WO2019061079A1 - Procédé et dispositif de traitement de mise au point - Google Patents

Procédé et dispositif de traitement de mise au point Download PDF

Info

Publication number
WO2019061079A1
WO2019061079A1 PCT/CN2017/103697 CN2017103697W WO2019061079A1 WO 2019061079 A1 WO2019061079 A1 WO 2019061079A1 CN 2017103697 W CN2017103697 W CN 2017103697W WO 2019061079 A1 WO2019061079 A1 WO 2019061079A1
Authority
WO
WIPO (PCT)
Prior art keywords
target object
focus
image
contrast
determining
Prior art date
Application number
PCT/CN2017/103697
Other languages
English (en)
Chinese (zh)
Inventor
封旭阳
赵丛
钱杰
余俊峰
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 PCT/CN2017/103697 priority Critical patent/WO2019061079A1/fr
Priority to CN201780004744.2A priority patent/CN108496350B/zh
Publication of WO2019061079A1 publication Critical patent/WO2019061079A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/67—Focus control based on electronic image sensor signals

Definitions

  • the present invention relates to the field of control technologies, and in particular, to a focus processing method and apparatus.
  • the method of autofocus is generally divided into active and passive.
  • active is to measure the distance between camera and object actively;
  • passive is to use phase focusing method or contrast detection focusing method, where phase focusing requires special sensor support.
  • Contrast focus is still the way most ordinary digital cameras use it.
  • the Contrast Detection Auto Focus (CDAF) mainly detects the highest contrast by adjusting the contrast information of the focus subject, that is, determining the focus. Contrast focusing usually does not require a spectroscopic device, so layout and operation are more flexible and less expensive.
  • the existing contrast focusing algorithm requires multiple iterations, and the focus is adjusted back and forth to the opposite direction to search for the focus position with the highest contrast, causing a short-distance flashing "breathing effect" on the video, and the focusing speed is limited. If the target object is in motion on the screen and the position changes too much, it is easy to fail focus.
  • the embodiment of the invention provides a focus processing method and device, which can automatically track and focus on a moving target object, optimize the focusing effect, and improve the focusing efficiency.
  • an embodiment of the present invention provides a focus processing method, including:
  • an embodiment of the present invention provides a focus processing device, including a memory and a processor;
  • the memory is configured to store program instructions
  • the processor executes program instructions stored in the memory, and when the program instructions are executed, the processor is configured to perform the following steps:
  • an embodiment of the present invention provides a computer readable storage medium storing a computer program, which when executed by a processor, implements the focus processing method according to the first aspect described above.
  • an auto-focusing direction is determined according to the moving direction by acquiring a moving direction of the target object with respect to the image capturing device, and automatic focusing is performed according to the auto-focusing direction to perform the target focusing on the target object.
  • Focusing which automatically performs tracking and focusing processing, optimizes the focusing effect, and improves the focusing efficiency.
  • FIG. 1 is a schematic flow chart of a focus processing method according to an embodiment of the present invention.
  • FIG. 2 is a schematic diagram of a scene of focusing processing according to an embodiment of the present invention
  • FIG. 3 is a schematic diagram of contrast difference of different focus positions according to an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of a focus evaluation function according to an embodiment of the present invention.
  • FIG. 5 is a schematic diagram of a hill climbing search algorithm according to an embodiment of the present invention.
  • FIG. 6 is a schematic flowchart diagram of another focus processing method according to an embodiment of the present invention.
  • FIG. 7 is a schematic structural diagram of a focus processing device according to an embodiment of the present invention.
  • FIG. 8 is a schematic structural diagram of another focus processing device according to an embodiment of the present invention.
  • the focus processing method provided by the embodiment of the present invention may be performed by a focus processing apparatus, or in other embodiments, the focus processing method may be applied to an image pickup apparatus such as a camera, and may be used for photographing, aerial photography, and motion photography. Etc., the following is an example of a focus processing method for use on an image pickup apparatus.
  • the scheme adopts the visual target tracking algorithm to assist the auto-focusing.
  • the target object's motion trend can be accurately estimated, and the target object's near-farming trend can be provided to obtain the judgment.
  • the auto-focusing direction is determined, thereby greatly optimizing the focusing effect on the target object during the movement, reducing the focus failure or focusing on the background, and also targeting the target object.
  • the position change on the screen has an accurate positioning. Wherein, if for a specific category of objects, such as a human face, face detection of consecutive frames can be used instead of the target tracking algorithm, and changes in target movement and size can also be obtained.
  • the embodiment of the invention captures an acquired image by the camera device, and recognizes and acquires the target object according to the obtained user operation in the image.
  • the focus processing device may use the target tracking algorithm to detect the transformed state information such as the size or position information of the target object in the image, and determine the moving direction of the target object relative to the camera device according to the changed state information.
  • the focus processing device may also acquire the position coordinates of the target object according to the positioning device, thereby determining the moving direction of the target object relative to the imaging device.
  • the focus processing apparatus may further determine a moving direction of the target object with respect to the imaging device by acquiring a depth map of the target object.
  • the focus processing device may determine an auto focus direction according to the moving direction, and perform auto focus according to the auto focus direction to focus the target object. .
  • a focus processing method is described by taking a corresponding processing by a focus processing device as an example.
  • FIG. 1 is a schematic flowchart of a focus processing method according to an embodiment of the present invention, which may be performed by a focus processing device, wherein a specific explanation of the focus processing device is as described above. Specifically, the method of the embodiment of the present invention includes the following steps.
  • S101 Acquire a moving direction of the target object with respect to the imaging device.
  • the focus processing device can acquire the moving direction of the target object with respect to the imaging device.
  • FIG. 2 the application scenario of the embodiment of the present invention is shown in FIG. 2, and FIG. 2 is an embodiment of the present invention.
  • the application scenario of the embodiment of the present invention includes an imaging device shown by 201 and a target object shown by 202.
  • the focus processing device can capture the target object 202 by using the camera 201, and the target object 202 is movable.
  • the focus processing device can acquire the target object while moving.
  • the moving direction for example, the moving direction of the target object 202 with respect to the image pickup device 201 is moving toward the vicinity of the image pickup device 201, at which time the target object captured by the image pickup device becomes blurred; or the movement of the target object 202 with respect to the image pickup device 201
  • the direction is moving away from the imaging device 201, and the target object captured by the imaging device is blurred at this time. Therefore, when the target object moves, it is necessary to acquire the moving direction of the target object with respect to the image pickup device, so that the focus focus can be adjusted according to the moving direction.
  • the focus processing device may detect the change state information of the target object in the image by visually recognizing the target object, wherein the state information includes a size of the target object in the image or in the image. Location area.
  • the focus processing device determines a moving direction of the target object with respect to the image pickup device based on the change state information.
  • the focus processing apparatus can recognize a target person (target object) in the captured image by visually recognizing the user, and then detect change information of the size of the target person (target object) to be photographed in the image. Or detecting change information of a position area of the person (target object) to be photographed in the image.
  • the moving direction of the target person with respect to the image pickup device is moving toward a direction close to the image pickup device; if the target person is detected to be When the positional area in the image becomes small, it is determined that the moving direction of the target person with respect to the imaging device is moving away from the imaging device.
  • the focus processing device may also acquire the position coordinates of the target object by using a positioning device carried by the target object, and determine a moving direction of the target object relative to the camera device according to the position coordinates.
  • a positioning device such as a Global Positioning System (GPS), an Ultra Wideband (UWB), or the like
  • the focus processing device can utilize the The positioning device, such as GPS, UWB, or the like, carried by the target object acquires the position coordinates of the target object, and obtains a change in the distance of the target object relative to the imaging device, and determines, according to the position coordinates, the target object In the moving direction of the imaging device.
  • the focus processing The device may acquire the position coordinates of the target object by using the GPS positioning device, and determine a moving direction of the target object relative to the camera device according to the position coordinates.
  • the focus processing device may further acquire a depth map of the target object, and determine a moving direction of the target object relative to the camera device according to the acquired depth map.
  • the focus processing device may acquire a distance (depth) of the target object from the camera device, and use an image composed of the distance as a depth map, and the focus processing device may determine the target according to the acquired depth map.
  • the direction of movement of the object relative to the camera For example, the focus processing device acquires an image in which the initial distance (depth) of the target object from the imaging device is 1 m, and the current distance of the target object from the imaging device is 1.5 m, and the two distances are formed.
  • the focus processing apparatus may determine that the moving direction of the target object relative to the image pickup device is moving away from the image pickup device according to the change of the two distances.
  • S102 Determine an auto focus direction according to the moving direction, and perform auto focus according to the auto focus direction to focus on the target object.
  • the focus processing device may determine an auto focus direction according to the moving direction, and perform auto focus according to the auto focus direction to focus on the target object. Specifically, the focus processing device assists autofocus by combining the moving direction of the target object. Firstly, by providing a judgment of the trend of the target object, the focus direction of the target is preferentially adjusted, the convergence speed is accelerated, and the back and forth are reduced. Search for breathing phenomena.
  • the contrast detection focus depends on the continuous frame, before and after changing the focus distance, according to the change trend of the contrast in a certain area of the image, it is judged whether the current focus change direction is consistent with the correct direction, and the comparison premise of the contrast change It is based on the image that the target object in the region is not moving. If the target object moves, and the contrast of the front and rear statistics is based on different scenes, the change values of the front and rear frames have no reference meaning for focusing. However, combined with the moving direction of the target object, the contrast of the front and rear frame statistics can be based on the image of the same target object, and can be dynamically changed in the focus process according to the movement of the target object on the screen, which greatly increases the target object. Focus success rate during exercise.
  • the focus processing device may implement auto-focusing in conjunction with the moving direction and contrast detection algorithm of the target object, or may combine the moving direction of the target object and phase detection to achieve auto-focusing.
  • the contrast detection focus is mainly by detecting the highest contrast in the process of adjusting the focus contrast information of the image in the image, that is, to determine the focus, the contrast detection focus usually does not require the spectroscopic device, so More flexible layout and operation This is also lower.
  • Phase detection focus is achieved by finding the point with the smallest aberration. A certain point of the object will emit light from all directions through the lens and image onto the sensor. When the light in different directions falls to the same position of the sensor, The aberration is the smallest.
  • phase detection to focus the focus itself is fast, but when using focus to detect focus, the focus itself is slightly slower when using contrast detection, but the entire focus "process" is not necessarily slow because there is no reflector Two extra moves.
  • the focus processing device may perform image tracking processing on the target object, and obtain the target object. a position area in the image, a contrast of the captured image is calculated according to the position area, and a focus focus of the target object is determined according to the contrast.
  • the target object is movable, and when the target object is moving, the focus processing device may perform image tracking processing on the moved target object, thereby obtaining a location area of the target object in the image, and A contrast of the captured image is calculated based on the location area, and a focus focus of the target object is determined according to the contrast.
  • the contrast of the different position areas is different. As shown in FIG. 3, FIG.
  • 3 is a schematic diagram of contrast difference of different focus positions according to an embodiment of the present invention, wherein 301 shows a contrast change of the focus position. 302 shows the contrast change of another different focus position. As can be seen from 301 and 302 of FIG. 3, the focus positions are different, and the acquired contrast is different.
  • the contrast is obtained based on a focus evaluation function score of the image contrast design.
  • FIG. 4 is a schematic diagram of a focus evaluation function according to an embodiment of the present invention.
  • the abscissa x is the focus position
  • the ordinate y is the focus evaluation function score
  • the established coordinate function 401 shows the focus evaluation function score at the time of near focus
  • 402 shows the focus evaluation function score at the time of the focus
  • 403 shows the focus evaluation function score at the far focus.
  • the ideal focus evaluation function has the following characteristics: unimodality, that is, an extreme value in the range of tuning; unbiased is the focus evaluation function when the system is in the best focus state. Give the maximum or minimum value; the polarity that can reflect the defocus, ie, before or after the focus; can resist all kinds of noise.
  • the focus processing device performs image tracking processing on the target object to obtain an image in the initial region of the current image frame and the previous image frame when the target region is obtained in the image. Comparing the images of the location area where the target object is located, wherein the initial area is the location area of the target object in the current image frame, if the similarity is greater than the preset The similarity threshold determines the initial region as the location region in which the target object is located in the current image frame.
  • the focus processing device compares the image in the initial region of the current image frame with the image of the location region in which the target object is located in the previous image frame, and the acquired similarity is 95%, and the preset similarity is The threshold is 90%, 95%>90%, so the focus processing device can determine the initial region as the location region in which the target object is located in the current image frame.
  • the focus processing device detects that the sharpness of the current image frame is less than a preset sharpness threshold, the preset similarity threshold may be lowered. Further, if the focus processing device detects that the resolution of the current image frame is less than a preset definition threshold, the image tracking algorithm based on the color information may be selected, or the weight of the color distribution in the image tracking algorithm may be adjusted.
  • the target object performs image tracking processing. For example, if the focus processing device detects that the current image frame has a sharpness of 50% and the preset sharpness threshold is 60%, 50% ⁇ 60%, the focus processing device can pass the preset similarity. The threshold is reduced by 90%, and image tracking processing is performed on the target object.
  • the focus processing device may select image tracking based on the color information.
  • the algorithm or the weight of the color distribution in the image tracking algorithm is adjusted, and the target object is subjected to image tracking processing.
  • the focus processing device determines the contrast tracking algorithm based on gradient information or frequency domain information when focusing on the moving target object. After the possible out of focus, the preset contrast threshold in the target tracking algorithm is adaptively reduced, and the implementation can achieve continuous tracking on the blurred image.
  • the focus processing device when focusing on the moving target object, can also fuse the focus evaluation function and the target tracking algorithm through the pre-trained model. Adjusting the contrast threshold preset in the target tracking algorithm adaptively according to the focusing effect, the implementation can not only keep track of the target object, but also maintain the accuracy of the tracking, avoiding the wrong or missing target object.
  • the focus processing device acquires the captured image by the image capturing device, acquires the target object and the moving direction of the target object with respect to the image capturing device, determines an automatic focusing direction according to the moving direction, and according to the Auto-focusing is performed in the auto-focusing direction to focus on the target object.
  • FIG. 6 is a schematic flowchart diagram of another focus processing method according to an embodiment of the present invention, which may be performed by a focus processing device, wherein a specific explanation of the focus processing device is as described above.
  • the method of the embodiment of the invention comprises the following steps.
  • S601 Determine a target object according to the captured image.
  • the focus processing device may determine the target object according to the captured image, wherein the target object is determined according to a selection operation in the image, or is automatically identified according to an image recognition algorithm. Specifically, the focus processing device captures an image by the image capturing device, and determines a target object that needs to be photographed according to the captured image, wherein the target object may be determined according to a user-based selection operation received in the image, or The identification is automatically identified based on the image recognition algorithm. Specifically, the focus processing device captures an image by the image capturing device. When it is detected that a user-based selection operation is received in the image, the focus processing device may determine the target object according to the received selection operation.
  • the selection operation may be a click operation, a frame selection operation, or the like, and the target object may be a specific type of object such as a human face, which is not limited in the embodiment of the present invention.
  • S602 Perform image tracking processing on the target object to obtain a size of the target object in the image or a position area in the image.
  • the focus processing device may perform image tracking processing on the target object to obtain a size of the target object in the image or a location area in the image. Specifically, it will not be elaborated here as described in the above embodiments.
  • the focus processing device may also acquire the position coordinates of the target object by using a positioning device carried by the target object, which is not described in detail herein as described in the foregoing embodiments.
  • S603 Calculate the contrast of the captured image according to the location area.
  • the focus processing device may calculate the contrast of the captured image according to the acquired location area of the target object in the image. Specifically, it will not be elaborated here as described in the above embodiments.
  • the focus processing device can detect whether the contrast of the captured image is decreased.
  • FIG. 5 is taken as an example, and FIG. 5 is the present invention.
  • a schematic diagram of a hill climbing search algorithm is provided in the embodiment.
  • 501 represents the contrast at the starting point
  • 502 represents the contrast at the best focus point
  • an arrow represents the moving direction.
  • FIG. 5 shows that the focus lens of the image pickup device moves from left to right in equal steps from the starting point 501.
  • the contrast of the image is calculated once, and if the calculated contrast is gradually increased, the moving direction is correct, according to Focus control continues in the current focus direction.
  • the focus processing device determines whether the decrease value of the contrast is less than a preset threshold.
  • the focus processing device detects the contrast drop when detecting the contrast of the captured image, and determines that the decrease value of the contrast is less than a preset threshold, determining the current focus as the target The focus of the object.
  • the imaging device of the focus processing device moves from left to right in equal steps from the starting point 501. Each time one step is moved, the contrast of the image is calculated once, and if the calculated contrast is gradually increased, The movement direction is correct.
  • the contrast reaches 502
  • the contrast decreases for the first time, and if the decrease value of the contrast acquired at 502 is less than the preset threshold, the current focus of the current 502 is determined as the The focus of the target object.
  • the embodiment avoids the phenomenon that the camera device searches for the best focus point by searching back and forth in the prior art, speeds up the convergence, and increases the focus success rate when the target object moves.
  • the focus processing device determines that the decrease value of the contrast is not less than a preset threshold, detecting a size of the target object in the image or a change in the position region in the image.
  • a preset threshold detecting a size of the target object in the image or a change in the position region in the image.
  • step S609 If it is detected that the size or the positional area becomes large, the direction close to the imaging device is determined as the autofocusing direction, and step S612 is performed.
  • the focus processing device detects that the size or the position area becomes large, the direction close to the image pickup device is determined as the auto focus direction.
  • the direction close to the image pickup device is determined as the auto focus direction.
  • the focus direction is automatically adjusted, and the target is focused according to the auto focus direction.
  • step S610 If it is detected that the size or the positional area becomes smaller, the direction away from the imaging device is determined as the auto-focusing direction, and step S612 is performed.
  • the focus processing device when detecting the size of the target object in the image or the change of the position area in the image, if the size or the location area is detected to be small, the focus processing device will be far away from the camera device.
  • the direction is determined as the auto focus direction. Taking FIG. 5 as an example, when the contrast reaches 503, the decrease value of the contrast is not less than a preset threshold. If the size of the target object in the image or the positional area in the image is detected to be small at this time, The direction away from the imaging device is determined as an auto-focusing direction, and focusing on the target object is performed according to the auto-focusing direction.
  • step S611 If the size or the location area is detected to be unchanged, the direction opposite to the focusing direction is determined as the auto-focusing direction, and step S612 is performed.
  • the focus processing device detects a change in the size of the target object in the image or a position region in the image, and if the size or the position region is detected to be unchanged, the focus direction is The opposite direction is determined as the auto focus direction.
  • the contrast value of the contrast is not less than a preset threshold. If the size of the target object in the image or the positional area in the image is detected at this time, A direction opposite to the focusing direction is determined as an auto-focusing direction, and focusing on the target object is performed according to the auto-focusing direction.
  • S612 Focus the target object according to the autofocus direction.
  • the focus processing device may determine the focus focus of the target object according to the auto focus direction, and perform focus control on the target object.
  • the focus processing device acquires the captured image by the image capturing device, acquires the target object from the image, performs image tracking processing on the target object, and obtains the size of the target object in the image or the position region in the image. Calculating a contrast of the captured image according to the location area, determining an auto-focusing direction according to the detected change in contrast and a change in a size of the target object in the image or a positional area in the image, according to the automatic adjustment Defocus direction, determine the target pair The focus of the image is focused on the target object.
  • the automatic tracking and focusing of the moving target object can be realized, the focusing effect is optimized, and the efficiency of focusing success is improved.
  • FIG. 7 is a schematic structural diagram of a focus processing device according to an embodiment of the present invention.
  • the device in the embodiment of the present invention includes: an obtaining unit 701 and a processing unit 702, where
  • the obtaining unit 701 is configured to acquire a moving direction of the target object relative to the camera device;
  • the processing unit 702 is configured to determine an auto focus direction according to the moving direction, and perform auto focus according to the auto focus direction to focus the target object.
  • the acquiring unit 701 is specifically configured to use a visual recognition target object, and detect change state information of the target object in an image, where the state information includes a size of the target object in an image or in an image. a location area; determining a moving direction of the target object with respect to the imaging device according to the change state information.
  • the acquiring unit 701 is further configured to acquire, by using a positioning device carried by the target object, location coordinates of the target object, and determine, according to the location coordinates, a moving direction of the target object relative to the camera device. .
  • the acquiring unit 701 is further configured to acquire a depth map of the target object, and determine a moving direction of the target object relative to the camera device according to the acquired depth map.
  • the device further includes a determining unit 703, where
  • the determining unit 703 is configured to determine a target object according to the captured image; wherein the target object is determined according to a selection operation in the image, or is automatically identified according to an image recognition algorithm.
  • the processing unit 702 is further configured to perform image tracking processing on the target object to obtain a location area of the target object in the image, and calculate a contrast of the captured image according to the location area; The contrast determines the focus focus of the target object.
  • the processing unit 702 is further configured to detect a contrast of the captured image; if the contrast is detected to rise, perform focus control according to the focusing direction.
  • the processing unit 702 is further configured to detect a contrast of the captured image; if the contrast is detected to decrease, determine a focus focus of the target object according to the falling value of the contrast.
  • the processing unit 702 is further configured to determine the current focus as the focus focus of the target object if the falling value of the contrast is detected to be less than a preset threshold.
  • the processing unit 702 is further configured to: if it is detected that the falling value of the contrast is not less than a preset threshold, determine an auto-focusing direction according to the change state information of the target object; according to the auto-focusing Focus control in the direction.
  • the processing unit 702 is further configured to detect a size of the target object in an image or a change in a location area in the image; if the size or the location area is detected to be large, the imaging unit is to be close to the camera.
  • the orientation of the device is determined to be the autofocus direction.
  • the processing unit 702 is further configured to detect a size of the target object in an image or a change in a location area in the image; if the size or the location area is detected to be small, the image is to be away from the camera The orientation of the device is determined to be the autofocus direction.
  • the processing unit 702 is further configured to detect a size of the target object in an image or a change in a location area in the image; if the size or the location area is detected to be unchanged, The direction in which the focal direction is opposite is determined as the autofocus direction.
  • the processing unit 702 is further configured to compare an image in an initial region of the current image frame with an image in a location region where the target object is located in a previous image frame; if the similarity is greater than a preset similarity The threshold is determined as the location area in which the target object is located in the current image frame.
  • the processing unit 702 is further configured to decrease the preset similarity threshold if it is detected that the resolution of the current image frame is less than a preset definition threshold.
  • the processing unit 702 is further configured to: if it is detected that the resolution of the current image frame is less than a preset definition threshold, select an image tracking algorithm based on the color information, or adjust the color distribution in the image tracking algorithm. Weighting, performing image tracking processing on the target object.
  • the focus processing device acquires the captured image by the determining unit 703, and acquires the target object from the image, and acquires the moving direction of the target object with respect to the imaging device by the obtaining unit 701, and the processing unit 702 according to the moving direction.
  • the auto focus direction is determined, and auto focus is performed according to the auto focus direction to focus on the target object.
  • FIG. 8 is a schematic structural diagram of another focus processing device according to an embodiment of the present invention.
  • the terminal in this embodiment as shown may include: one or more processors 801; one or more input devices 802, one or more output devices 803, and memory 804.
  • the above processor 801, input device 802, output device 803, and memory 804 are connected by a bus 805.
  • Storage The processor 802 is configured to store instructions, and the processor 801 is configured to execute instructions stored by the memory 802. Wherein, when the program instruction is executed, the processor 801 is configured to perform the following steps:
  • the processor 801 calls a program instruction stored in the memory 802 for performing the following steps:
  • Detecting change state information of the target object in an image the state information including a size of the target object in an image or a location area in an image;
  • the processor 801 calls a program instruction stored in the memory 802 for performing the following steps:
  • the processor 801 calls a program instruction stored in the memory 802 for performing the following steps:
  • the processor 801 calls a program instruction stored in the memory 802 for performing the following steps:
  • the target object is determined according to a selection operation in an image, or is automatically identified according to an image recognition algorithm.
  • the processor 801 calls a program instruction stored in the memory 802 for performing the following steps:
  • a focus focus of the target object is determined based on the contrast.
  • the processor 801 calls a program instruction stored in the memory 802 for performing the following steps:
  • the focus control is continued in accordance with the focus direction.
  • the processor 801 calls a program instruction stored in the memory 802 for performing the following steps:
  • the focus focus of the target object is determined according to the decrease value of the contrast.
  • the processor 801 calls a program instruction stored in the memory 802 for performing the following steps:
  • the current focus is determined as the focus focus of the target object.
  • the processor 801 calls a program instruction stored in the memory 802 for performing the following steps:
  • the processor 801 calls a program instruction stored in the memory 802 for performing the following steps:
  • a change in the size of the target object in the image or a positional area in the image is detected; if it is detected that the size or the positional area becomes large, the direction close to the image pickup device is determined as the autofocus direction.
  • the processor 801 calls a program instruction stored in the memory 802 for performing the following steps:
  • a change in the size of the target object in the image or a positional area in the image is detected; if it is detected that the size or the positional area becomes smaller, the direction away from the image pickup device is determined as the autofocus direction.
  • the processor 801 calls a program instruction stored in the memory 802 for executing, for example, Next steps:
  • a change in the size of the target object in the image or a positional area in the image is detected; if the size or the positional area is detected to be unchanged, a direction opposite to the focusing direction is determined as an auto-focusing direction.
  • the processor 801 calls a program instruction stored in the memory 802 for performing the following steps:
  • the processor 801 calls a program instruction stored in the memory 802 for performing the following steps:
  • the preset similarity threshold is lowered.
  • the processor 801 calls a program instruction stored in the memory 802 for performing the following steps:
  • the image tracking algorithm based on the color information, or the weight of the color distribution in the image tracking algorithm is selected, and the target object is subjected to image tracking processing.
  • the processor 801 may be a central processing unit (CPU), and the processor may also be another general-purpose processor, a digital signal processor (DSP). , Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc.
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
  • the input device 802 may include a touchpad, a fingerprint sensor (for collecting fingerprint information of the user and direction information of the fingerprint), a microphone, and the like, and the output device 803 may include a display (LCD or the like), a speaker, and the like.
  • a touchpad for collecting fingerprint information of the user and direction information of the fingerprint
  • a microphone for collecting fingerprint information of the user and direction information of the fingerprint
  • the output device 803 may include a display (LCD or the like), a speaker, and the like.
  • the memory 804 can include a read only memory and a random access memory, and is directed to the processor 801. Provide instructions and data. A portion of the memory 804 may also include a non-volatile random access memory. For example, the memory 804 can also store information of the device type.
  • processor 801 for a specific implementation of the processor 801 in the embodiment of the present invention, refer to the description of related content in the foregoing embodiments, and details are not described herein.
  • the focus processing device acquires the captured image by the image capturing device, acquires the target object from the image, acquires a moving direction of the target object with respect to the image capturing device, and determines an automatic focusing direction according to the moving direction, and Autofocusing is performed according to the autofocus direction to focus on the target object.
  • An embodiment of the present invention further provides a computer readable storage medium storing a computer program, which when executed by a processor, implements the embodiment corresponding to FIG. 1 or FIG. 6 of the present invention.
  • the focus processing device of the embodiment of the present invention described in FIG. 7 or FIG. 8 can also be implemented in the manner of the focus processing method described herein, and details are not described herein again.
  • the computer readable storage medium may be an internal storage unit of the device described in any of the preceding embodiments, such as a hard disk or a 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 memory card (SMC), and 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 for storing the computer program and other programs and data required by the terminal.
  • the computer readable storage medium can also be used to temporarily store data that has been output or is about to be output.
  • the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Automatic Focus Adjustment (AREA)
  • Studio Devices (AREA)

Abstract

Les modes de réalisation de la présente invention concernent un procédé et un dispositif de traitement de mise au point, ledit procédé comportant les étapes consistant à: acquérir une direction de déplacement d'un objet cible par rapport à un dispositif de caméra; et déterminer une direction de mise au point automatique selon la direction de déplacement, et effectuer une mise au point automatique selon la direction de mise au point automatique, de façon à réaliser la mise au point sur l'objet cible. Les modes de réalisation de la présente invention réalisent la mise au point sur l'objet cible en mouvement, satisfont les exigences de poursuite et de mise au point sur l'objet cible, optimisent l'effet de mise au point, améliorent le rendement de réalisation d'une mise au point réussie, et satisfont les exigences des utilisateurs concernant la mise au point automatique et intelligente sur l'objet cible en mouvement.
PCT/CN2017/103697 2017-09-27 2017-09-27 Procédé et dispositif de traitement de mise au point WO2019061079A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2017/103697 WO2019061079A1 (fr) 2017-09-27 2017-09-27 Procédé et dispositif de traitement de mise au point
CN201780004744.2A CN108496350B (zh) 2017-09-27 2017-09-27 一种对焦处理方法及设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/103697 WO2019061079A1 (fr) 2017-09-27 2017-09-27 Procédé et dispositif de traitement de mise au point

Publications (1)

Publication Number Publication Date
WO2019061079A1 true WO2019061079A1 (fr) 2019-04-04

Family

ID=63344796

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/103697 WO2019061079A1 (fr) 2017-09-27 2017-09-27 Procédé et dispositif de traitement de mise au point

Country Status (2)

Country Link
CN (1) CN108496350B (fr)
WO (1) WO2019061079A1 (fr)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112000226A (zh) * 2020-08-26 2020-11-27 杭州海康威视数字技术股份有限公司 一种人眼视线估计方法、装置及视线估计系统
CN112835172A (zh) * 2020-12-31 2021-05-25 华兴源创(成都)科技有限公司 一种定倍率成像的自动对焦方法及系统
CN113364968A (zh) * 2020-03-05 2021-09-07 浙江宇视科技有限公司 一种对焦方法、装置、摄像机和可读存储介质
CN114143594A (zh) * 2021-12-06 2022-03-04 百度在线网络技术（北京）有限公司 视频画面的处理方法、装置、设备及可读存储介质
CN114422685A (zh) * 2020-10-13 2022-04-29 Oppo广东移动通信有限公司 对焦方法及相关装置
CN115297262A (zh) * 2022-08-09 2022-11-04 中国电信股份有限公司 对焦方法、对焦装置、存储介质与电子设备

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109104573B (zh) * 2018-09-29 2021-01-08 维沃移动通信（杭州）有限公司 一种确定对焦点的方法及终端设备
CN111050060B (zh) * 2018-10-12 2021-08-31 华为技术有限公司 一种应用于终端设备的对焦方法、装置和终端设备
CN109451240B (zh) * 2018-12-04 2021-01-26 百度在线网络技术（北京）有限公司 对焦方法、装置、计算机设备和可读存储介质
CN109525786B (zh) * 2018-12-26 2021-04-30 北京旷视科技有限公司 视频处理方法、装置、终端设备及存储介质
CN109769090A (zh) * 2019-02-18 2019-05-17 桂林长海发展有限责任公司 一种基于图像处理的长焦变倍快速聚焦方法及系统
CN112004019B (zh) * 2019-05-27 2023-02-24 福建天晴数码有限公司 跟踪对焦方法及计算机可读存储介质
CN112132858A (zh) * 2019-06-25 2020-12-25 杭州海康微影传感科技有限公司 一种视频跟踪设备的跟踪方法和视频跟踪设备
WO2021026754A1 (fr) * 2019-08-13 2021-02-18 深圳市大疆创新科技有限公司 Procédé et appareil de commande de mise au point pour appareil de photographie, et aéronef sans pilote
CN110545384B (zh) * 2019-09-23 2021-06-08 Oppo广东移动通信有限公司 对焦方法和装置、电子设备、计算机可读存储介质
CN112136312A (zh) * 2019-10-21 2020-12-25 深圳市大疆创新科技有限公司 一种获取目标距离的方法、控制装置及移动平台
CN110933314B (zh) * 2019-12-09 2021-07-09 Oppo广东移动通信有限公司 追焦拍摄方法及相关产品
CN110991397B (zh) * 2019-12-17 2023-08-04 深圳市捷顺科技实业股份有限公司 一种行进方向确定方法及相关设备
CN111131717B (zh) * 2019-12-31 2021-10-26 深圳市维海德技术股份有限公司 聚焦方法、装置、设备与计算机可读存储介质
CN114466129A (zh) * 2020-11-09 2022-05-10 哲库科技(上海)有限公司 图像处理方法、装置、存储介质及电子设备
CN114697524B (zh) * 2020-12-30 2023-05-02 浙江宇视科技有限公司 自动聚焦方法、装置、电子设备及介质
CN113542604A (zh) * 2021-07-12 2021-10-22 口碑(上海)信息技术有限公司 视频对焦方法及装置
CN115499585B (zh) * 2022-09-07 2024-04-16 湖南中信安科技有限责任公司 一种混杂场景执法视频焦点局部修正方法与系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103179338A (zh) * 2011-12-22 2013-06-26 奥林巴斯映像株式会社 跟踪装置和跟踪方法
CN103945126A (zh) * 2014-04-21 2014-07-23 中国人民解放军国防科学技术大学 一种自动对焦定位方法
CN104038691A (zh) * 2013-03-07 2014-09-10 联发科技股份有限公司 自动聚焦方法及自动聚焦装置
US20150201182A1 (en) * 2013-04-11 2015-07-16 Altek Semiconductor Corp. Auto focus method and auto focus apparatus
CN105259729A (zh) * 2014-07-17 2016-01-20 宁波舜宇光电信息有限公司 一种af快速对焦方法
CN106961552A (zh) * 2017-03-27 2017-07-18 联想(北京)有限公司 一种对焦控制方法及电子设备

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101661624A (zh) * 2009-09-24 2010-03-03 北京中星微电子有限公司 运动跟踪方法及装置
JP2013221993A (ja) * 2012-04-13 2013-10-28 Olympus Corp オートフォーカス制御装置、オートフォーカス制御方法、および撮像装置
US10192582B2 (en) * 2015-05-21 2019-01-29 Adobe Inc. Automatic generation of time-lapse videos
CN105227833A (zh) * 2015-09-09 2016-01-06 华勤通讯技术有限公司 连续对焦方法及装置
CN106488124A (zh) * 2016-10-20 2017-03-08 努比亚技术有限公司 一种跟踪锁定微距拍摄方法及终端
CN106791411B (zh) * 2016-12-28 2020-02-21 歌尔科技有限公司 一种镜头调焦方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103179338A (zh) * 2011-12-22 2013-06-26 奥林巴斯映像株式会社 跟踪装置和跟踪方法
CN104038691A (zh) * 2013-03-07 2014-09-10 联发科技股份有限公司 自动聚焦方法及自动聚焦装置
US20150201182A1 (en) * 2013-04-11 2015-07-16 Altek Semiconductor Corp. Auto focus method and auto focus apparatus
CN103945126A (zh) * 2014-04-21 2014-07-23 中国人民解放军国防科学技术大学 一种自动对焦定位方法
CN105259729A (zh) * 2014-07-17 2016-01-20 宁波舜宇光电信息有限公司 一种af快速对焦方法
CN106961552A (zh) * 2017-03-27 2017-07-18 联想(北京)有限公司 一种对焦控制方法及电子设备

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113364968A (zh) * 2020-03-05 2021-09-07 浙江宇视科技有限公司 一种对焦方法、装置、摄像机和可读存储介质
CN113364968B (zh) * 2020-03-05 2023-06-20 浙江宇视科技有限公司 一种对焦方法、装置、摄像机和可读存储介质
CN112000226A (zh) * 2020-08-26 2020-11-27 杭州海康威视数字技术股份有限公司 一种人眼视线估计方法、装置及视线估计系统
CN114422685A (zh) * 2020-10-13 2022-04-29 Oppo广东移动通信有限公司 对焦方法及相关装置
CN112835172A (zh) * 2020-12-31 2021-05-25 华兴源创(成都)科技有限公司 一种定倍率成像的自动对焦方法及系统
CN114143594A (zh) * 2021-12-06 2022-03-04 百度在线网络技术（北京）有限公司 视频画面的处理方法、装置、设备及可读存储介质
CN115297262A (zh) * 2022-08-09 2022-11-04 中国电信股份有限公司 对焦方法、对焦装置、存储介质与电子设备

Also Published As

Publication number Publication date
CN108496350A (zh) 2018-09-04
CN108496350B (zh) 2021-02-02

Similar Documents

Publication Publication Date Title
WO2019061079A1 (fr) Procédé et dispositif de traitement de mise au point
JP7311418B2 (ja) 焦点合わせの方法、端末、およびコンピュータ可読記憶媒体
US9998650B2 (en) Image processing apparatus and image pickup apparatus for adding blur in an image according to depth map
CN108076278B (zh) 一种自动对焦方法、装置及电子设备
US8068164B2 (en) Face recognition auto focus apparatus for a moving image
JP6887960B2 (ja) 自動焦点トリガのためのシステムおよび方法
CN110381261B (zh) 聚焦方法、装置、计算机可读存储介质及电子设备
US9160922B2 (en) Subject detection device and control method for the same, imaging apparatus, and storage medium
JP2015104016A (ja) 被写体検出装置、撮像装置、被写体検出装置の制御方法、被写体検出装置の制御プログラムおよび記憶媒体
WO2014153950A1 (fr) Procédé de focalisation rapide automatique et dispositif d'acquisition d'image
TWI471677B (zh) 自動對焦方法及自動對焦裝置
US20150201182A1 (en) Auto focus method and auto focus apparatus
US9838594B2 (en) Irregular-region based automatic image correction
JP2009025381A (ja) デジタルカメラ
WO2019104569A1 (fr) Procédé et dispositif de mise au point, et support de stockage lisible
TW201541141A (zh) 使用多鏡頭的自動對焦系統及其方法
WO2017166076A1 (fr) Procédé, dispositif et appareil permettant de déterminer une fenêtre de mise au point
WO2020042000A1 (fr) Dispositif de caméra et procédé de mise au point
WO2017101292A1 (fr) Procédé, dispositif et système de mise au point automatique
JP6495451B2 (ja) 方向認識オートフォーカス
US20140327743A1 (en) Auto focus method and auto focus apparatus
CN102650801A (zh) 摄像装置及其自动对焦方法
WO2022021093A1 (fr) Procédé de photographie, appareil de photographie et support d'enregistrement
TW201236448A (en) Auto-focusing camera and method for automatically focusing of the camera
US20240163554A1 (en) System and method for image auto-focusing

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: 17927001

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: 17927001

Country of ref document: EP

Kind code of ref document: A1