightness, etc. of each image with the same image area may be inconsistent due to the different environments.
  • a histogram matching method is often used to process multiple images with the same image area. This processing method is likely to cause the cumulative shift of colors, and there is likely to be a large color difference after processing, and the processing speed is slow, which cannot solve the problem well.
  • the embodiments of the present invention provide an image processing method, device, system and storage medium, which can realize global color adjustment of an image and improve the efficiency of image processing.
  • an embodiment of the present invention provides an image processing method, the method including:
  • the color of each image is adjusted according to the color adjustment parameter corresponding to each image.
  • an embodiment of the present invention provides an image processing device, including a memory and a processor;
  • the memory is used to store program instructions
  • the processor is configured to call the program instructions, and when the program instructions are executed, to perform the following operations:
  • the color of each image is adjusted according to the color adjustment parameter corresponding to each image.
  • an embodiment of the present invention provides an image processing system, including: a drone and an image processing device, the drone is provided with an image acquisition device;
  • the unmanned aerial vehicle is configured to collect multiple images during the movement of the unmanned aerial vehicle through the image acquisition device, and send the acquired multiple images to the image processing device;
  • the image processing device is used to determine the feature points of the multiple images with the same name; determine the color adjustment parameters corresponding to each image based on the color information of the feature points of the multiple images with the same name; The adjustment parameter adjusts the color of each image.
  • an embodiment of the present invention provides a computer-readable storage medium that stores a computer program that, when executed by a processor, implements the image processing method described in the first aspect.
  • the image processing device determines the color adjustment parameters corresponding to each image based on the color information of the feature points of the same name of multiple images by determining the feature points of the same name of the multiple images, and according to the corresponding
  • the color adjustment parameter adjusts the color of each image, which can realize global color adjustment of multiple images, so that the adjusted multiple images have color consistency, and the efficiency of image processing is improved.
  • Fig. 1 is a schematic structural diagram of an image processing system provided by an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of an image processing method according to an embodiment of the present invention.
  • Figure 3a is a schematic diagram of an image interface provided by an embodiment of the present invention.
  • 3b is a schematic diagram of an interface of an adjusted image provided by an embodiment of the present invention.
  • FIG. 4 is a schematic flowchart of another image processing method provided by an embodiment of the present invention.
  • Fig. 5 is a schematic structural diagram of an image processing device provided by an embodiment of the present invention.
  • the image processing method provided in the embodiment of the present invention may be executed by an image processing system, and the image processing system may include a drone and an image processing device.
  • the drone is provided with an image acquisition device; in some embodiments, the image acquisition device may be a camera mounted on the pan/tilt of the drone, and the image acquisition device It may also be other devices with an image acquisition function, which is not specifically limited in the embodiment of the present invention.
  • the image capture device is used to capture images during the movement of the drone and send them to the image processing device; the image processing device is used to perform processing on the images captured by the image capture device deal with.
  • the image processing device may be provided on the drone; in some embodiments, the image processing device may be independent of the drone.
  • the image processing device may be a ground image processing device.
  • the image processing device may also be set in a cloud processor.
  • the image processing system may be set on equipment such as drones, robots, mobile terminals (such as mobile phones). The following is a schematic description of an image processing system composed of an unmanned aerial vehicle and an image processing device with reference to FIG. 1.
  • Figure 1 is a schematic structural diagram of an image processing system provided by an embodiment of the present invention.
  • the image processing system shown in Figure 1 includes: a drone 11 and an image processing device 12, the drone 11 An image acquisition device 111 is provided on the UAV.
  • the UAV 11 may be a rotary-wing UAV, for example, a quadrotor UAV, a hexarotor UAV, an eight-rotor UAV, or a fixed-wing UAV. Wait.
  • the drone 11 includes a power system 112, and the power system 112 is used to provide power for the drone 11 to fly.
  • the image acquisition device 111 may acquire multiple images during the movement of the drone 11, and send the acquired multiple images to the image processing device 12.
  • the image processing After the device 12 receives the multiple images sent by the image acquisition device 111, the multiple images may be processed.
  • the plurality of images includes images with a common viewing area.
  • the plurality of images may have a common view area in pairs, or an image and at least two images may have a common view area, or there may be a common view area between multiple images, which is not done in this embodiment of the present invention.
  • the common view area of the image means that there are image areas that at least partially overlap each other between the images.
  • the image processing device 12 when the image processing device 12 processes the image, it can determine the feature points of the multiple images with the same name, and based on the color information of the feature points of the multiple images with the same name, determine each The color adjustment parameter corresponding to the image, and the color of each image is adjusted according to the color adjustment parameter corresponding to each image.
  • the embodiment of the present invention can realize global color adjustment of multiple images, so that the multiple images after adjustment have color consistency, and the efficiency of image processing is improved.
  • FIG. 2 is a schematic flowchart of an image processing method provided by an embodiment of the present invention.
  • the method may be executed by an image processing device, wherein the specific explanation of the image processing device is as described above.
  • the method of the embodiment of the present invention includes the following steps.
  • S201 Determine feature points with the same name of multiple images.
  • the image processing device can determine the feature points of multiple images with the same name.
  • the plurality of images includes images with a common viewing area.
  • two of the multiple images may have a common view area, or one of the images and at least two images may have a common view area, or multiple images may have a common view area.
  • the common view area of the image means that there are image areas that at least partially overlap each other between the images.
  • the image processing device may acquire the feature points of the multiple images, and perform feature matching on the feature points of the multiple images to determine the Feature points with the same name from multiple images.
  • the color of the image area where each feature point with the same name is located can be adjusted subsequently to ensure that the color of the image area where the feature point with the same name is located in each image is consistent.
  • the feature points of the multiple images with the same name refer to the features that are extracted from images with common view areas in the multiple images during the process of feature extraction and feature matching, and the matching is successful point.
  • the image processing device can perform feature extraction and feature matching on n images to determine the features of the same name in the common viewing area of each image point.
  • the image of the same object P on different images is p i
  • p i is extracted as feature points on different images
  • the point p i is called the feature point with the same name.
  • S202 Determine color adjustment parameters corresponding to each image based on the color information of the feature points with the same name of the multiple images.
  • the image processing device may determine the color adjustment parameter corresponding to each image based on the color information of the feature points with the same name of the multiple images.
  • the color information includes a first color space value and a second color space value.
  • the first color space value is an RGB color space
  • the RGB color space includes three channels of red, green, and blue
  • the first color space value includes a red value R, a green value G
  • the blue value is B.
  • the second color space is a YCbCr color space
  • the YCbCr color space value includes three channels of brightness, first color difference and second color difference.
  • the second color space value includes a brightness value Y, a first color difference value Cb, and a second color difference value Cr.
  • Y is lumens (luminance), which represents the density of light and is non-linear, using gamma correction (gamma correction) encoding processing, Cb is the concentration offset component of blue, and Cr is the concentration offset component of red .
  • the image processing device when the image processing device determines the color adjustment parameters corresponding to each image based on the color information of the feature points of the multiple images with the same name, it may be based on the first color corresponding to the feature points of the multiple images with the same name. Spatial value, determining the second color space value corresponding to the feature points of the multiple images with the same name, and determining the color adjustment parameter corresponding to each image according to the second color space value corresponding to the feature points of the multiple images with the same name .
  • the image processing device can correspond to the feature points Pi of the two images with the same name Determine the YCbCr color space value corresponding to the feature point Pi of the two images with the same name, and determine the color adjustment parameter corresponding to each image according to the YCbCr color space value corresponding to the feature point with the same name of the two images .
  • the first color space value is an RGB color space value
  • the second color space value is a YCbCr color space value. Color space value.
  • the RGB color space values corresponding to the feature points of the multiple images with the same name can be converted into YCbCr colors according to a preset conversion formula Spatial value.
  • the preset conversion formula is shown in the following formula (1):
  • the image processing device when it determines the second color space value corresponding to the feature points of the multiple images according to the first color space values corresponding to the feature points of the multiple images, it may The first color space values corresponding to the feature points of the multiple images with the same name are calculated, the first color space average values corresponding to the feature points with the same names of the multiple images are calculated, and the first color space average values are converted to obtain the multiple The second color space value corresponding to the feature point of the image with the same name.
  • the first color space average value includes the average value of the red value R, the average value of the green value G, and the average value of the blue value B in the RGB color space.
  • the image processing device may convert the calculated RGB mean values corresponding to the feature points of the multiple images with the same name according to formula (1) to obtain the corresponding feature points of the multiple images. YCbCr color space value.
  • the image processing device can target these two images.
  • three YCbCr color space values of Y_ij, Cb_ij and Cr_ij are obtained.
  • the image processing device can calculate the average value of the three color values R_ji, G_ji, and B_ji of the image image_j for all the feature points of the same name on the two images, and calculate the average value R_ji of the three color values corresponding to image_j, G_ji, B_ji are brought into the above formula (1) and converted to YCbCr color space, thereby obtaining three YCbCr color space values of Y_ji, Cb_ji, and Cr_ji.
  • the color adjustment parameter includes a brightness adjustment parameter, a first color adjustment parameter, and a second color adjustment parameter; the image processing device is based on the second color space value corresponding to the feature points of the multiple images with the same name,
  • the brightness adjustment parameters corresponding to the respective images may be determined according to the brightness values corresponding to the feature points of the multiple images with the same name; and, according to the features with the same names of the multiple images
  • the first color difference value corresponding to the point determine the first color adjustment parameter corresponding to each image; and, determine the first color difference value corresponding to each image according to the second color difference value corresponding to the feature points of the multiple images 2.
  • the image processing device may adjust the color of each image according to the color adjustment parameter corresponding to each image, so that the adjusted multiple images meet the preset color uniformity requirement.
  • the meeting the color uniformity requirement includes that the brightness difference of the multiple images is less than a preset brightness difference threshold.
  • the image processing device may adjust the color of each image by using a gamma correction method according to the color adjustment parameter of each image.
  • a gamma correction method according to the color adjustment parameter of each image.
  • the calculated color adjustment parameter can be brought into the ⁇ of the function for calculation, and the result of the gamma correction is output to realize the image correction.
  • the multiple images may be images collected by an image capture device on a drone, and the image processing device may generate an orthophoto or a real image based on the multiple images after color adjustment.
  • the color-adjusted image makes the imaging of the same scene on different images more consistent, which can improve the effect of image-based applications.
  • FIG. 3a is a schematic diagram of an image interface provided by an embodiment of the present invention
  • FIG. 3b is a schematic diagram of an adjusted image interface provided by an embodiment of the present invention.
  • the image processing device can determine the color adjustment parameters corresponding to Figure 3a according to the above method, and adjust Figure 3a according to the color adjustment parameters to obtain the image shown in Figure 3b The image shown.
  • the image processing device can determine feature points of the same name of multiple images, determine the color adjustment parameters corresponding to each image based on the color information of the feature points of the same name of the multiple images, and determine the color adjustment parameters corresponding to each image according to the color information corresponding to each image.
  • the adjustment parameter adjusts the color of each image.
  • FIG. 4 is a schematic flowchart of another image processing method provided by an embodiment of the present invention.
  • the method may be executed by an image processing device, wherein the specific explanation of the image processing device is as described above.
  • the difference between the embodiment of the present invention and the embodiment described in FIG. 2 is that the embodiment of the present invention is a schematic description of the process of determining the color adjustment parameters on the image processing device.
  • S401 Determine feature points with the same name of multiple images.
  • the image processing device can determine feature points of the same name of multiple images, and the specific implementation is as described above.
  • S402 Determine a second color space value corresponding to the feature points of the multiple images with the same name according to the first color space value corresponding to the feature points of the multiple images.
  • the image processing device may determine the second color space value corresponding to the feature points of the multiple images corresponding to the feature points of the multiple images according to the first color space values corresponding to the feature points of the multiple images.
  • the first color space value is an RGB color space value
  • the second color space value is a YCbCr color space value.
  • the color space value when determining the second color space value corresponding to the feature points of the multiple images with the same name, the RGB color space values corresponding to the feature points of the multiple images with the same name can be converted into YCbCr colors according to the above formula (1) Spatial value.
  • the image processing device when the image processing device determines the second color space value corresponding to the feature points of the multiple images according to the first color space values corresponding to the feature points of the multiple images, it may The first color space values corresponding to the feature points of the multiple images with the same name are calculated, the first color space average values corresponding to the feature points with the same names of the multiple images are calculated, and the first color space average values are converted to obtain the multiple The second color space value corresponding to the feature point of the image with the same name.
  • the specific embodiments are as described above, and will not be repeated here.
  • S403 Determine a color adjustment parameter corresponding to each image according to the second color space value corresponding to the feature points of the multiple images with the same name.
  • the image processing device may determine the color adjustment parameter corresponding to each image according to the second color space value corresponding to the feature points of the multiple images with the same name.
  • the second color space value includes a brightness value, a first color difference value, and a second color difference value.
  • the color adjustment parameter includes a brightness adjustment parameter, a first color adjustment parameter, and a second color adjustment parameter.
  • the image processing device may establish a target based on the color information of the feature points of the multiple images with the same name. Function, and determine the color adjustment parameters corresponding to each image by optimizing the objective function.
  • the embodiment of the present invention does not specifically limit the objective function.
  • the image processing device may determine the brightness adjustment parameter corresponding to each image according to the brightness value corresponding to the feature points of the same name of the multiple images.
  • the image processing device may establish a first objective function based on the brightness values corresponding to the feature points of the multiple images with the same name, and determine the brightness adjustment parameters corresponding to the respective images by optimizing the first objective function.
  • the brightness value is the brightness value Y in the YCbCr color space
  • the first objective function is as shown in formula (2):
  • n is the number of images
  • ⁇ i is the brightness adjustment parameter of the i-th image
  • ⁇ j is the brightness adjustment parameter of the j-th image
  • ⁇ N and ⁇ g are two constants used to control the intensity of color adjustment Weak (the smaller ⁇ g is relative to ⁇ N , the weaker the color adjustment is)
  • B i,j ln(Y ij )
  • Y ij is the image pair i, j of all feature points with the same name on the i-th image
  • the average value of the three color values R_ij, G_ij, B_ij is calculated according to formula (1) to obtain the brightness value Y corresponding to the feature point of the i-th image with the same name.
  • B j,i ln(Y ji )
  • Y ji is the average value of the three color values R_ji, G_ji, B_ji of all feature points with the same name on the image pair i, j on the j-th image, calculated according to formula (1)
  • the brightness value Y corresponding to the feature point with the same name in the j-th image.
  • the image processing device may determine the first color adjustment parameter corresponding to each image according to the first color difference value corresponding to the feature points of the multiple images with the same name.
  • the image processing device may establish a second objective function based on the first color difference values corresponding to the feature points of the multiple images with the same name, and determine the first objective function corresponding to each image by optimizing the second objective function.
  • Color adjustment parameters In some embodiments, the first color difference value is the first color difference value Cb in the YCbCr color space, and the second objective function is as shown in formula (3):
  • n is the number of images
  • ⁇ i is the first color adjustment parameter of the i-th image
  • ⁇ j is the first color adjustment parameter of the j-th image
  • ⁇ N and ⁇ g are two constants used to control the color Adjust the intensity of intensity (the smaller the ⁇ g relative to ⁇ N , the weaker the intensity of the color adjustment)
  • the average value of the color values R_ij, G_ij, B_ij is the first color difference value Cb corresponding to the feature point of the i-th image calculated according to formula (1)
  • the average value R_ji, G_ji, B_ji of the three color values of all feature points with the same name on the j-th image
  • the image processing device may determine the second color adjustment parameter corresponding to each image according to the second color difference value corresponding to the feature points of the multiple images with the same name.
  • the image processing device may establish a third objective function based on the second color difference values corresponding to the feature points of the multiple images with the same name, and determine the second objective function corresponding to each image by optimizing the third objective function.
  • Color adjustment parameters In some embodiments, the second color difference value is the second color difference value Cr in the YCbCr color space, and the third objective function is as shown in formula (4):
  • n is the number of images
  • ⁇ i is the second color adjustment parameter of the i-th image
  • ⁇ j is the second color adjustment parameter of the j-th image
  • ⁇ N and ⁇ g are two constants used to control the color Adjust the intensity of intensity (the smaller the ⁇ g relative to ⁇ N , the weaker the intensity of color adjustment)
  • the average value of the color values R_ij, G_ij, B_ij is the second color difference value Cr of the i-th image calculated according to formula (1)
  • the average value R_ji, G_ji, B_ji of the three color values on the j-th image is calculated according to the formula (1) to obtain the
  • the color adjustment parameters are calculated by using the color information of the feature points with the same name between the two images in a plurality of images, and only the color information of the feature points with the same name needs to be stored, which reduces the memory required for image processing. There is no need to use an image as a reference image, avoiding the cumulative shift of color adjustment, realizing global color adjustment, and avoiding repeated reading of the same image, improving image processing efficiency.
  • the image processing device may adjust the color of each image according to the color adjustment parameter corresponding to each image, so that the adjusted multiple images meet the preset color uniformity requirement.
  • meeting the color uniformity requirement includes that the brightness difference of the multiple images is less than a preset brightness difference threshold.
  • the image processing device can adjust each image according to the color adjustment parameters corresponding to each image.
  • the color of the image is adjusted so that the adjusted images have color consistency.
  • the gamma correction method can be used to adjust the color of each image.
  • the image processing device may determine the feature points of the multiple images with the same name, and according to the first color space value corresponding to the feature points of the multiple images with the same name, determine which feature points of the multiple images correspond to The second color space value, and the second color space value corresponding to the feature points of the multiple images with the same name, determine the color adjustment parameter corresponding to each image, so that the color adjustment parameter corresponding to each image is Adjust the color of each image.
  • FIG. 5 is a schematic structural diagram of an image processing device according to an embodiment of the present invention.
  • the image processing device includes: a memory 501, a processor 502, and a data interface 503.
  • the memory 501 may include a volatile memory (volatile memory); the memory 501 may also include a non-volatile memory (non-volatile memory); the memory 501 may also include a combination of the foregoing types of memories.
  • the processor 502 may be a central processing unit (CPU).
  • the processor 502 may further include a hardware image processing device.
  • the foregoing hardware image processing device may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. For example, it may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), or any combination thereof.
  • ASIC application-specific integrated circuit
  • PLD programmable logic device
  • FPGA field-programmable gate array
  • the memory 501 is used to store program instructions.
  • the processor 502 can call the program instructions stored in the memory 501 to perform the following steps:
  • the color of each image is adjusted according to the color adjustment parameter corresponding to each image.
  • the processor 502 determines the color adjustment parameters corresponding to each image based on the color information of the feature points with the same name of the multiple images, it is specifically configured to:
  • the processor 502 determines the second color space value corresponding to the feature points of the multiple images with the same name according to the first color space values corresponding to the feature points of the multiple images, it is specifically configured to:
  • the second color space value includes a brightness value, a first color difference value and a second color difference value.
  • the color adjustment parameter includes a brightness adjustment parameter, a first color adjustment parameter, and a second color adjustment parameter; the processor 502 determines the second color space value corresponding to the feature points of the multiple images with the same name.
  • the color adjustment parameters corresponding to each image it is specifically used for:
  • the processor 502 determines the brightness adjustment parameter corresponding to each image according to the brightness value corresponding to the feature points of the same name of the multiple images, it is specifically configured to:
  • the brightness adjustment parameters corresponding to the respective images are determined by optimizing the first objective function.
  • the processor 502 determines the first color adjustment parameter corresponding to each image according to the first color difference value corresponding to the feature points of the multiple images with the same name, it is specifically configured to:
  • the first color adjustment parameter corresponding to each image is determined by optimizing the second objective function.
  • the processor 502 determines the second color adjustment parameter corresponding to each image according to the second color difference values corresponding to the feature points of the multiple images with the same name, it is specifically configured to:
  • the second color adjustment parameter corresponding to each image is determined by optimizing the third objective function.
  • the first color space value includes a red value, a blue value and a green value.
  • processor 502 determines feature points with the same name of multiple images, it is specifically configured to:
  • the feature points of the multiple images are acquired, and feature matching is performed on the feature points of the multiple images to determine the feature points of the multiple images with the same name.
  • the processor 502 determines the color adjustment parameters corresponding to each image based on the color information of the feature points with the same name of the multiple images, it is specifically configured to:
  • the color adjustment parameters corresponding to the respective images are determined by optimizing the objective function.
  • processor 502 adjusts the color of each image according to the color adjustment parameter of each image, it is specifically configured to:
  • the color of each image is adjusted by a gamma correction method.
  • the multiple images are images collected by an image collection device on a drone, and the processor 502 is further configured to:
  • An orthophoto or a real image is generated based on the multiple images after color adjustment.
  • the image processing device may determine feature points of the same name of multiple images, determine the color adjustment parameters corresponding to each image based on the color information of the feature points of the same name of the multiple images, and determine the color adjustment parameters corresponding to each image according to the corresponding
  • the color adjustment parameters adjust the color of each image.
  • the embodiment of the present invention also provides an image processing system, the image processing system includes an unmanned aerial vehicle and an image processing device, and the unmanned aerial vehicle is provided with an image acquisition device;
  • the image acquisition device is configured to acquire multiple images during the movement of the drone, and send the multiple images acquired to the image processing device;
  • the image processing device is used to determine the feature points of the multiple images with the same name; determine the color adjustment parameters corresponding to each image based on the color information of the feature points of the multiple images with the same name; adjust the color corresponding to each image The parameters adjust the color of each image.
  • the image processing device determines the color adjustment parameter corresponding to each image based on the color information of the feature points of the same name of the multiple images, it is specifically used for:
  • the image processing device determines the second color space value corresponding to the feature points of the multiple images with the same name according to the first color space values corresponding to the feature points of the multiple images, it is specifically configured to:
  • the second color space value includes a brightness value, a first color difference value and a second color difference value.
  • the color adjustment parameter includes a brightness adjustment parameter, a first color adjustment parameter, and a second color adjustment parameter; the image processing device determines according to the second color space value corresponding to the feature points of the multiple images with the same name
  • the color adjustment parameters corresponding to each image are specifically used for:
  • the second color adjustment parameter corresponding to each image is determined according to the second color difference values corresponding to the feature points of the multiple images with the same name.
  • the image processing device determines the brightness adjustment parameter corresponding to each image according to the brightness value corresponding to the feature points of the multiple images with the same name, it is specifically configured to:
  • the brightness adjustment parameters corresponding to the respective images are determined by optimizing the first objective function.
  • the image processing device determines the first color adjustment parameter corresponding to each image according to the first color difference value corresponding to the feature points of the multiple images with the same name, it is specifically configured to:
  • the first color adjustment parameter corresponding to each image is determined by optimizing the second objective function.
  • the image processing device determines the second color adjustment parameter corresponding to each image according to the second color difference values corresponding to the feature points of the multiple images with the same name, it is specifically configured to:
  • the second color adjustment parameter corresponding to each image is determined by optimizing the third objective function.
  • the first color space value includes a red value, a blue value and a green value.
  • the image processing device is specifically used for determining feature points of the same name in multiple images:
  • the feature points of the multiple images are acquired, and feature matching is performed on the feature points of the multiple images to determine the feature points of the multiple images with the same name.
  • the image processing device determines the color adjustment parameter corresponding to each image based on the color information of the feature points of the same name of the multiple images, it is specifically used for:
  • the color adjustment parameters corresponding to the respective images are determined by optimizing the objective function.
  • the image processing device adjusts the color of each image according to the color adjustment parameter of each image, it is specifically configured to:
  • the color of each image is adjusted by a gamma correction method.
  • the multiple images are images collected by an image collection device on a drone, and the image processing device is also used for:
  • An orthophoto or a real image is generated based on the multiple images after color adjustment.
  • the image acquisition device on the drone can send multiple images collected during the movement of the drone to the image processing device, and the image processing device can determine the features of the multiple images with the same name Point, determine the color adjustment parameter corresponding to each image based on the color information of the feature points with the same name of the multiple images, and adjust the color of each image according to the color adjustment parameter corresponding to each image.
  • the image processing device can determine the features of the multiple images with the same name Point, determine the color adjustment parameter corresponding to each image based on the color information of the feature points with the same name of the multiple images, and adjust the color of each image according to the color adjustment parameter corresponding to each image.
  • the embodiment of the present invention also provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to realize the image described in the embodiment of the present invention in FIG. 2 or FIG. 4
  • the processing method can also implement the device in the embodiment corresponding to FIG. 5 of the present invention, and will not be repeated here.
  • the computer-readable storage medium may be an internal storage unit of the device described in any of the foregoing embodiments, such as a hard disk or memory of the device.
  • the computer-readable storage medium may also be an external storage device of the device, such as a plug-in hard disk equipped on the device, a Smart Media Card (SMC), or a Secure Digital (SD) card. , Flash Card, etc.
  • the computer-readable storage medium may also include both an internal storage unit of the device and an external storage device.
  • the computer-readable storage medium is used to store the computer program and other programs and data required by the device.
  • the computer-readable storage medium can also be used to temporarily store data that has been output or will be output.
  • the program can be stored in a computer readable storage medium. During execution, it may include the procedures of the above-mentioned method embodiments.
  • the storage medium may be a magnetic disk, an optical disc, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Processing (AREA)

Abstract

本发明实施例提供了一种图像处理方法、设备、***及存储介质,其中,方法包括:确定多个图像的同名特征点;基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数;根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整。通过这种方式,实现了对多个图像的全局色彩调整,使得调整后的多个图像具有色彩一致性,避免了色彩失真,提高了图像处理的效率。

Description

一种图像处理方法、设备、***及存储介质 技术领域
本发明涉及图像处理技术领域,尤其涉及一种图像处理方法、设备、***及存储介质。
背景技术
目前,图像采集设备在不同的环境(如光照不同)下采集具有相同图像区域的多个图像时,会由于环境的不同而导致具有相同图像区域的各图像的颜色、亮度等不一致。目前,为了解决这类问题常采用直方图匹配的方式对具有相同图像区域的多个图像进行处理。这种处理方式容易导致颜色的累计偏移,处理后容易存在较大的色差,处理速度较慢,不能很好的解决该问题。
发明内容
本发明实施例提供了一种图像处理方法、设备、***及存储介质,可实现对图像的全局色彩调整,提高了图像处理的效率。
第一方面,本发明实施例提供了一种图像处理方法,所述方法包括:
确定多个图像的同名特征点;
基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数;
根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整。
第二方面,本发明实施例提供了一种图像处理设备,包括存储器和处理器;
所述存储器,用于存储程序指令;
所述处理器,用于调用所述程序指令,当所述程序指令被执行时,用于执行以下操作:
确定多个图像的同名特征点;
基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数;
根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整。
第三方面,本发明实施例提供了一种图像处理***,包括:无人机和图像 处理设备,所述无人机上设置有图像采集设备;
所述无人机,用于通过所述图像采集设备在所述无人机移动的过程中采集多个图像,并将采集到的所述多个图像发送给所述图像处理设备;
所述图像处理设备,用于确定所述多个图像的同名特征点;基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数;根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整。
第四方面,本发明实施例提供了一种计算机可读存储介质,该计算机可读存储介质存储有计算机程序,该计算机程序被处理器执行时实现如上述第一方面所述的图像处理方法。
本发明实施例中,图像处理设备通过确定多个图像的同名特征点,基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数,并根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整,可以实现对多个图像的全局色彩调整,使得调整后的多个图像具有色彩一致性,提高了图像处理的效率。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1是本发明实施例提供的一种图像处理***的结构示意图;
图2是本发明实施例提供的一种图像处理方法的流程示意图;
图3a是本发明实施例提供的一种图像的界面示意图;
图3b是本发明实施例提供的一种调整后的图像的界面示意图;
图4是本发明实施例提供的另一种图像处理方法的流程示意图;
图5是是本发明实施例提供的一种图像处理设备的结构示意图。
具体实施方式
下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分实施例,而不是 全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
下面结合附图,对本发明的一些实施方式作详细说明。在不冲突的情况下,下述的实施例及实施例中的特征可以相互组合。
本发明实施例中提供的图像处理方法可以由一种图像处理***执行,所述图像处理***可以包括无人机和图像处理设备。在某些实施例中,所述无人机上设置有图像采集设备;在某些实施例中,所述图像采集设备可以是挂载在无人机的云台上的相机,所述图像采集设备也可以是其他具有图像采集功能的设备,本发明实施例不做具体限定。在一些实施例中,所述图像采集设备用于在所述无人机移动的过程中采集图像,并发送给图像处理设备;所述图像处理设备用于对所述图像采集设备采集的图像进行处理。在某些实施例中,所述图像处理设备可以设置在所述无人机上;在某些实施例中,所述图像处理设备可以独立于所述无人机。示例的,该图像处理设备可以是地面图像处理设备。在一种实施方式中,该图像处理设备还可以设置在云处理器中。在其他实施例中,所述图像处理***可以设置在无人机、机器人、移动终端(如手机)等设备上。下面结合附图1对由无人机和图像处理设备组成的图像处理***进行示意性说明。
请参见图1,图1是本发明实施例提供的一种图像处理***的结构示意图,如图1所示的图像处理***包括:无人机11和图像处理设备12,所述无人机11上设置有图像采集设备111,所述无人机11可以为旋翼型无人机,例如,四旋翼无人机、六旋翼无人机、八旋翼无人机,也可以是固定翼无人机等。所述无人机11包括动力***112,所述动力***112用于为无人机11提供飞行的动力。
本发明实施例中,所述图像采集设备111可以在所述无人机11移动的过程中采集多个图像,并将所述采集到的多个图像发送给图像处理设备12,所述图像处理设备12在接收到图像采集设备111发送的多个图像后,可以对所述多个图像进行处理。在某些实施例中,所述多个图像包括有共视区域的图像。可选的,所述多个图像中可以是两两有共视区域,或一个图像与至少两个图像有共视区域,或多个图像之间均有共视区域,本发明实施例不做具体限定。其中,图像有共视区域是指图像之间存在至少部分相互重叠的图像区域。
在一个实施例中,所述图像处理设备12在对所述图像进行处理时,可以确定所述多个图像的同名特征点,并基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数,以及根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整。本发明实施例可以实现对多个图像的全局色彩调整,使得调整后的多个图像具有色彩一致性,提高了图像处理的效率。
下面结合附图对本发明实施例提供的图像处理方法进行示意性说明。
请参见图2,图2是本发明实施例提供的一种图像处理方法的流程示意图,所述方法可以由图像处理设备执行,其中,所述图像处理设备的具体解释如前所述。具体地,本发明实施例的所述方法包括如下步骤。
S201:确定多个图像的同名特征点。
本发明实施例中,图像处理设备可以确定多个图像的同名特征点。在某些实施例中,所述多个图像包括有共视区域的图像。可选的,所述多个图像中可以是两两有共视区域,或其中一个图像与至少两个图像有共视区域,或多个图像之间均有共视区域,本发明实施例不做具体限定。其中,图像有共视区域是指图像之间存在至少部分相互重叠的图像区域。
在一个实施例中,所述图像处理设备在确定多个图像的同名特征点时,可以获取所述多个图像的特征点,并对所述多个图像的特征点进行特征匹配以确定所述多个图像的同名特征点。通过确定各图像之间的同名特征点,以便后续对各同名特征点所在图像区域的色彩进行调整,从而确保各图像中同名特征点所在图像区域的色彩一致。
在某些实施例中,所述多个图像的同名特征点是指在特征提取与特征匹配过程中,从所述多个图像中有共视区域的图像中提取到的,且匹配成功的特征点。例如,假设多个图像中n(n>1)个图像中存在共视区域,则图像处理设备可以对n个图像进行特征提取和特征匹配,以便确定出各图像的共视区域中的同名特征点。在特征提取与特征匹配的过程中,如果同一物体P在不同的图像上的成像为p i,若p i在不同图像上均被视为特征点提取出来,并且在匹配的过程中成功的匹配,则该点p i被称为同名特征点。
S202:基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数。
本发明实施例中,图像处理设备可以基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数。在某些实施例中,所述色彩信息包括第一色彩空间值和第二色彩空间值。
在某些实施例中,所述第一色彩空间值为RGB色彩空间,所述RGB色彩空间包括红色、绿色为和蓝色三个通道,第一色彩空间值包括红色值R,绿色值G,蓝色值B。在某些实施例中,所述第二色彩空间为YCbCr色彩空间,所述YCbCr色彩空间值包括亮度,第一色差和第二色差三个通道。所述第二色彩空间值包括亮度值Y,第一色差值Cb和第二色差值Cr。其中,Y是流明(luminance),表示光的浓度且为非线性,使用伽马修正(gamma correction)编码处理,Cb为蓝色的浓度偏移量成份,Cr则为红色的浓度偏移量成份。
在一个实施例中,图像处理设备在基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数时,可以根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值,以及根据所述多个图像的同名特征点对应的第二色彩空间值,确定所述各个图像对应的色彩调整参数。例如,假设两个图像的同名特征点为Pi,Pi对应的第一色彩空间为RGB色彩空间,第二色彩空间为YCbCr色彩空间,则图像处理设备可以根据这两个图像的同名特征点Pi对应的RGB色彩空间值,确定这两个图像的同名特征点Pi对应的YCbCr色彩空间值,以及根据这两个图像的同名特征点对应的YCbCr色彩空间值,确定所述各个图像对应的色彩调整参数。
在一些实施例中,所述第一色彩空间值为RGB色彩空间值,第二色彩空间值为YCbCr色彩空间值,所述图像处理设备在根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值时,可以根据预设的转换公式将所述多个图像的同名特征点对应的RGB色彩空间值转换为YCbCr色彩空间值。
在某些实施例中,所述预设的转换公式如下公式(1)所示:
Y=0.299R+0.578G+0.114B
Cb=0.564(B-Y)
Cr=0.713(B-Y)           (1)
在一个实施例中,图像处理设备在根据所述多个图像的同名特征点对应的 第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值时,可以根据所述多个图像的同名特征点对应的第一色彩空间值,计算所述多个图像的同名特征点对应的第一色彩空间均值,以及对所述第一色彩空间均值进行转换得到所述多个图像的同名特征点对应的第二色彩空间值。在某些实施例中,所述第一色彩空间均值包括RGB色彩空间中红色值R的平均值、绿色值G的平均值、蓝色值B的平均值。在某些实施例中,所述图像处理设备可以根据公式(1)对计算得到的所述多个图像的同名特征点对应的RGB均值进行转换,得到所述多个图像的同名特征点对应的YCbCr色彩空间值。
例如,假设所述第一色彩空间为RGB色彩空间,所述第二色彩空间为YCbCr色彩空间,如果获取到两个包括共视区域的图像分别为image_i,image_j,则图像处理设备可以针对这两个图像上的所有同名特征点,计算图像image_i对应的三个颜色值的平均值R_ij,G_ij,B_ij,并将平均值R_ij,G_ij,B_ij带入上述公式(1),转换到YCbCr色彩空间,从而得到Y_ij,Cb_ij,Cr_ij三个YCbCr色彩空间值。同理,图像处理设备可以针对这两个图像上的所有同名特征点,计算图像image_j的三个颜色值的平均值R_ji,G_ji,B_ji,并将image_j对应的三个颜色值的平均值R_ji,G_ji,B_ji带入上述公式(1),转换到YCbCr色彩空间,从而得到Y_ji,Cb_ji,Cr_ji三个YCbCr色彩空间值。
在一个实施例中,所述色彩调整参数包括亮度调整参数、第一颜色调整参数和第二颜色调整参数;图像处理设备在根据所述多个图像的同名特征点对应的第二色彩空间值,确定所述各个图像对应的色彩调整参数时,可以根据所述多个图像的同名特征点对应的亮度值,确定所述各个图像对应的亮度调整参数;以及,根据所述多个图像的同名特征点对应的第一色差值,确定所述各个图像对应的第一颜色调整参数;以及,根据所述多个图像的同名特征点对应的第二色差值,确定所述各个图像对应的第二颜色调整参数。
S203:根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整。
本发明实施例中,图像处理设备可以根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整,以使得调整后的所述多个图像满足预设色彩均匀度要求。可选的,所述满足色彩均匀度要求包括所述多个图像的亮度差 值小于预设亮度差阈值。通过这种实施方式,可以实现对图像的亮度和颜色进行调整,使得调整后的多个图像具有色彩一致性,避免了RGB色彩空间中各个通道单独处理后融合导致的色彩失真现象。
在一个实施例中,图像处理设备可以根据所述各个图像的色彩调整参数,采用伽马校正的方法对所述各个图像的色彩进行调整。通过这种实施方式对各图像的色彩进行调整,可以使图像的亮度平滑过渡,不存在亮度溢出灰度上下界的情况,并且伽马校正基于图像均值进行调整,只需少量的观测即可得到较为可靠的结果,同时具备一定的抗噪点或误匹配能力,每个图像只需三个参数调整,对于大规模的数据处理极大的减小了运算量。
在某些实施例中,所述伽马校正是利用函数对某一灰度值进行映射的过程,所述函数为:Value out=Value in γ。图像处理设备在采用伽马校正的方法对所述各个图像的色彩进行调整时,可以将计算得到的色彩调整参数带入该函数的γ中进行计算,输出伽马校正的结果,以实现对图像的伽马校正。
在一些实施例中,所述多个图像可以为无人机上的图像采集设备采集到的图像,图像处理设备可以基于色彩调整后的所述多个图像生成正射影像或真正射影像。通过这种实施方式,经过色彩调整的图像使得同一场景在不同图像上的成像更加一致,能够提高基于图像的应用的效果。
以图3a和3b为例进行说明,图3a是本发明实施例提供的一种图像的界面示意图,图3b是本发明实施例提供的一种调整后的图像的界面示意图。假设无人机上的图像采集设备采集到图3a所示的图像,则图像处理设备可以根据上述方法确定图3a对应的色彩调整参数,并根据该色彩调整参数对图3a进行调整,得到图3b所示的图像。
本发明实施例中,图像处理设备可以确定多个图像的同名特征点,基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数,根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整。通过这种实施方式,实现了对多个图像的全局色彩调整,使得调整后的多个图像具有色彩一致性,避免了色彩失真,提高了图像处理的效率。
请参见图4,图4是本发明实施例提供的另一种图像处理方法的流程示意图,所述方法可以由图像处理设备执行,其中,所述图像处理设备的具体解释 如前所述。本发明实施例与上述图2所述实施例的区别在于,本发明实施例是对图像处理设备上的色彩调整参数的确定过程的示意性说明。
S401:确定多个图像的同名特征点。
本发明实施例中,所述图像处理设备可以确定多个图像的同名特征点,具体实施例如前所述。
S402:根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值。
本发明实施例中,所述图像处理设备可以根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值。
在一些实施例中,所述第一色彩空间值为RGB色彩空间值,第二色彩空间值为YCbCr色彩空间值,所述图像处理设备在根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值时,可以根据上述公式(1)将所述多个图像的同名特征点对应的RGB色彩空间值转换为YCbCr色彩空间值。
在一个实施例中,图像处理设备在根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值时,可以根据所述多个图像的同名特征点对应的第一色彩空间值,计算所述多个图像的同名特征点对应的第一色彩空间均值,以及对所述第一色彩空间均值进行转换得到所述多个图像的同名特征点对应的第二色彩空间值。具体实施例举例如前所述,此处不再赘述。
S403:根据所述多个图像的同名特征点对应的第二色彩空间值,确定所述各个图像对应的色彩调整参数。
本发明实施例中,所述图像处理设备可以根据所述多个图像的同名特征点对应的第二色彩空间值,确定所述各个图像对应的色彩调整参数。
在某些实施例中,所述第二色彩空间值包括亮度值、第一色差值和第二色差值。在某些实施例中,所述色彩调整参数包括亮度调整参数、第一颜色调整参数和第二颜色调整参数。
在一个实施例中,图像处理设备在基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数时,可以基于所述多个图像的同名特 征点的色彩信息建立目标函数,并通过优化所述目标函数确定所述各个图像对应的色彩调整参数,本发明实施例对所述目标函数不做具体限定。
在一个实施例中,图像处理设备可以根据所述多个图像的同名特征点对应的亮度值,确定所述各个图像对应的亮度调整参数。具体实施例中,图像处理设备可以基于所述多个图像的同名特征点对应的亮度值建立第一目标函数,并通过优化所述第一目标函数确定所述各个图像对应的亮度调整参数。在某些实施例中,所述亮度值为YCbCr色彩空间中的亮度值Y,所述第一目标函数如公式(2)所示:
Figure PCTCN2019077702-appb-000001
其中,n为图像个数,γ i为第i张图像的亮度调整参数,γ j为第j张图像的亮度调整参数,δ N,δ g为两个常量,用于控制色彩调整力度的强弱(δ g相对于δ N越小则色彩调整的力度越弱),B i,j=ln(Y ij),Y ij是图像对i,j的所有同名特征点在第i张图像上的三个颜色值的平均值R_ij,G_ij,B_ij根据公式(1)计算得到的第i张图像的同名特征点对应的亮度值Y。B j,i=ln(Y ji),Y ji是图像对i,j的所有同名特征点在第j张图像上的三个颜色值的平均值R_ji,G_ji,B_ji根据公式(1)计算得到的第j张图像的同名特征点对应的亮度值Y。通过最小化E1的值即可得到第i张图像的亮度调整参数γ i,以及第j张图像的亮度调整参数γ j
在一个实施例中,图像处理设备可以根据所述多个图像的同名特征点对应的第一色差值,确定所述各个图像对应的第一颜色调整参数。具体实施例中,图像处理设备可以基于所述多个图像的同名特征点对应的第一色差值建立第二目标函数,并通过优化所述第二目标函数确定所述各个图像对应的第一颜色调整参数。在某些实施例中,所述第一色差值为YCbCr色彩空间中的第一色差值Cb,所述第二目标函数如公式(3)所示:
Figure PCTCN2019077702-appb-000002
其中,n为图像个数,α i为第i张图像的第一颜色调整参数,α j为第j张图像的第一颜色调整参数,δ N,δ g为两个常量,用于控制色彩调整力度的强弱(δ g相对于δ N越小则色彩调整的力度越弱),S i,j=Cb_ij,Cb_ij是图像对i,j 的所有同名特征点在第i张图像上的三个颜色值的平均值R_ij,G_ij,B_ij根据公式(1)计算得到的第i张图像的同名特征点对应的第一色差值Cb;S j,i=Cb_ji,Cb_ji是图像对i,j的所有同名特征点在第j张图像上的三个颜色值的平均值R_ji,G_ji,B_ji根据公式(1)计算得到的第j张图像的第一色差值Cb。通过最小化E2的值即可得到第i张图像的第一颜色调整参数α i,以及第j张图像的第一颜色调整参数α j
在一个实施例中,图像处理设备可以根据所述多个图像的同名特征点对应的第二色差值,确定所述各个图像对应的第二颜色调整参数。具体实施例中,图像处理设备可以基于所述多个图像的同名特征点对应的第二色差值建立第三目标函数,并通过优化所述第三目标函数确定所述各个图像对应的第二颜色调整参数。在某些实施例中,所述第二色差值为YCbCr色彩空间中的第二色差值Cr,所述第三目标函数如公式(4)所示:
Figure PCTCN2019077702-appb-000003
其中,n为图像个数,β i为第i张图像的第二颜色调整参数,β j为第j张图像的第二颜色调整参数,δ N,δ g为两个常量,用于控制色彩调整力度的强弱(δ g相对于δ N越小则色彩调整的力度越弱),S i,j=Cr_ij,Cr_ij是图像对i,j的所有同名特征点在第i张图像上的三个颜色值的平均值R_ij,G_ij,B_ij根据公式(1)计算得到的第i张图像的的第二色差值Cr;S j,i=Cr_ji,Cr_ji是图像对i,j的所有同名特征点在第j张图像上的三个颜色值的平均值R_ji,G_ji,B_ji根据公式(1)计算得到的第j张图像的的第二色差值Cr。通过最小化E3的值即可得到第i张图像的第二颜色调整参数β i,以及第j张图像的第二颜色调整参数β j
本发明实施例,通过在多个图像中的两两图像之间的同名特征点的色彩信息,来计算色彩调整参数,只需要存储同名特征点的色彩信息,减小了图像处理所需的内存空间,并且不需要以一个图像作为参考图像,避免了色彩调整的累计偏移,实现了全局色彩调整,也避免了重复读取同一个图像,提高了图像处理效率。
S404:根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整。
本发明实施例中,图像处理设备可以根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整,以使得调整后的所述多个图像满足预设色彩均匀度要求。可选的,满足色彩均匀度要求包括所述多个图像的亮度差值小于预设亮度差阈值。通过这种实施方式,可以实现对图像的亮度和颜色进行调整,使得调整后的多个图像具有色彩一致性,避免了RGB通道各个通道单独处理后融合导致的色彩失真现象。
例如,假设两个图像image_i,image_j的色彩调整参数为γ i、α i、β i,和γ j、α j、β j,则所述图像处理设备可以根据各个图像对应的色彩调整参数对各个图像的色彩进行调整,以使得调整后的各图像具有色彩一致性。示例的,可采用伽马校正的方法对各个图像的色彩进行调整。
本发明实施例中,图像处理设备可以确定多个图像的同名特征点,并根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值,以及根据所述多个图像的同名特征点对应的第二色彩空间值,确定所述各个图像对应的色彩调整参数,从而根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整。通过这种实施方式,实现了对多个图像的全局色彩调整,使得调整后的所述多个图像具有色彩一致性,避免了色彩失真,提高了图像处理的效率。
请参见图5,图5是是本发明实施例提供的一种图像处理设备的结构示意图。具体的,所述图像处理设备包括:存储器501、处理器502以及数据接口503。
所述存储器501可以包括易失性存储器(volatile memory);存储器501也可以包括非易失性存储器(non-volatile memory);存储器501还可以包括上述种类的存储器的组合。所述处理器502可以是中央处理器(central processing unit,CPU)。所述处理器502还可以进一步包括硬件图像处理设备。上述硬件图像处理设备可以是专用集成电路(application-specific integrated circuit,ASIC),可编程逻辑器件(programmable logic device,PLD)或其组合。具体例如可以是复杂可编程逻辑器件(complex programmable logic device,CPLD),现场可编程逻辑门阵列(field-programmable gate array,FPGA)或其任意组合。
进一步地,所述存储器501用于存储程序指令,当程序指令被执行时所述 处理器502可以调用存储器501中存储的程序指令,用于执行如下步骤:
确定多个图像的同名特征点;
基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数;
根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整。
进一步地,所述处理器502基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数时,具体用于:
根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值;
根据所述多个图像的同名特征点对应的第二色彩空间值,确定所述各个图像对应的色彩调整参数。
进一步地,所述处理器502根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值时,具体用于:
根据所述多个图像的同名特征点对应的第一色彩空间值,计算所述多个图像的同名特征点对应的第一色彩空间均值;
对所述第一色彩空间均值进行转换得到所述多个图像的同名特征点对应的第二色彩空间值。
进一步地,所述第二色彩空间值包括亮度值,第一色差值和第二色差值。
进一步地,所述色彩调整参数包括亮度调整参数、第一颜色调整参数和第二颜色调整参数;所述处理器502根据所述多个图像的同名特征点对应的第二色彩空间值,确定所述各个图像对应的色彩调整参数时,具体用于:
根据所述多个图像的同名特征点对应的亮度值,确定所述各个图像对应的亮度调整参数;
根据所述多个图像的同名特征点对应的第一色差值,确定所述各个图像对应的第一颜色调整参数;
根据所述多个图像的同名特征点对应的第二色差值,确定所述各个图像对应的第二颜色调整参数。
进一步地,所述处理器502根据所述多个图像的同名特征点对应的亮度值,确定所述各个图像对应的亮度调整参数时,具体用于:
基于所述多个图像的同名特征点对应的亮度值建立第一目标函数;
通过优化所述第一目标函数确定所述各个图像对应的亮度调整参数。
进一步地,所述处理器502根据所述多个图像的同名特征点对应的第一色差值,确定所述各个图像对应的第一颜色调整参数时,具体用于:
基于所述多个图像的同名特征点对应的第一色差值建立第二目标函数;
通过优化所述第二目标函数确定所述各个图像对应的第一颜色调整参数。
进一步地,所述处理器502根据所述多个图像的同名特征点对应的第二色差值,确定所述各个图像对应的第二颜色调整参数时,具体用于:
基于所述多个图像的同名特征点对应的第二色差值建立第三目标函数;
通过优化所述第三目标函数确定所述各个图像对应的第二颜色调整参数。
进一步地,所述第一色彩空间值包括红色值、蓝色值和绿色值。
进一步地,所述处理器502确定多个图像的同名特征点时,具体用于:
获取所述多个图像的特征点,并对所述多个图像的特征点进行特征匹配以确定所述多个图像的同名特征点。
进一步地,所述处理器502基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数时,具体用于:
基于所述多个图像的同名特征点的色彩信息建立目标函数;
通过优化所述目标函数确定所述各个图像对应的色彩调整参数。
进一步地,所述处理器502根据所述各个图像的色彩调整参数对所述各个图像的色彩进行调整时,具体用于:
根据所述各个图像的色彩调整参数,采用伽马校正的方法对所述各个图像的色彩进行调整。
进一步地,所述多个图像为无人机上的图像采集设备采集到的图像,所述处理器502还用于:
基于色彩调整后的所述多个图像生成正射影像或真正射影像。
本发明实施例中,所述图像处理设备可以确定多个图像的同名特征点,基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数,根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整。通过这种实施方式,实现了对多个图像的全局色彩调整,使得调整后的多个图像具有色彩一致性,避免了色彩失真,提高了图像处理的效率。
本发明实施例还提供了一种图像处理***,所述图像处理***包括无人机和图像处理设备,所述无人机上设置有图像采集设备;
所述图像采集设备用于在所述无人机移动的过程中采集多个图像,并将采集到的所述多个图像发送给所述图像处理设备;
所述图像处理设备用于确定所述多个图像的同名特征点;基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数;根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整。
进一步地,所述图像处理设备在基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数时,具体用于:
根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值;
根据所述多个图像的同名特征点对应的第二色彩空间值,确定所述各个图像对应的色彩调整参数。
进一步地,所述图像处理设备在根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值时,具体用于:
根据所述多个图像的同名特征点对应的第一色彩空间值,计算所述多个图像的同名特征点对应的第一色彩空间均值;
对所述第一色彩空间均值进行转换得到所述多个图像的同名特征点对应的第二色彩空间值。
进一步地,所述第二色彩空间值包括亮度值,第一色差值和第二色差值。
进一步地,所述色彩调整参数包括亮度调整参数、第一颜色调整参数和第二颜色调整参数;所述图像处理设备在根据所述多个图像的同名特征点对应的第二色彩空间值,确定所述各个图像对应的色彩调整参数时,具体用于:
根据所述多个图像的同名特征点对应的亮度值,确定所述各个图像对应的亮度调整参数;
根据所述多个图像的同名特征点对应的第一色差值,确定所述各个图像对应的第一颜色调整参数;
根据所述多个图像的同名特征点对应的第二色差值,确定所述各个图像对 应的第二颜色调整参数。
进一步地,所述图像处理设备在根据所述多个图像的同名特征点对应的亮度值,确定所述各个图像对应的亮度调整参数时,具体用于:
基于所述多个图像的同名特征点对应的亮度值建立第一目标函数;
通过优化所述第一目标函数确定所述各个图像对应的亮度调整参数。
进一步地,所述图像处理设备在根据所述多个图像的同名特征点对应的第一色差值,确定所述各个图像对应的第一颜色调整参数时,具体用于:
基于所述多个图像的同名特征点对应的第一色差值建立第二目标函数;
通过优化所述第二目标函数确定所述各个图像对应的第一颜色调整参数。
进一步地,所述图像处理设备在根据所述多个图像的同名特征点对应的第二色差值,确定所述各个图像对应的第二颜色调整参数时,具体用于:
基于所述多个图像的同名特征点对应的第二色差值建立第三目标函数;
通过优化所述第三目标函数确定所述各个图像对应的第二颜色调整参数。
进一步地,所述第一色彩空间值包括红色值、蓝色值和绿色值。
进一步地,所述图像处理设备在确定多个图像的同名特征点时,具体用于:
获取所述多个图像的特征点,并对所述多个图像的特征点进行特征匹配以确定所述多个图像的同名特征点。
进一步地,所述图像处理设备在基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数时,具体用于:
基于所述多个图像的同名特征点的色彩信息建立目标函数;
通过优化所述目标函数确定所述各个图像对应的色彩调整参数。
进一步地,所述图像处理设备在根据所述各个图像的色彩调整参数对所述各个图像的色彩进行调整时,具体用于:
根据所述各个图像的色彩调整参数,采用伽马校正的方法对所述各个图像的色彩进行调整。
进一步地,所述多个图像为无人机上的图像采集设备采集到的图像,所述图像处理设备还用于:
基于色彩调整后的所述多个图像生成正射影像或真正射影像。
本发明实施例中,所述无人机上的图像采集设备可以将在所述无人机移动的过程中采集到的多个图像发送给图像处理设备,图像处理设备可以确定多个 图像的同名特征点,基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数,根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整。通过这种实施方式,实现了对多个图像的全局色彩调整,使得调整后的所述多个图像具有色彩一致性,避免了色彩失真,提高了图像处理的效率。
本发明实施例还提供了一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,所述计算机程序被处理器执行时实现本发明实施例图2或图4中描述的图像处理方法,也可实现本发明图5所对应实施例的设备,在此不再赘述。
所述计算机可读存储介质可以是前述任一项实施例所述的设备的内部存储单元,例如设备的硬盘或内存。所述计算机可读存储介质也可以是所述设备的外部存储设备,例如所述设备上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。进一步地,所述计算机可读存储介质还可以既包括所述设备的内部存储单元也包括外部存储设备。所述计算机可读存储介质用于存储所述计算机程序以及所述设备所需的其他程序和数据。所述计算机可读存储介质还可以用于暂时地存储已经输出或者将要输出的数据。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程,是可以通过计算机程序来指令相关的硬件来完成,所述的程序可存储于一计算机可读取存储介质中,该程序在执行时,可包括如上述各方法的实施例的流程。其中,所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory,ROM)或随机存储记忆体(Random Access Memory,RAM)等。
以上所揭露的仅为本发明部分实施例而已,当然不能以此来限定本发明之权利范围,因此依本发明权利要求所作的等同变化,仍属本发明所涵盖的范围。

Claims (40)

  1. 一种图像处理方法,其特征在于,所述方法包括:
    确定多个图像的同名特征点;
    基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数;
    根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整。
  2. 根据权利要求1所述的方法,其特征在于,所述基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数,包括:
    根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值;
    根据所述多个图像的同名特征点对应的第二色彩空间值,确定所述各个图像对应的色彩调整参数。
  3. 根据权利要求2所述的方法,其特征在于,所述根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值,包括:
    根据所述多个图像的同名特征点对应的第一色彩空间值,计算所述多个图像的同名特征点对应的第一色彩空间均值;
    对所述第一色彩空间均值进行转换得到所述多个图像的同名特征点对应的第二色彩空间值。
  4. 根据权利要求2所述的方法,其特征在于,所述第二色彩空间值包括亮度值,第一色差值和第二色差值。
  5. 根据权利要求4所述的方法,其特征在于,所述色彩调整参数包括亮度调整参数、第一颜色调整参数和第二颜色调整参数;所述根据所述多个图像的同名特征点对应的第二色彩空间值,确定所述各个图像对应的色彩调整参数,包括:
    根据所述多个图像的同名特征点对应的亮度值,确定所述各个图像对应的亮度调整参数;
    根据所述多个图像的同名特征点对应的第一色差值,确定所述各个图像对应的第一颜色调整参数;
    根据所述多个图像的同名特征点对应的第二色差值,确定所述各个图像对应的第二颜色调整参数。
  6. 根据权利要求5所述的方法,其特征在于,所述根据所述多个图像的同名特征点对应的亮度值,确定所述各个图像对应的亮度调整参数,包括:
    基于所述多个图像的同名特征点对应的亮度值建立第一目标函数;
    通过优化所述第一目标函数确定所述各个图像对应的亮度调整参数。
  7. 根据权利要求5所述的方法,其特征在于,所述根据所述多个图像的同名特征点对应的第一色差值,确定所述各个图像对应的第一颜色调整参数,包括:
    基于所述多个图像的同名特征点对应的第一色差值建立第二目标函数;
    通过优化所述第二目标函数确定所述各个图像对应的第一颜色调整参数。
  8. 根据权利要求5所述的方法,其特征在于,所述根据所述多个图像的同名特征点对应的第二色差值,确定所述各个图像对应的第二颜色调整参数,包括:
    基于所述多个图像的同名特征点对应的第二色差值建立第三目标函数;
    通过优化所述第三目标函数确定所述各个图像对应的第二颜色调整参数。
  9. 根据权利要求2所述的方法,其特征在于,所述第一色彩空间值包括红色值、蓝色值和绿色值。
  10. 根据权利要求1所述的方法,其特征在于,所述确定多个图像的同名特征点,包括:
    获取所述多个图像的特征点,并对所述多个图像的特征点进行特征匹配以 确定所述多个图像的同名特征点。
  11. 根据权利要求1所述的方法,其特征在于,所述基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数,包括:
    基于所述多个图像的同名特征点的色彩信息建立目标函数;
    通过优化所述目标函数确定所述各个图像对应的色彩调整参数。
  12. 根据权利要求1所述的方法,其特征在于,所述根据所述各个图像的色彩调整参数对所述各个图像的色彩进行调整,包括:
    根据所述各个图像的色彩调整参数,采用伽马校正的方法对所述各个图像的色彩进行调整。
  13. 根据权利要求1所述的方法,其特征在于,所述多个图像为无人机上的图像采集设备采集到的图像,所述方法还包括:
    基于色彩调整后的所述多个图像生成正射影像或真正射影像。
  14. 一种图像处理设备,其特征在于,所述设备包括存储器和处理器;
    所述存储器,用于存储程序指令;
    所述处理器,用于调用所述程序指令,当所述程序指令被执行时,用于执行以下操作:
    确定多个图像的同名特征点;
    基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数;
    根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整。
  15. 根据权利要求14所述的设备,其特征在于,所述处理器在基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数时,具体用于:
    根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值;
    根据所述多个图像的同名特征点对应的第二色彩空间值,确定所述各个图像对应的色彩调整参数。
  16. 根据权利要求15所述的设备,其特征在于,所述处理器在根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值时,具体用于:
    根据所述多个图像的同名特征点对应的第一色彩空间值,计算所述多个图像的同名特征点对应的第一色彩空间均值;
    对所述第一色彩空间均值进行转换得到所述多个图像的同名特征点对应的第二色彩空间值。
  17. 根据权利要求15所述的设备,其特征在于,所述第二色彩空间值包括亮度值,第一色差值和第二色差值。
  18. 根据权利要求17所述的设备,其特征在于,所述色彩调整参数包括亮度调整参数、第一颜色调整参数和第二颜色调整参数;所述处理器在根据所述多个图像的同名特征点对应的第二色彩空间值,确定所述各个图像对应的色彩调整参数时,具体用于:
    根据所述多个图像的同名特征点对应的亮度值,确定所述各个图像对应的亮度调整参数;
    根据所述多个图像的同名特征点对应的第一色差值,确定所述各个图像对应的第一颜色调整参数;
    根据所述多个图像的同名特征点对应的第二色差值,确定所述各个图像对应的第二颜色调整参数。
  19. 根据权利要求18所述的设备,其特征在于,所述处理器在根据所述多个图像的同名特征点对应的亮度值,确定所述各个图像对应的亮度调整参数时,具体用于:
    基于所述多个图像的同名特征点对应的亮度值建立第一目标函数;
    通过优化所述第一目标函数确定所述各个图像对应的亮度调整参数。
  20. 根据权利要求18所述的设备,其特征在于,所述处理器在根据所述多个图像的同名特征点对应的第一色差值,确定所述各个图像对应的第一颜色调整参数时,具体用于:
    基于所述多个图像的同名特征点对应的第一色差值建立第二目标函数;
    通过优化所述第二目标函数确定所述各个图像对应的第一颜色调整参数。
  21. 根据权利要求18所述的设备,其特征在于,所述处理器在根据所述多个图像的同名特征点对应的第二色差值,确定所述各个图像对应的第二颜色调整参数时,具体用于:
    基于所述多个图像的同名特征点对应的第二色差值建立第三目标函数;
    通过优化所述第三目标函数确定所述各个图像对应的第二颜色调整参数。
  22. 根据权利要求15所述的设备,其特征在于,所述第一色彩空间值包括红色值、蓝色值和绿色值。
  23. 根据权利要求14所述的设备,其特征在于,所述处理器在确定多个图像的同名特征点时,具体用于:
    获取所述多个图像的特征点,并对所述多个图像的特征点进行特征匹配以确定所述多个图像的同名特征点。
  24. 根据权利要求14所述的设备,其特征在于,所述处理器在基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数时,具体用于:
    基于所述多个图像的同名特征点的色彩信息建立目标函数;
    通过优化所述目标函数确定所述各个图像对应的色彩调整参数。
  25. 根据权利要求14所述的设备,其特征在于,所述处理器在根据所述各个图像的色彩调整参数对所述各个图像的色彩进行调整时,具体用于:
    根据所述各个图像的色彩调整参数,采用伽马校正的方法对所述各个图像 的色彩进行调整。
  26. 根据权利要求14所述的设备,其特征在于,所述多个图像为无人机上的图像采集设备采集到的图像,所述处理器还用于:
    基于色彩调整后的所述多个图像生成正射影像或真正射影像。
  27. 一种图像处理***,其特征在于,所述图像处理***包括:无人机和图像处理设备,所述无人机上设置有图像采集设备;
    所述无人机,用于通过所述图像采集设备在所述无人机移动的过程中采集多个图像,并将采集到的所述多个图像发送给所述图像处理设备;
    所述图像处理设备,用于确定所述多个图像的同名特征点;基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数;根据所述各个图像对应的色彩调整参数对所述各个图像的色彩进行调整。
  28. 根据权利要求27所述的***,其特征在于,所述图像处理设备基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数时,具体用于:
    根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值;
    根据所述多个图像的同名特征点对应的第二色彩空间值,确定所述各个图像对应的色彩调整参数。
  29. 根据权利要求28所述的***,其特征在于,所述图像处理设备根据所述多个图像的同名特征点对应的第一色彩空间值,确定所述多个图像的同名特征点对应的第二色彩空间值,包括:
    根据所述多个图像的同名特征点对应的第一色彩空间值,计算所述多个图像的同名特征点对应的第一色彩空间均值;
    对所述第一色彩空间均值进行转换得到所述多个图像的同名特征点对应的第二色彩空间值。
  30. 根据权利要求28所述的***,其特征在于,所述第二色彩空间值包括亮度值,第一色差值和第二色差值。
  31. 根据权利要求30所述的***,其特征在于,所述色彩调整参数包括亮度调整参数、第一颜色调整参数和第二颜色调整参数;所述图像处理设备根据所述多个图像的同名特征点对应的第二色彩空间值,确定所述各个图像对应的色彩调整参数时,具体用于:
    根据所述多个图像的同名特征点对应的亮度值,确定所述各个图像对应的亮度调整参数;
    根据所述多个图像的同名特征点对应的第一色差值,确定所述各个图像对应的第一颜色调整参数;
    根据所述多个图像的同名特征点对应的第二色差值,确定所述各个图像对应的第二颜色调整参数。
  32. 根据权利要求31所述的***,其特征在于,所述图像处理设备根据所述多个图像的同名特征点对应的亮度值,确定所述各个图像对应的亮度调整参数时,具体用于:
    基于所述多个图像的同名特征点对应的亮度值建立第一目标函数;
    通过优化所述第一目标函数确定所述各个图像对应的亮度调整参数。
  33. 根据权利要求31所述的***,其特征在于,所述图像处理设备根据所述多个图像的同名特征点对应的第一色差值,确定所述各个图像对应的第一颜色调整参数时,具体用于:
    基于所述多个图像的同名特征点对应的第一色差值建立第二目标函数;
    通过优化所述第二目标函数确定所述各个图像对应的第一颜色调整参数。
  34. 根据权利要求31所述的***,其特征在于,所述图像处理设备根据所述多个图像的同名特征点对应的第二色差值,确定所述各个图像对应的第二颜色调整参数时,具体用于:
    基于所述多个图像的同名特征点对应的第二色差值建立第三目标函数;
    通过优化所述第三目标函数确定所述各个图像对应的第二颜色调整参数。
  35. 根据权利要求28所述的***,其特征在于,所述第一色彩空间值包括红色值、蓝色值和绿色值。
  36. 根据权利要求27所述的***,其特征在于,所述图像处理设备确定多个图像的同名特征点时,具体用于:
    获取所述多个图像的特征点,并对所述多个图像的特征点进行特征匹配以确定所述多个图像的同名特征点。
  37. 根据权利要求27所述的***,其特征在于,所述图像处理设备基于所述多个图像的同名特征点的色彩信息,确定各个图像对应的色彩调整参数时,具体用于:
    基于所述多个图像的同名特征点的色彩信息建立目标函数;
    通过优化所述目标函数确定所述各个图像对应的色彩调整参数。
  38. 根据权利要求27所述的***,其特征在于,所述图像处理设备根据所述各个图像的色彩调整参数对所述各个图像的色彩进行调整时,具体用于:
    根据所述各个图像的色彩调整参数,采用伽马校正的方法对所述各个图像的色彩进行调整。
  39. 根据权利要求27所述的***,其特征在于,所述多个图像为无人机上的图像采集设备采集到的图像,所述图像处理设备还用于:
    基于色彩调整后的所述多个图像生成正射影像或真正射影像。
  40. 一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,其特征在于,所述计算机程序被处理器执行时实现如权利要求1至13任一项所述方法。
PCT/CN2019/077702 2019-03-11 2019-03-11 一种图像处理方法、设备、***及存储介质 WO2020181469A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201980002930.1A CN110785772A (zh) 2019-03-11 2019-03-11 一种图像处理方法、设备、***及存储介质
PCT/CN2019/077702 WO2020181469A1 (zh) 2019-03-11 2019-03-11 一种图像处理方法、设备、***及存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/077702 WO2020181469A1 (zh) 2019-03-11 2019-03-11 一种图像处理方法、设备、***及存储介质

Publications (1)

Publication Number Publication Date
WO2020181469A1 true WO2020181469A1 (zh) 2020-09-17

Family

ID=69394853

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/077702 WO2020181469A1 (zh) 2019-03-11 2019-03-11 一种图像处理方法、设备、***及存储介质

Country Status (2)

Country Link
CN (1) CN110785772A (zh)
WO (1) WO2020181469A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112419443A (zh) * 2020-12-09 2021-02-26 中煤航测遥感集团有限公司 真正射影像生成方法和装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011204121A (ja) * 2010-03-26 2011-10-13 Pasuko:Kk 単画像の生成方法
CN104077760A (zh) * 2014-03-19 2014-10-01 中科宇图天下科技有限公司 一种航空摄影测量的快速拼接***及其实现方法
CN105635719A (zh) * 2014-11-20 2016-06-01 三星电子株式会社 用于校准图像的方法和设备
CN106875449A (zh) * 2017-02-17 2017-06-20 深圳飞马机器人科技有限公司 一种基于飞行数据的无人机非量测型相机检校方法
CN106910235A (zh) * 2017-01-20 2017-06-30 同济大学 基于坐标转换的地面激光扫描数据匀光匀色方法
CN108596837A (zh) * 2018-05-09 2018-09-28 北京玖瑞科技有限公司 图像拼接方法、装置、设备和计算机介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5195395B2 (ja) * 2008-12-19 2013-05-08 株式会社リコー 画像処理装置、画像処理方法、画像処理プログラム及び記録媒体
JP6327071B2 (ja) * 2014-09-03 2018-05-23 オムロン株式会社 画像処理装置および画像処理方法
CN105933687A (zh) * 2016-07-04 2016-09-07 凌云光技术集团有限责任公司 一种对图像进行自动白平衡处理的方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011204121A (ja) * 2010-03-26 2011-10-13 Pasuko:Kk 単画像の生成方法
CN104077760A (zh) * 2014-03-19 2014-10-01 中科宇图天下科技有限公司 一种航空摄影测量的快速拼接***及其实现方法
CN105635719A (zh) * 2014-11-20 2016-06-01 三星电子株式会社 用于校准图像的方法和设备
CN106910235A (zh) * 2017-01-20 2017-06-30 同济大学 基于坐标转换的地面激光扫描数据匀光匀色方法
CN106875449A (zh) * 2017-02-17 2017-06-20 深圳飞马机器人科技有限公司 一种基于飞行数据的无人机非量测型相机检校方法
CN108596837A (zh) * 2018-05-09 2018-09-28 北京玖瑞科技有限公司 图像拼接方法、装置、设备和计算机介质

Also Published As

Publication number Publication date
CN110785772A (zh) 2020-02-11

Similar Documents

Publication Publication Date Title
CN106210501B (zh) 图像合成方法与图像处理装置
KR100886099B1 (ko) 감마 보정 곡선의 자동 산출 장치 및 방법
US20180082454A1 (en) Color normalization for a multi-camera system
US20120170842A1 (en) Tone mapping of very large aerial image mosaic
WO2021057474A1 (zh) 主体对焦方法、装置、电子设备和存储介质
JP4831514B2 (ja) 設定パラメータ最適化装置およびそのプログラム
CN111292246B (zh) 图像颜色校正方法、存储介质及内窥镜
US10785466B2 (en) Multi-image color-refinement with application to disparity estimation
US8810693B2 (en) Image processing apparatus and method thereof
CN111932601B (zh) 一种基于YCbCr颜色空间光场数据的稠密深度重建方法
CN112669758A (zh) 显示屏校正方法、装置、***和计算机可读存储介质
DE112016001871T5 (de) Bildverarbeitungsvorrichtung, Bildverarbeitungsverfahren und Programm
WO2021051307A1 (zh) 图像的颜色校正方法、拍摄设备、图像的颜色校正***
CN114998122A (zh) 一种低照度图像增强方法
WO2020181469A1 (zh) 一种图像处理方法、设备、***及存储介质
CN111587573B (zh) 一种图像处理方法、装置及计算机存储介质
WO2021168707A1 (zh) 对焦方法、装置及设备
CN112734630A (zh) 正射影像处理方法、装置、设备及存储介质
CN100584036C (zh) 影像补偿装置与方法
WO2023151210A1 (zh) 图像处理方法、电子设备及计算机可读存储介质
WO2019137396A1 (zh) 一种图像处理方法及装置
CN113055659B (zh) 颜色补偿参数生成方法、装置、计算机设备以及存储介质
CN110458768B (zh) 图像处理方法、计算机设备和可读存储介质
CN113781330A (zh) 图像处理方法、装置及电子***
Ewiak et al. Functionality assessment of algorithms for the coloring of images in terms of increasing radiometric values of aerial photographs archives

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19919484

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19919484

Country of ref document: EP

Kind code of ref document: A1