WO2019061079A1

WO2019061079A1 - Focusing processing method and device

Info

Publication number: WO2019061079A1
Application number: PCT/CN2017/103697
Authority: WO
Inventors: 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: 2017-09-27
Filing date: 2017-09-27
Publication date: 2019-04-04
Also published as: CN108496350B; CN108496350A

Abstract

The embodiments of the present invention provide a focusing processing method and a device, said method comprising: acquiring a moving direction of a target object relative to a camera device; and determining an automatic focusing direction according to the moving direction, and performing automatic focusing according to the automatic focusing direction, so as to focus the target object. The embodiments of the present invention realize focusing of the moving target object, satisfies the requirements of tracking and focusing the target object, optimizes the focusing effect, improves the efficiency of performing focusing successfully, and satisfies the requirements of the users for automatic and intelligent focusing of the moving target object.

Description

Focus processing method and device

Technical field

The present invention relates to the field of control technologies, and in particular, to a focus processing method and apparatus.

Background technique

The method of autofocus is generally divided into active and passive. Among them, 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.

However, 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.

Summary of the invention

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.

In a first aspect, an embodiment of the present invention provides a focus processing method, including:

Obtaining a moving direction of the target object relative to the camera device;

And determining an auto focus direction according to the moving direction, and performing auto focus according to the auto focus direction to focus on the target object.

In a second aspect, 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:

In a third aspect, 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.

In the embodiment of the present invention, 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.

DRAWINGS

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings to be used in the embodiments will be briefly described below. Obviously, the drawings in the following description are only some of the present invention. For the embodiments, those skilled in the art can obtain other drawings according to the drawings without any creative work.

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;

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.

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.

Detailed ways

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

Some embodiments of the present invention are described in detail below with reference to the accompanying drawings. In the absence of conflict, The features of the following embodiments and examples can be combined with each other.

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. In combination with the visual target tracking algorithm in the focusing process, 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 moving direction of the target object with respect to the camera. According to the moving direction combined with the contrast focusing algorithm, 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. Wherein, if the target object carries the positioning device, 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. In addition, 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. After determining the moving direction of the target object relative to the camera device, 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. . In the embodiment of the present invention, a focus processing method is described by taking a corresponding processing by a focus processing device as an example.

Referring to FIG. 1, 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.

In the embodiment of the present invention, the focus processing device can acquire the moving direction of the target object with respect to the imaging device. Specifically, 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. A schematic diagram of a scene for focusing processing. As shown in FIG. 2, 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.

In one embodiment, 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. Specifically, 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. If it is detected that the size of the target person in the image becomes large, determining that 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.

In one embodiment, 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. Specifically, if the target object acquired by the focus processing device carries 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. Specifically, for example, if the target object acquired by the focus processing device carries a GPS positioning 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.

Further, 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. Specifically, 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. As a depth map, 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.

In the embodiment of the present invention, 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. Secondly, since 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.

In one embodiment, 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. Among them, it should be noted that 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. When using 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.

In an embodiment, in a process in which the focus processing device combines the moving direction and the contrast detection method of the target object to implement auto focus, 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. Specifically, 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.

In one embodiment, the contrast is obtained based on a focus evaluation function score of the image contrast design. As shown in FIG. 4, FIG. 4 is a schematic diagram of a focus evaluation function according to an embodiment of the present invention. As shown in FIG. 4, the abscissa x is the focus position, and the ordinate y is the focus evaluation function score, and the established coordinate function. Among them, 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, and 403 shows the focus evaluation function score at the far focus. There may be many variants of this type of function, and 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.

In an embodiment, 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. For example, 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.

Further, if 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. For another 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 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.

In one embodiment, in the implementation of assisting auto focus based on the target tracking algorithm, 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.

Further, in the implementation of the automatic focus adjustment based on the target tracking algorithm, when focusing on the moving target object, the focus processing device 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.

In the embodiment of the present invention, 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. Thereby, 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.

Referring to FIG. 6, 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.

In the embodiment of the present invention, 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.

In the embodiment of the present invention, 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.

In one embodiment, 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.

In the embodiment of the present invention, 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.

S604: Detect whether the contrast is decreased.

In the embodiment of the invention, the focus processing device can detect whether the contrast of the captured image is decreased.

S605: If the detection result is no, the focus control is continued according to the focusing direction.

In the embodiment of the present invention, if the focus processing device detects that the contrast rises, the focus control may be continued according to the focus direction. Specifically, 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. In FIG. 5, 501 represents the contrast at the starting point, 502 represents the contrast at the best focus point, and 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. Each time one step is moved, 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.

S606: If the detection result is yes, determine whether the falling value of the contrast is less than a preset threshold.

In the embodiment of the present invention, when detecting the contrast, if the contrast is detected to decrease, the focus processing device determines whether the decrease value of the contrast is less than a preset threshold.

S607: If the judgment result is YES, the current focus is determined as the focus focus of the target object.

In the embodiment of the present invention, if 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. Taking FIG. 5 as an example, 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. When 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. Compared with the prior art, 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.

S608: If the result of the determination is no, detecting a change in the size of the target object in the image or the positional area in the image.

In the embodiment of the present invention, if 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. Taking FIG. 5 as an example, the focus lens of the imaging device of the focus processing device moves from left to right in equal steps from the starting point 501, and the contrast of the image is calculated every time one step is moved. When the contrast reaches 503, The falling value of the contrast is not less than the preset threshold, indicating that the camera lens has defocused beyond the best focus of the target object, and the size of the target object in the image or the change in the position area in the image will be detected.

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.

In the embodiment of the present invention, if 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. Taking FIG. 5 as an example, when the contrast is detected to reach 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 large at this time, The direction near the camera is determined as the auto focus direction, the focus direction is automatically adjusted, and the target is focused according to the auto focus direction.

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.

In the embodiment of the present invention, 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.

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.

In the embodiment of the present invention, 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. Taking FIG. 5 as an example, when the contrast reaches 503, 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.

In the embodiment of the present invention, after determining the auto focus 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.

In the embodiment of the present invention, 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. Thereby, 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.

Referring to FIG. 7 , FIG. 7 is a schematic structural diagram of a focus processing device according to an embodiment of the present invention. Specifically, 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.

Specifically, 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.

Specifically, 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. .

Specifically, 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.

Specifically, 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.

Specifically, 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.

Specifically, 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.

Specifically, 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.

Specifically, 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.

Specifically, 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.

Specifically, 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.

Specifically, 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.

Specifically, 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.

Specifically, 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.

Specifically, 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.

Specifically, 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.

In the embodiment of the present invention, 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. Thereby, the automatic tracking and focusing of the moving target object can be realized, the focusing effect is optimized, and the focusing efficiency is improved.

Referring to FIG. 8, FIG. 8 is a schematic structural diagram of another focus processing device according to an embodiment of the present invention. Specifically, 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:

Specifically, the processor 801 calls a program instruction stored in the memory 802 for performing the following steps:

Visually identifying the target object;

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;

And determining a moving direction of the target object with respect to the imaging device according to the change state information.

Obtaining, by using a positioning device carried by the target object, location coordinates of the target object;

Determining a moving direction of the target object with respect to the image pickup device according to the position coordinates.

Obtaining a depth map of the target object;

And determining, according to the acquired depth map, a moving direction of the target object with respect to the camera.

Determining the target object based on the captured image;

Wherein, the target object is determined according to a selection operation in an image, or is automatically identified according to an image recognition algorithm.

Performing image tracking processing on the target object to obtain a location area of the target object in the image;

Calculating a contrast of the captured image according to the location area;

A focus focus of the target object is determined based on the contrast.

Detecting the contrast of the captured image;

If the contrast rise is detected, the focus control is continued in accordance with the focus direction.

Detecting the contrast of the captured image;

If the contrast drop is detected, the focus focus of the target object is determined according to the decrease value of the contrast.

If it is detected that the decrease value of the contrast is less than a preset threshold, the current focus is determined as the focus focus of the target object.

If it is detected that the falling value of the contrast is not less than a preset threshold, determining an auto-focusing direction according to the change state information of the target object; performing focus control according to the auto-focusing direction.

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.

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.

Specifically, 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.

Comparing 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; if the similarity is greater than the preset similarity threshold, determining the initial region as the current image The location area where the target object is located in the frame.

If it is detected that the sharpness of the current image frame is less than a preset sharpness threshold, the preset similarity threshold is lowered.

If it is detected that the resolution of the current image frame is less than a preset definition threshold, 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.

It should be understood that, in the embodiment of the present invention, 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.

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.

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.

In the embodiment of the present method, 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. Thereby, the automatic tracking and focusing of the moving target object can be realized, the focusing effect is optimized, and the focusing efficiency is improved.

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. Further, 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.

One of ordinary skill in the art can understand that all or part of the process of implementing the foregoing embodiments can be completed by a computer program to instruct related hardware, and the program can be stored in a computer readable storage medium. When executed, the flow of an embodiment of the methods as described above may be included. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

The above is only the preferred embodiment of the present invention, and the scope of the present invention is not limited thereto, and thus equivalent changes made in the claims of the present invention are still within the scope of the present invention.

Claims

A focus processing method, comprising:

Obtaining a moving direction of the target object relative to the camera device;

And determining an auto focus direction according to the moving direction, and performing auto focus according to the auto focus direction to focus on the target object.
The method according to claim 1, wherein the obtaining a moving direction of the target object relative to the camera comprises:

Visually identifying the target object;

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;

And determining a moving direction of the target object with respect to the imaging device according to the change state information.
The method according to claim 1, wherein the acquiring the moving direction of the target object relative to the camera device further comprises:

Obtaining, by using a positioning device carried by the target object, location coordinates of the target object;

Determining a moving direction of the target object with respect to the image pickup device according to the position coordinates.
The method according to claim 1, wherein the acquiring the moving direction of the target object relative to the camera device further comprises:

Obtaining a depth map of the target object;

And determining, according to the acquired depth map, a moving direction of the target object with respect to the camera.
The method according to claim 2, wherein before the obtaining the moving direction of the target object relative to the camera device, the method comprises:

Determining the target object based on the captured image;

Wherein, the target object is determined according to a selection operation in an image, or is based on image recognition The algorithm does not automatically identify the determined ones.
The method of claim 1 wherein said focusing on said target object comprises:

Performing image tracking processing on the target object to obtain a location area of the target object in the image;

Calculating a contrast of the captured image according to the location area;

A focus focus of the target object is determined based on the contrast.
The method according to claim 6, wherein the determining the focus focus of the target object according to the contrast comprises:

Obtaining the contrast of the image taken by the detection;

If the contrast rise is detected, the focus control is continued in accordance with the focus direction.
The method according to claim 7, wherein the determining the focus focus of the target object according to the contrast further comprises:

Obtaining the contrast of the image taken by the detection;

If the contrast drop is detected, the focus focus of the target object is determined according to the decrease value of the contrast.
The method according to claim 8, wherein the determining the focus focus of the target object according to the falling value of the contrast comprises:

If it is detected that the decrease value of the contrast is less than a preset threshold, the current focus is determined as the focus focus of the target object.
The method according to claim 8 or 9, wherein the determining the focus focus of the target object according to the falling value of the contrast further comprises:

If it is detected that the falling value of the contrast is not less than a preset threshold, determining an auto-focusing direction according to the change state information of the target object;

Focus control is performed according to the auto focus direction.
The method according to claim 10, wherein the determining the auto focus direction according to the change state information of the target object comprises:

Detecting a change in size of the target object in the image or a positional area in the image;

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 method according to claim 10, wherein the determining the auto-focusing direction according to the change state information of the target object further comprises:

Detecting a change in size of the target object in the image or a positional area in the image;

If it is detected that the size or the positional area becomes small, the direction away from the image pickup device is determined as the autofocus direction.
The method according to claim 10, wherein the determining the auto-focusing direction according to the change state information of the target object further comprises:

Detecting a change in size of the target object in the image or a positional area in the image;

If it is detected that the size or the positional area is unchanged, the direction opposite to the focusing direction is determined as the autofocusing direction.
The method according to claim 6, wherein the performing an image tracking process on the target object to obtain a location area of the target object in the image comprises:

Comparing 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 during focusing in accordance with the focus control;

If the similarity is greater than the preset similarity threshold, the initial region is determined as the location region in which the target object is located in the current image frame.
The method of claim 14 further comprising:

If it is detected that the sharpness of the current image frame is less than a preset sharpness threshold, the preset similarity threshold is lowered.
The method according to claim 14 or 15, further comprising:

If it is detected that the resolution of the current image frame is less than a preset definition threshold, 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.
A focus processing device, comprising: 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:

Obtaining a moving direction of the target object relative to the camera device;

And determining an auto focus direction according to the moving direction, and performing auto focus according to the auto focus direction to focus on the target object.
The device according to claim 17, wherein the processor is configured to perform the following steps when acquiring a moving direction of the target object with respect to the camera device:

Visually identifying the target object;

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;

And determining a moving direction of the target object with respect to the imaging device according to the change state information.
The device according to claim 17, wherein the processor is configured to perform the following steps when acquiring a moving direction of the target object with respect to the camera device:

Obtaining, by using a positioning device carried by the target object, location coordinates of the target object;

Determining a moving direction of the target object with respect to the image pickup device according to the position coordinates.
The device according to claim 17, wherein the processor is configured to perform the following steps when acquiring a moving direction of the target object with respect to the camera device:

Obtaining a depth map of the target object;

Determining a moving side of the target object relative to the camera device according to the acquired depth map to.
The device according to claim 18, wherein the processor performs the following steps before acquiring a moving direction of the target object with respect to the camera device:

Determining the target object based on the captured image;

Wherein, the target object is determined according to a selection operation in an image, or is automatically identified according to an image recognition algorithm.
The device according to claim 17, wherein the processor is configured to perform the following steps when focusing on the target object:

Performing image tracking processing on the target object to obtain a location area of the target object in the image;

Calculating a contrast of the captured image according to the location area; determining a focus focus of the target object according to the contrast.
The apparatus according to claim 22, wherein said processor is configured to perform the following steps when determining a focus focus of said target object based on said contrast:

Detecting the contrast of the captured image;

If the contrast rise is detected, the focus control is continued in accordance with the focus direction.
The apparatus according to claim 23, wherein said processor is configured to perform the following steps when determining a focus focus of said target object based on said contrast:

Detecting the contrast of the captured image;

If the contrast drop is detected, the focus focus of the target object is determined according to the decrease value of the contrast.
The device according to claim 24, wherein the processor is configured to perform the following steps when determining the focus focus of the target object according to the falling value of the contrast:

If it is detected that the decrease value of the contrast is less than a preset threshold, the current focus is determined as the focus focus of the target object.
The device according to claim 24 or 25, wherein the processor is configured to perform the following steps when determining the focus of the target object according to the falling value of the contrast:

If it is detected that the falling value of the contrast is not less than a preset threshold, determining an auto-focusing direction according to the change state information of the target object;

Focus control is performed according to the auto focus direction.
The device according to claim 26, wherein the processor is configured to perform the following steps when determining an autofocus direction according to the change state information of the target object:

Detecting a change in size of the target object in the image or a positional area in the image;

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 device according to claim 26, wherein the processor is configured to perform the following steps when determining an autofocus direction according to the change state information of the target object:

Detecting a change in size of the target object in the image or a positional area in the image;

If it is detected that the size or the positional area becomes small, the direction away from the image pickup device is determined as the autofocus direction.
The device according to claim 26, wherein the processor is configured to determine an autofocus direction according to the change state information of the target object, and perform the following steps:

Detecting a change in size of the target object in the image or a positional area in the image;

If it is detected that the size or the positional area is unchanged, the direction opposite to the focusing direction is determined as the autofocusing direction.
The device according to claim 22, wherein the processor is configured to perform image tracking processing on the target object, and perform the following steps when obtaining the location area of the target object in the image:

Comparing an image in an initial region of the current image frame with an image of a location region in which the target object is located in a previous image frame;

If the similarity is greater than the preset similarity threshold, the initial region is determined as the location region in which the target object is located in the current image frame.
The device according to claim 30, wherein said processor is configured to perform the following steps:

If it is detected that the sharpness of the current image frame is less than a preset sharpness threshold, the preset similarity threshold is lowered.
The device according to claim 30 or 31, wherein the processor is configured to perform the following steps:

If it is detected that the resolution of the current image frame is less than a preset definition threshold, 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.
A computer readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the method of any one of claims 1 to 16.