WO2020133409A1 - 拍照方法及拍照终端 - Google Patents

拍照方法及拍照终端 Download PDF

Info

Publication number
WO2020133409A1
WO2020133409A1 PCT/CN2018/125603 CN2018125603W WO2020133409A1 WO 2020133409 A1 WO2020133409 A1 WO 2020133409A1 CN 2018125603 W CN2018125603 W CN 2018125603W WO 2020133409 A1 WO2020133409 A1 WO 2020133409A1
Authority
WO
WIPO (PCT)
Prior art keywords
candidate
photo
photos
preset
camera terminal
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2018/125603
Other languages
English (en)
French (fr)
Inventor
应礼剑
胡攀
曹子晟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
SZ DJI Technology Co Ltd
Original Assignee
SZ DJI Technology Co Ltd
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 SZ DJI Technology Co Ltd filed Critical SZ DJI Technology Co Ltd
Priority to PCT/CN2018/125603 priority Critical patent/WO2020133409A1/zh
Priority to CN201880068096.1A priority patent/CN111247787A/zh
Publication of WO2020133409A1 publication Critical patent/WO2020133409A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/80Camera processing pipelines; Components thereof
    • H04N23/84Camera processing pipelines; Components thereof for processing colour signals
    • H04N23/88Camera processing pipelines; Components thereof for processing colour signals for colour balance, e.g. white-balance circuits or colour temperature control
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/64Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/70Circuitry for compensating brightness variation in the scene

Definitions

  • This application relates to the field of computer technology, in particular to a photographing method and photographing terminal.
  • this application shows a photographing method and a photographing terminal.
  • the present application shows a photographing method applied to a photographing terminal.
  • the method includes: determining a current shooting scene; determining a user's interest in the current shooting scene of the photographing terminal; if the interest level If it is greater than the preset interest level, a candidate photo is taken; the candidate photo is saved.
  • the present application shows a camera terminal
  • the camera terminal includes: a processor and a camera lens; the processor is used to determine a current shooting scene; and the user of the camera terminal is interested in the current shooting scene
  • the camera lens is used to take a candidate photo if the interest level is greater than a preset interest level; the processor is also used to save the candidate photo.
  • an electronic device including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to perform as described in the first aspect Photographing method.
  • a non-transitory computer-readable storage medium when instructions in the storage medium are executed by a processor of an electronic device, enabling the electronic device to perform the photographing as described in the first aspect method.
  • a computer program product which, when instructions in the computer program product are executed by a processor of an electronic device, enables the electronic device to execute the photographing method described in the first aspect.
  • the present application includes the following advantages:
  • the current shooting scene can be determined, and the user's interest in the current shooting scene can be determined by the camera terminal. If the interest is greater than the preset interest, the shooting Candidate photo, save the candidate photo.
  • the photographing terminal can automatically take pictures of the scene that the user of the photographing terminal is interested in the presented scene without manual participation, thereby reducing the scrap rate of the pictures.
  • FIG. 1 is a flowchart of steps of a photographing method of the present application
  • FIG. 3 is a flowchart of steps of a photographing method of the present application.
  • FIG. 7 is a structural block diagram of a camera terminal of the present application.
  • FIG. 8 is a structural block diagram of a photographing terminal of the present application.
  • the photographing terminal includes a device with a photographing function, such as a camera, a mobile phone, and a tablet computer.
  • the method may specifically include The following steps:
  • step S101 the current shooting scene is determined.
  • a sample image set can be obtained in advance, and the sample image set includes at least one sample image marked with a scene.
  • the scene includes: people, faces, sky, buildings, plants, mountains, water, etc.
  • the sample image set can be used
  • the sample image trains the preset neural network model until the weights in the preset neural network model all converge, thereby obtaining a scene classification model based on the neural network.
  • the preset neural network models include CNN (Convolutional Neural Networks, Convolutional Neural Network) or LSTM (Long Short-Term Memory, long-short-term memory network), etc., which is not limited in this application.
  • the user of the camera terminal can carry the camera terminal on his body, for example, hang the camera terminal on his chest, or install the camera terminal on the shoulder of the user through the gimbal. In this way, the camera terminal will According to the method of the present application, the candidate photos are automatically taken and stored, and the user of the camera terminal is not required to participate in the whole process.
  • the camera terminal in order to take a photo of interest to the user, the camera terminal needs to determine the current shooting scene, and then execute step S102.
  • the camera terminal can take a scene picture, for example, take a picture as the shooting scene picture, and then use the neural network-based scene classification model to determine the scene presented by the scene picture, and as the current shooting scene, for example, the scene
  • the picture is input into the scene classification model based on the neural network to obtain the scene output from the scene classification model based on the neural network.
  • the camera terminal may also discard the scene picture.
  • step S102 the degree of interest of the user of the photographing terminal in the current shooting scene is determined.
  • the user of the photographing terminal may set the user's interest level for each shooting scene in the photographing terminal in advance.
  • the camera terminal can form a correspondence table with the shooting scene and the interest level of the shooting terminal set by the user of the camera terminal, and store it in the shooting scene and the user In the correspondence between the interest levels of the shooting scenes, the above operations are also performed for every other shooting scene.
  • the correspondence between the shooting scene and the user's interest in the shooting scene set in the shooting terminal in advance can be determined, and then the degree of interest corresponding to the current shooting scene can be found in the correspondence , So as to obtain the interest degree of the user of the camera terminal in the current shooting scene.
  • a sample image set may be obtained in advance, and the sample image set includes at least one sample image marked with a scene and the user's interest in the marked scene of the camera terminal, and the sample in the sample image set may be used
  • the image trains the preset neural network model until the weights in the preset neural network model all converge, so as to obtain the interest degree determination model based on the neural network.
  • the preset neural network model includes CNN or LSTM, etc., which is not limited in this application.
  • the interest degree determination model based on the neural network may be used to determine the interest degree of the user of the camera terminal in the current shooting scene.
  • the current shooting scene is input into the scene classification model based on the neural network to obtain the interest degree output from the scene classification model based on the neural network, thereby obtaining the interest degree of the user of the camera terminal in the current shooting scene.
  • step S103 If the degree of interest is greater than the preset degree of interest, in step S103, a candidate photo is taken.
  • the size between the degree of interest and the preset degree of interest can be compared, if the degree of interest is greater than the preset degree of interest, it means that the user of the camera terminal is interested in the current shooting scene, and can then take a candidate photo, The scene presented in the candidate photo is the current shooting scene. Therefore, the candidate photo is also often a photo of interest to the user of the camera terminal, so the candidate photo can be saved.
  • the degree of interest is less than or equal to the preset degree of interest, it means that the user of the camera terminal is not interested in the current shooting scene. In this case, there is no need to take a candidate photo, and the process can be ended.
  • the shooting scene of the camera terminal's lens is often constantly changing, in order to be able to take pictures
  • the user of the terminal is interested in the picture of the presented scene, and therefore, can return to step S101.
  • step S104 candidate photos are saved.
  • the current shooting scene can be determined, and the interest degree of the user of the photographing terminal in the current shooting scene can be determined. If the degree of interest is greater than the preset degree of interest, the candidate photos are taken and the candidate photos are saved.
  • the photographing terminal can automatically take pictures of the scene that the user of the photographing terminal is interested in the presented scene without manual participation, thereby reducing the scrap rate of the pictures.
  • step S103 the method further includes:
  • step S201 the image quality of the candidate photo is determined.
  • the steps can be realized through the following processes, including:
  • the contrast information of the candidate photos can be obtained, and then the difference information between the contrast information of the candidate photos and the preset contrast information is calculated and used as the autofocus statistical information.
  • the preset contrast information may be the contrast information of a photo that is of interest to a large number of people, that is, the preset contrast information is the standard contrast information.
  • the contrast information of a photo is the standard contrast information
  • the photo is affected by the majority of people in contrast Interested.
  • the first number of pixels in the candidate photos whose pixel value is less than the first preset pixel value can be counted; the second number of pixels in the candidate photo whose pixel value is greater than the second preset pixel value can be counted;
  • the sum of the second quantity obtains the automatic exposure statistical information.
  • the first preset pixel value is smaller than the second preset pixel value, for example, the first preset pixel value may be 45, the second preset pixel value may be 204, and so on.
  • the target red gain can be the red gain of the photos that are of interest to the general population, that is, the target red gain is the standard red gain.
  • the red gain of a photo is the standard red gain, the photo is affected by the majority of people in the red gain interest.
  • the target blue gain can be the blue gain of the photos that are of interest to the general population, that is, the target blue gain is the standard blue gain.
  • the blue gain of a photo is the standard blue gain, the photo is in the blue
  • the color gain is of interest to the general public.
  • the first preset coefficient, the second preset coefficient, and the first preset coefficient may be determined according to actual conditions.
  • the present application does not limit the specific values of the first preset coefficient, the second preset coefficient, and the first preset coefficient.
  • step S202 it is determined whether the image quality is greater than the first preset threshold.
  • step S104 is executed: save the candidate photos.
  • the image quality of the candidate photo is less than the first preset threshold, it means that at least one of the autofocus statistical information, automatic exposure statistical information, and automatic white balance statistical information of the candidate photo meets the requirements of the standard.
  • the user of the camera terminal is interested in the scene presented by the candidate photo, and may not be interested in the candidate photo because the image quality of the candidate photo is less than the first preset threshold, resulting in the candidate photo being a waste piece, which will still improve the photo The scrap rate. Therefore, in order to reduce the scrap rate of photos, you need to determine the image quality of the candidate photos, and save the candidate photos if the image quality is greater than the first preset threshold.
  • the preset threshold indicates that the candidate photos meet the requirements of the standard in auto focus statistics, auto exposure statistics, and auto white balance statistics. Therefore, users of the camera terminal are more likely to be interested in the candidate photos, thus Can reduce the scrap rate of photos.
  • step S203 If the image quality is less than or equal to the first preset threshold, in step S203, the candidate photos are discarded.
  • step S204 is executed.
  • step S204 the shooting parameters of the camera terminal are adjusted so that the image quality of the photos taken based on the adjusted shooting parameters of the camera terminal is greater than the first preset threshold.
  • the image quality of the photos taken by the camera terminal is affected by the shooting parameters of the camera terminal.
  • the shooting parameters of the camera terminal are not suitable for the current shooting environment, or the current environment is dark and the exposure of the camera terminal is low, resulting in shooting Photos are dark, or the exposure time of the camera terminal is long, resulting in blurred photos.
  • the camera terminal can automatically adjust the shooting parameters so that the image quality of the photos taken based on the adjusted shooting parameters of the camera terminal is greater than the first
  • the threshold is set, so that the photographing terminal can retake photos that are of interest to the user and present the current shooting scene based on the adjusted shooting parameters.
  • step S205 the candidate photos are retaken based on the adjusted shooting parameters.
  • the image quality of multiple photos taken repeatedly in a shooting scene is less than the first preset threshold, it often means that the shooting scene is not suitable for taking photos. In order to save the shooting resources of the camera terminal, it can be no longer necessary. Continue to take photos in the shooting scene.
  • the cumulative number of shots of re-taken candidate photos in the current shooting scene can be counted. If the cumulative number of shooting times is less than the preset number of times, the candidate photos are taken again based on the adjusted shooting parameters. If the cumulative number of shots is greater than or equal to the preset number of times, the process ends.
  • the preset number of times may be set by the user of the photographing terminal in the photographing terminal in advance, and the preset number of times may be 3, 4, 5, or 6, etc., which is not limited in this application.
  • step S103 the method further includes:
  • step S301 it is determined whether the candidate photo has motion blur.
  • the first position of the SIFT (Scale-invariant feature transform) feature point in the candidate photo in the candidate photo can be obtained.
  • the camera terminal can continuously take photos, so that the adjacent photos are very similar.
  • the reference photos that are adjacent to the candidate photos and whose shooting order is before the candidate photos are determined.
  • step S104 is executed: the candidate photo is saved.
  • the camera terminal sometimes shoots the candidate photos when the user is walking. Therefore, the candidate photos may have motion blur, for example, some parts of the candidate photos are blurred and unclear.
  • the majority of people are not interested in photos with motion blur, so even if the user of the camera terminal is interested in the scene presented by the candidate photo, they may not be interested in the candidate photo due to the motion blur of the candidate photo.
  • the candidate photos are scraps, which will still increase the scrap rate of the photos. Therefore, in order to reduce the scrap rate of the photos, it is necessary to determine whether the candidate photos have motion blur. If the candidate photos do not have motion blur, it indicates the use of the camera terminal. It is more likely that the person is interested in the candidate photos, and then saving the candidate photos can reduce the scrap rate of the photos.
  • step S302 the candidate photo is discarded.
  • step S303 is executed.
  • step S303 the shooting parameters of the camera terminal are adjusted so that the photos taken based on the adjusted shooting parameters of the camera terminal do not have motion blur.
  • Whether there is motion blur in the photos taken by the camera terminal is affected by the camera terminal's shooting parameters, which include exposure brightness and/or exposure duration. For example, the current ambient brightness is low, and the exposure of the camera terminal is low, resulting in blurring of the captured photos, or the exposure time of the camera terminal is long, resulting in blurring of the captured photos.
  • the camera terminal can automatically adjust the shooting parameters, such as increasing the exposure brightness of the camera terminal and/or reducing the exposure time of the camera terminal to make the camera based on the camera terminal
  • the image quality of the photos taken by the adjusted shooting parameters is greater than the first preset threshold, which in turn enables the camera terminal to retake photos that are of interest to the user and present the current shooting scene based on the adjusted shooting parameters.
  • step S304 the candidate photos are retaken based on the adjusted shooting parameters.
  • the image quality of multiple photos taken repeatedly in a shooting scene is less than the first preset threshold, it often means that the shooting scene is not suitable for taking photos. In order to save the shooting resources of the camera terminal, it can be no longer necessary. Continue to take photos in the shooting scene.
  • the cumulative number of shots of re-taken candidate photos in the current shooting scene can be counted. If the cumulative number of shooting times is less than the preset number of times, the candidate photos are taken again based on the adjusted shooting parameters. If the cumulative number of shots is greater than or equal to the preset number of times, the process ends.
  • the preset number of times may be set by the user of the photographing terminal in the photographing terminal in advance, and the preset number of times may be 3, 4, 5, or 6, etc., which is not limited in this application.
  • step S103 the method further includes:
  • step S401 the aesthetic quality of the candidate photo is determined.
  • a sample image set can be obtained in advance, and the sample image set includes at least one sample image marked with aesthetic quality, and the sample image in the sample image set can be used to train the preset neural network model until the preset neural network The weights in the model all converge, and a neural network-based aesthetic quality determination model is obtained.
  • the preset neural network model includes CNN or LSTM, etc., which is not limited in this application.
  • the aesthetic quality of the sample image can be marked by professional photographers on the sample image.
  • the aesthetic quality of the candidate photos can be determined using a neural network-based aesthetic quality determination model.
  • the candidate photos are input into the aesthetic quality based on the neural network to obtain the aesthetic quality based on the aesthetic quality output of the neural network, thereby obtaining the aesthetic quality of the candidate photos.
  • step S402 it is determined whether the aesthetic quality is greater than the second preset threshold.
  • step S104 is executed: save the candidate photos.
  • the aesthetic quality of the candidate photos needs to be determined. If the aesthetic quality is greater than the second preset threshold, the candidate photos are saved.
  • the aesthetic quality is greater than the second preset threshold, it means that professional photographers may be interested in the candidate photos, because ordinary people's aesthetic techniques for photos are often lower than professional photographers' aesthetic techniques for photos, so be professional photographers When interested in a photo, ordinary people are often interested in the photo.
  • the aesthetic quality is greater than the second preset threshold, the user of the photographing terminal is more likely to be interested in the candidate photos, thereby reducing the scrap rate of the photos.
  • step S403 If the aesthetic quality is less than or equal to the second preset threshold, in step S403, the candidate photos are discarded.
  • the user candidate photos of the camera terminal may not be interested, that is, in order to save storage space of the camera terminal, the candidate photos may be discarded.
  • the camera terminal may take multiple photos in a scene. If the multiple photos are similar, the user of the camera terminal will often only use one of the photos later.
  • the method further includes:
  • step S501 among the saved photos, it is detected whether there is a stored photo whose similarity with the candidate photo is greater than a preset similarity.
  • any similarity calculation method in the prior art may be used to calculate the similarity between the candidate photos and the saved photos, and the application does not limit the calculation of the similarity.
  • step S104 is executed: save the candidate photo.
  • step S502 If there are stored photos, in step S502, the candidate photos are discarded.
  • only one photo can be saved in a plurality of similar photos continuously taken by the camera terminal, so that the storage resources of the camera terminal can be saved.
  • the camera terminal may take multiple photos in a scene. If the multiple photos are similar, the user of the camera terminal will often only use one of the photos later.
  • the method further includes:
  • step S601 among the stored photos, it is detected whether there is a stored photo whose similarity with the candidate photo is greater than a preset similarity.
  • step S104 is executed: save the candidate photo.
  • step S602 it is determined whether the aesthetic quality of the stored photo is smaller than the aesthetic quality of the candidate photo.
  • step S603 delete the stored photo, and then perform step S104: save the candidate photo.
  • step S604 the candidate photo is discarded.
  • only one photo can be saved in a plurality of similar photos continuously taken by the camera terminal, so that the storage resources of the camera terminal can be saved, and secondly, the saved photos are still the highest aesthetic quality among the multiple photos taken Photos, so that users of the camera terminal can later use the photos with the highest aesthetic quality, thereby improving the user experience of the camera terminal.
  • the camera terminal includes an inertial measurement unit IMU, a sensor, and a hardware clock; the method further includes: using a hardware clock to synchronize the frequency of information collected by the IMU and the frequency of the camera terminal taking photos with the sensor. In this way, after the candidate photo is taken, the steering angle of the camera terminal can be obtained; the measured angle of the IMU; the angle difference between the steering angle and the measured angle can be determined; if the angle difference is less than the fourth preset threshold, the candidate photo can be saved.
  • the camera terminal is applied to an aircraft.
  • the camera terminal may specifically include: a processor 1111 and a camera lens 1212;
  • the processor 11 is used to determine the current shooting scene; determine the interest of the user of the camera terminal in the current shooting scene;
  • the photo lens 12 is used to take a candidate photo if the degree of interest is greater than a preset degree of interest
  • the processor 11 is also used to save the candidate photos.
  • the processor 11 is further configured to determine the image quality of the candidate photo; if the image quality is greater than the first preset threshold, save the candidate photo.
  • the processor 11 is further configured to discard the candidate photos if the image quality is less than or equal to the first preset threshold; adjust the shooting parameters of the camera terminal to Making the image quality of the photo taken based on the adjusted shooting parameters of the camera terminal greater than the first preset threshold;
  • the camera lens 12 is also used to retake the candidate photos based on the adjusted shooting parameters.
  • the processor 11 is further configured to determine whether the candidate photo has motion blur; if the candidate photo does not have motion blur, the candidate photo is saved.
  • the processor 11 is further configured to discard the candidate photos if there is motion blur in the candidate photos; adjust the shooting parameters of the camera terminal so that the adjustment based on the camera terminal There is no motion blur in the photos taken by the shooting parameters;
  • the camera lens 12 is also used to retake the candidate photos based on the adjusted shooting parameters.
  • the shooting parameters include exposure brightness and/or exposure duration
  • the processor 11 is further used to increase the exposure brightness of the camera terminal and/or reduce the exposure time of the camera terminal.
  • the processor 11 is further used to determine the aesthetic quality of the candidate photo; if the aesthetic quality is greater than the second preset threshold, the candidate photo is saved.
  • the processor 11 is further configured to discard the candidate photos if the aesthetic quality is less than or equal to the second preset threshold.
  • the processor 11 is further configured to detect, in the saved photos, whether there is a stored photo with a similarity greater than the preset similarity to the candidate photo; if there is no If the stored photos are stored, the candidate photos are saved; if the stored photos exist, the candidate photos are discarded.
  • the processor 11 is further configured to detect, in the saved photos, whether there is a stored photo with a similarity between the candidate photos greater than a preset similarity; Store a photo, determine whether the aesthetic quality of the stored photo is less than the aesthetic quality of the candidate photo; if the aesthetic quality of the stored photo is less than the aesthetic quality of the candidate photo, delete the stored photo, and save the Candidate photo; if the aesthetic quality of the stored photo is greater than or equal to the aesthetic quality of the candidate photo, discard the candidate photo.
  • the processor 11 is further configured to count the cumulative number of times that the candidate photos are retaken in the current shooting scene;
  • the photo lens 12 is also used to re-take candidate photos based on the adjusted shooting parameters if the cumulative number of shooting times is less than the preset number of times.
  • the processor 11 is further used to take a scene picture; a scene classification model based on a neural network is used to determine the scene presented by the scene picture and serve as the current shooting scene.
  • the processor 11 is further configured to acquire a sample image set, the sample image set includes at least one sample image marked with a scene; using the sample images in the sample image set to preset The neural network model is trained until the weights in the preset neural network model all converge to obtain the scene classification model based on the neural network.
  • the processor 11 is further configured to determine a correspondence relationship between the shooting scene and the user's interest in the shooting scene set in the shooting terminal in advance; To find the degree of interest corresponding to the current shooting scene.
  • the processor 11 is further configured to determine a user's interest in the current shooting scene using a neural network-based interest determination model.
  • the processor 11 is further configured to acquire a sample image set, the sample image set includes at least one sample image marked with a scene and the user's interest in the marked scene;
  • the sample images in the sample image set are used to train the preset neural network model until the weights in the preset neural network model are all converged to obtain the neural network-based interest degree determination model.
  • the processor 11 is further configured to obtain automatic focus statistical information of the candidate photos; obtain automatic exposure statistical information of the candidate photos; and obtain automatic white balance statistical information of the candidate photos Obtain the image quality according to the autofocus statistical information, the automatic exposure statistical information, and the automatic white balance statistical information.
  • the processor 11 is further configured to obtain the contrast information of the candidate photo; calculate the difference information between the contrast information and the preset contrast information, and use it as the autofocus statistical information .
  • the processor 11 is further configured to count the first number of pixels in the candidate photos whose pixel value is less than the first preset pixel value; count the pixel values in the candidate photo greater than the second preset pixel The second number of pixels of the value; calculating the sum of the first number and the second number to obtain the automatic exposure statistical information.
  • the processor 11 is further configured to obtain color temperature information of the candidate photo; determine a target red gain and a target blue gain according to the color temperature information; and obtain a current red gain of the candidate photo And the current blue gain; calculate the automatic white balance statistics based on the target red gain, the target blue gain, the current red gain, and the current blue gain.
  • the processor 11 is further configured to calculate a first ratio between the current red gain and the target red gain; calculate the current blue gain and the target blue gain A second ratio between; calculating the sum of the first ratio and the second ratio to obtain the automatic white balance statistical information.
  • the processor 11 is further configured to calculate a first product between a first preset coefficient and the autofocus statistical information; calculate a second preset coefficient and the automatic exposure statistical information The second product between; calculating the third product between the third preset coefficient and the automatic white balance statistics; calculating the sum between the first product, the second product, and the third product Value; determine the reciprocal of the sum as the image quality.
  • the processor 11 is further used to obtain the first position of the scale-invariant feature transformation SIFT feature point in the candidate photo in the candidate photo; continuous shooting in the camera terminal Among multiple photos, determine a reference photo that is adjacent to the candidate photo and the shooting order is before the candidate photo; determine the second position of the SIFT feature point in the reference photo in the reference photo; determine A position difference between the first position and the second position; if the position difference is greater than a third preset threshold, it is determined that the candidate photo has motion blur; if the position difference is less than or equal to the third preset threshold, it is determined There is no motion blur in the candidate photos.
  • the processor 11 is further configured to determine the aesthetic quality of the candidate photo using a neural network-based aesthetic quality determination model.
  • the processor 11 is further configured to obtain a sample image set including at least one sample image marked with aesthetic quality; the sample images in the sample image set are used to preset The neural network model is trained until the weights in the preset neural network model all converge, and the neural network-based aesthetic quality determination model is obtained.
  • the camera terminal includes an inertial measurement unit IMU, a sensor, and a hardware clock;
  • the processor 11 is further configured to use the hardware clock to synchronize the frequency of the information collected by the IMU and the frequency of the photos taken by the camera terminal using the sensor.
  • the processor 11 is further configured to acquire the steering angle of the camera terminal; acquire the measurement angle of the IMU; determine the angle difference between the steering angle and the measurement angle; if If the angle difference is smaller than the fourth preset threshold, the candidate photos are saved.
  • the current shooting scene can be determined, and the interest degree of the user of the photographing terminal in the current shooting scene can be determined. If the degree of interest is greater than the preset degree of interest, the candidate photos are taken and the candidate photos are saved.
  • the photographing terminal can automatically take pictures of the scene that the user of the photographing terminal is interested in the presented scene without manual participation, thereby reducing the scrap rate of the pictures.
  • the description is relatively simple, and the relevant part can be referred to the description of the method embodiment.
  • the camera terminal 600 includes but is not limited to: a radio frequency unit 601, a network module 602, an audio output unit 603, an input unit 604, a sensor 605, and a display unit 606, user input unit 607, interface unit 608, memory 609, processor 610, power supply 611 and other components.
  • a radio frequency unit 601 for implementing various embodiments of the present invention.
  • the camera terminal 600 includes but is not limited to: a radio frequency unit 601, a network module 602, an audio output unit 603, an input unit 604, a sensor 605, and a display unit 606, user input unit 607, interface unit 608, memory 609, processor 610, power supply 611 and other components.
  • the camera terminal may include more or fewer components than the illustration, or a combination of certain components, or different components Layout.
  • the camera terminal includes but is not limited to a mobile phone, a tablet computer, a notebook computer, a palmtop computer, a vehicle-mounted terminal, a wearable device, a pedometer, and the like.
  • the radio frequency unit 601 may be used to receive and send signals during sending and receiving information or during a call. Specifically, after receiving the downlink data from the base station, it is processed by the processor 610; The uplink data is sent to the base station.
  • the radio frequency unit 601 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like.
  • the radio frequency unit 601 can also communicate with the network and other devices through a wireless communication system.
  • the camera terminal provides users with wireless broadband Internet access through the network module 602, such as helping users send and receive emails, browse web pages, and access streaming media.
  • the audio output unit 603 may convert the audio data received by the radio frequency unit 601 or the network module 602 or stored in the memory 609 into an audio signal and output as sound. Moreover, the audio output unit 603 may also provide audio output related to a specific function performed by the photographing terminal 600 (for example, call signal reception sound, message reception sound, etc.).
  • the audio output unit 603 includes a speaker, a buzzer, a receiver, and the like.
  • the input unit 604 is used to receive audio or video signals.
  • the input unit 604 may include a graphics processor (Graphics Processing Unit, GPU) 6041 and a microphone 6042.
  • Image data is processed.
  • the processed image frame may be displayed on the display unit 606.
  • the image frame processed by the graphics processor 6041 may be stored in the memory 609 (or other storage medium) or sent via the radio frequency unit 601 or the network module 602.
  • the microphone 6042 can receive sound, and can process such sound into audio data.
  • the processed audio data can be converted into a format that can be sent to the mobile communication base station via the radio frequency unit 601 in the case of a telephone call mode and output.
  • the camera terminal 600 further includes at least one sensor 605, such as a light sensor, a motion sensor, and other sensors.
  • the light sensor includes an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel 6061 according to the brightness of the ambient light, and the proximity sensor can close the display panel 6061 and the display panel 6061 when the camera terminal 600 moves to the ear /Or backlight.
  • the accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes), and can detect the magnitude and direction of gravity when at rest, and can be used to identify the posture of the camera terminal (such as horizontal and vertical screen switching, related games) , Magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tap), etc.; sensor 605 can also include fingerprint sensor, pressure sensor, iris sensor, molecular sensor, gyroscope, barometer, hygrometer, thermometer, Infrared sensors, etc. will not be repeated here.
  • the display unit 606 is used to display information input by the user or information provided to the user.
  • the display unit 606 may include a display panel 6061, and the display panel 6061 may be configured in the form of a liquid crystal display (Liquid Crystal) (LCD), an organic light-emitting diode (Organic Light-Emitting Diode, OLED), or the like.
  • LCD Liquid Crystal
  • OLED Organic Light-Emitting Diode
  • the user input unit 607 may be used to receive input numeric or character information, and generate key signal input related to user settings and function control of the camera terminal.
  • the user input unit 607 includes a touch panel 6071 and other input devices 6072.
  • the touch panel 6071 also known as a touch screen, can collect user's touch operations on or near it (for example, the user uses any suitable objects or accessories such as fingers, stylus, etc. on or near the touch panel 6071 operating).
  • the touch panel 6071 may include a touch detection camera terminal and a touch controller.
  • the touch detection camera terminal detects the user's touch orientation and detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection camera terminal and converts it into contact coordinates , And then sent to the processor 610 to receive the command sent by the processor 610 and execute it.
  • the touch panel 6071 may be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves.
  • the user input unit 607 may also include other input devices 6072.
  • other input devices 6072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which are not repeated here.
  • the touch panel 6071 may be overlaid on the display panel 6061.
  • the touch panel 6071 detects a touch operation on or near it, it is transmitted to the processor 610 to determine the type of touch event, and then the processor 610 according to the touch The type of event provides corresponding visual output on the display panel 6061.
  • the touch panel 6071 and the display panel 6061 are used as two independent components to realize the input and output functions of the camera terminal, in some embodiments, the touch panel 6071 and the display panel 6061 may be integrated
  • the input and output functions of the camera terminal are not specifically limited here.
  • the interface unit 608 is an interface connecting the external camera terminal and the camera terminal 600.
  • the external camera terminal may include a wired or wireless headset port, an external power (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a camera terminal with an identification module, audio input /Output (I/O) port, video I/O port, headphone port, etc.
  • the interface unit 608 may be used to receive input (eg, data information, power, etc.) from an external camera terminal and transmit the received input to one or more elements within the camera terminal 600 or may be used in the camera terminal 600 and Transfer data between external camera terminals.
  • the memory 609 can be used to store software programs and various data.
  • the memory 609 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, application programs required by at least one function (such as a sound playback function, an image playback function, etc.), etc.; the storage data area may store Data created by the use of mobile phones (such as audio data, phonebooks, etc.), etc.
  • the memory 609 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.
  • the processor 610 is the control center of the camera terminal, and uses various interfaces and lines to connect the various parts of the entire camera terminal, by running or executing the software programs and/or modules stored in the memory 609, and calling the data stored in the memory 609 , Perform various functions and process data of the camera terminal, so as to monitor the camera terminal as a whole.
  • the processor 610 may include one or more processing units; preferably, the processor 610 may integrate an application processor and a modem processor, where the application processor mainly processes an operating system, a user interface, and application programs, etc.
  • the processor mainly deals with wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 610.
  • the camera terminal 600 may further include a power supply 611 (such as a battery) that supplies power to various components.
  • a power supply 611 such as a battery
  • the power supply 611 may be logically connected to the processor 610 through a power management system, thereby managing charge, discharge, and power consumption management through the power management system And other functions.
  • the camera terminal 600 includes some function modules not shown, which will not be repeated here.
  • an embodiment of the present invention further provides a camera terminal, including a processor 610, a memory 609, a computer program stored on the memory 609 and executable on the processor 610, when the computer program is executed by the processor 610.
  • a camera terminal including a processor 610, a memory 609, a computer program stored on the memory 609 and executable on the processor 610, when the computer program is executed by the processor 610.
  • Embodiments of the present invention also provide a computer-readable storage medium, and a computer program is stored on the computer-readable storage medium.
  • the computer program is executed by a processor, the processes of the above embodiments of the photographing method are implemented, and the same technical effect can be achieved In order to avoid repetition, I will not repeat them here.
  • the computer-readable storage medium such as read-only memory (Read-Only Memory, ROM for short), random access memory (Random Access Memory, RAM for short), magnetic disk or optical disk, etc.
  • the embodiments of the present application may be provided as a method, a camera terminal, or a computer program product. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.
  • a computer usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing terminal device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product that includes instructions to take a photographic terminal,
  • the instruction photographing terminal implements the functions specified in one block or multiple blocks in one flow or multiple processes in the flowchart and/or one block in the block diagram.
  • These computer program instructions can also be loaded on a computer or other programmable data processing terminal device, so that a series of operation steps are performed on the computer or other programmable terminal device to generate computer-implemented processing, so that the computer or other programmable terminal device
  • the instructions executed above provide steps for implementing the functions specified in one block or multiple blocks of the flowchart one flow or multiple flows and/or block diagrams.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Studio Devices (AREA)

Abstract

本申请提供了一种拍照方法及拍照终端。在本申请中,可以确定当前拍摄场景(S101),确定拍照终端的使用者对当前拍摄场景的兴趣度(S102),如果该兴趣度大于预设兴趣度,则拍摄候选照片(S103),保存候选照片(S104)。通过本申请,拍照终端可以在无需人工参与的情况下,自动拍摄出拍照终端的使用者对呈现的场景感兴趣的照片,从而可以降低照片的废片率。

Description

拍照方法及拍照终端 技术领域
本申请涉及计算机技术领域,特别是涉及一种拍照方法及拍照终端。
背景技术
当前,越来越多的用户在旅行或观看运动赛事的过程中都会携带照相机拍照。当用户希望把自己也拍入照片内时,常采用定时拍照功能。然而,定时拍照具有一定盲目性,从而会使得得到的照片的废片率较高。
发明内容
为解决上述技术问题,本申请示出了一种拍照方法及拍照终端。
第一方面,本申请示出了一种拍照方法,应用于拍照终端,所述方法包括:确定当前拍摄场景;确定所述拍照终端的使用者对当前拍摄场景的兴趣度;如果所述兴趣度大于预设兴趣度,则拍摄候选照片;保存所述候选照片。
第二方面,本申请示出了一种拍照终端,所述拍照终端包括:处理器和拍照镜头;所述处理器用于确定当前拍摄场景;确定所述拍照终端的使用者对当前拍摄场景的兴趣度;所述拍照镜头用于如果所述兴趣度大于预设兴趣度,则拍摄候选照片;所述处理器还用于保存所述候选照片。
根据本申请的第三方面,提供一种电子设备,所述电子设备包括:处理器;用于存储处理器可执行指令的存储器;其中,所述处理器被配置为执行如第一方面所述的拍照方法。
根据本申请的第四方面,提供一种非临时性计算机可读存储介质,当所述存储介质中的指令由电子设备的处理器执行时,使得电子设备能够执行如第一方面所述的拍照方法。
根据本申请的第五方面,提供一种计算机程序产品,当所述计算机程序产品中的指令由电子设备的处理器执行时,使得电子设备能够执行如第一方面所述的拍照方法。
与现有技术相比,本申请包括以下优点:在本申请中,可以确定当前拍摄场景,确定拍照终端的使用者对当前拍摄场景的兴趣度,如果该兴趣度大于预设兴趣度,则拍摄候选照片,保存候选照片。通过本申请,拍照终端可以在无需人工参与的情况下,自动拍摄出拍照终端的使用者对呈现的场景感兴趣的照片,从而可以降低照片的废片率。
附图说明
图1是本申请的一种拍照方法的步骤流程图;
图2是本申请的一种拍照方法的步骤流程图;
图3是本申请的一种拍照方法的步骤流程图;
图4是本申请的一种拍照方法的步骤流程图;
图5是本申请的一种拍照方法的步骤流程图;
图6是本申请的一种拍照方法的步骤流程图;
图7是本申请的一种拍照终端的结构框图;
图8是本申请的一种拍照终端的结构框图。
具体实施例
为使本申请的上述目的、特征和优点能够更加明显易懂,下面结合附图和具体实施方式对本申请作进一步详细的说明。
参照图1,示出了本申请的一种拍照方法的步骤流程图,该方法应用于拍照终端,拍照终端包括具有拍摄功能的设备,例如,照相机、手机以及平板电脑等,该方法具体可以包括如下步骤:
在步骤S101中,确定当前拍摄场景。
在本申请中,事先可以获取样本图像集,样本图像集中包括至少一个标注有场景的样本图像,场景包括:人物、人脸、天空、建筑、植物、山以及水等,可以使用样本图像集中的样本图像对预设的神经网络模型进行训练,直至预设的神经网络模型中的权重均收敛,从而得到基于神经网络的场景分类模型。预设的神经网络模型包括CNN(Convolutional Neural Networks,卷积神经网络)或LSTM(Long Short-Term Memory,是长短期记忆网络)等,本申请对此不加以限定。
拍照终端的使用者可以将拍照终端携带在身上,例如,将拍照终端挂在胸前,或者,通过云台将拍照终端安装在用户肩部,如此,在用户走动的过程中,拍照终端就会按照本申请的方法自动拍摄候选照片并存储候选照片,全程无需拍照终端的使用者参与。
在本申请中,为了拍摄出用户感兴趣的照片,拍照终端需要确定当前拍摄场景,然后执行步骤S102。
在确定当前拍摄场景时,拍照终端可以拍摄场景图片,例如拍摄一张图片作为拍摄场景图片,然后使用基于神经网络的场景分类模型确定场景图片所呈现的场景,并作为当前拍摄场景,例如将场景图片输入至基于神经网络的场景分类模型中,得到基于神经网络的场景分类模型输出的场景。
其中,在确定出当前拍摄场景之后,为了节省拍照终端的存储空间,拍照终端也可以丢弃场景图片。
在步骤S102中,确定拍照终端的使用者对当前拍摄场景的兴趣度。
在本申请一个实施例中,拍照终端的使用者事先可以在拍照终端中设置用户对各个拍摄场景的兴趣度。
对于任意一个拍摄场景,拍照终端可以将该拍摄场景与拍照终端的使用者设置的对该拍摄场景的兴趣度组成对应表项,并存储在事先在拍摄终端中设置的、拍摄场景与使用者对拍摄场景的兴趣度之间的对应关系中,对于其他每一个拍摄场景,同样执行上述操作。
如此,在本步骤中,可以确定事先在拍摄终端中设置的、拍摄场景与使用者对拍摄场景的兴趣度之间的对应关系,然后在该对应关系中查找与当前拍摄场景相对应的兴趣度,从而得到拍照终端的使用者对当前拍摄场景的兴趣度。
在本申请另一个实施例中,事先可以获取样本图像集,样本图像集中包括至少一个标注有场景以及拍照终端的使用者的对标注的场景的兴趣度的样本图像,可以使用样本图像集中的样本图像对预设的神经网络模型进行训练,直至预设的神经网络模型中的权重均收敛,从而得到基于神经网络的兴趣度确定模型。预设的神经网络模型包括CNN或LSTM等,本申请对此不加以限定。
如此,在本步骤中,可以使用基于神经网络的兴趣度确定模型确定拍照终端的使用者对当前拍摄场景的兴趣度。例如,将当前拍摄场景输入至基于神经网络的场景分类模型中,得到基于神经网络的场景分类模型输出的兴趣度,从而得到拍照终端的使用者对当前拍摄场景的兴趣度。
如果该兴趣度大于预设兴趣度,在步骤S103中,拍摄候选照片。
在本申请中,可以比较该兴趣度与预设兴趣度之间的大小,如果该兴趣度大于预设兴趣度,则说明拍照终端的使用者对当前拍摄场景感兴趣,进而可以拍摄候选照片,候选照片中呈现的场景即为当前拍摄场景,因此,候选照片往往也是拍照终端的使用者感兴趣的照片,因此,可以保存候选照片。
进一步地,如果该兴趣度小于或等于预设兴趣度,则说明拍照终端的使用者对当前拍摄场景不感兴趣,此时无需拍摄候选照片,可以结束流程。
或者,在另一实施例中,由于拍照终端的使用者在携带拍照终端的过程中,使用者往往走动的,因此拍照终端的镜头所对的拍摄场景往往是不断变化的,为了能够拍摄出拍照终端的使用者对呈现的场景感兴趣的照片,因此,可以返回执行步骤S101。
在步骤S104中,保存候选照片。
在本申请中,可以确定当前拍摄场景,确定拍照终端的使用者对当前拍摄场景的兴趣度,如果该兴趣度大于预设兴趣度,则拍摄候选照片,保存候选照片。通过本申请,拍照终端可以在无需人工参与的情况下,自动拍摄出拍照终端的使用者对呈现的场景感兴趣的照片,从而可以降低照片的废片率。
进一步地,参见图2,在步骤S103之后,该方法还包括:
在步骤S201中,确定候选照片的图像质量。
其中,步骤可以通过如下流程实现,包括:
2011、获取候选照片的自动对焦统计信息。
在本申请中,可以获取候选照片的对比度信息,然后计算候选照片的对比度信息与预设对比度信息之间的差异信息,并作为自动对焦统计信息。
预设对比度信息可以为受广大人群感兴趣的照片的对比度信息,也即,预设对比度信息为标准的对比度信息,当一个照片的对比度信息为标准的对比度信息,该照片在对比度上受广大人群感兴趣。
2012、获取候选照片的自动曝光统计信息。
其中,可以统计候选照片中像素值小于第一预设像素值的像素点的第一数量;统计候选照片中像素值大于第二预设像素值的像素点的第二数量;计算第一数量与第二数量之和,得到所述自动曝光统计信息。
第一预设像素值小于第二预设像素值,例如,第一预设像素值可以为45,第二预设像素值可以为204等。
2013、获取候选照片的自动白平衡统计信息。
在本申请中,可以获取候选照片的色温信息,根据色温信息确定目标红色增益和目标蓝色增益,获取候选照片的当前红色增益和当前蓝色增益,根据目标红色增益、目标蓝色增益、当前红色增益以及当前蓝色增益计算自动白平衡统计信息。
例如,计算当前红色增益与目标红色增益之间的第一比值以及计算当前蓝色增益与目标蓝色增益之间的第二比值,再计算第一比值与第二比值之和,得到自动白平衡统计信息。
目标红色增益可以为受广大人群感兴趣的照片的红色增益,也即,目标红色增益为标准的红色增益,当一个照片的红色增益为标准的红色增益,该照片在红色增益上受广大人群感兴趣。
目标蓝色增益可以为受广大人群感兴趣的照片的蓝色增益,也即,目标蓝色增益为标准的蓝色增益,当一个照片的蓝色增益为标准的蓝色增益,该照片在蓝色增益上受广大人群感兴趣。
2014、根据自动对焦统计信息、自动曝光统计信息以及自动白平衡统计信息获取图像质量。
在本申请中,可以计算第一预设系数与自动对焦统计信息之间的第一乘积,计算第二预设系数与自动曝光统计信息之间的第二乘积以及计算第三预设系数与自动白平衡统计信息之间的第三乘积,再计算第一乘积、第二乘积以及第三乘积之间的和值,然后将该和值的倒数确定为图像质量。
第一预设系数、第二预设系数以及第一预设系数可以根据实际情况确定,本申请对第一预设系数、第二预设系数以及第一预设系数的具体数值不做限定。
在步骤S202中,确定图像质量是否大于第一预设阈值。
如果图像质量大于第一预设阈值,则执行步骤S104:保存候选照片。
在本申请中,如果候选照片的图像质量小于第一预设阈值,则说明候选照片在自动对焦统计信息、自动曝光统计信息以及自动白平衡统计信息中的至少一个符合标准的要求,如此,即使拍照终端的使用者对候选照片呈现的场景感兴趣,则可能也会由于候选照片的图像质量小于第一预设阈值而对候选照片不感兴趣,从而导致候选照片为废片,仍旧会提高照片的废片率,因此,为了降低照片的废片率,需要确定候选照片的图像质量,并在图像质量大于第一预设阈值的情况下,再保存候选照片,如果候选照片的图像质量大于第一预设阈值,则说明候选照片在自动对焦统计信息、自动曝光统计信息以及自动白平衡统计信息上均符合标准的要求,因此,拍照终端的使用者对候选照片感兴趣的可能性较大,从而可以降低照片的废片率。
如果图像质量小于或等于第一预设阈值,在步骤S203中,丢弃候选照片。
如果图像质量小于或等于第一预设阈值,则拍照终端的使用者候选照片可能不感兴趣,也即,因此,为了节省拍照终端的存储空间,可以丢弃候选照片,然后执行步骤S204。
在步骤S204中,调整拍照终端的拍摄参数,以使基于拍照终端的调整后的拍摄参数拍摄的照片的图像质量大于第一预设阈值。
拍照终端拍摄的照片的图像质量受拍照终端的拍摄参数的影响,例如,拍照终端的拍摄参数与当前拍摄环境不适应,或者,当前环境亮度较暗,拍照终端的曝光量较低,导致拍摄到的照片较暗,或者,拍照终端的曝光时长较长,导致拍摄到的照片虚化不清晰。
因此,为了在用户感兴趣的当前拍摄场景中能够拍摄出用户感兴趣的照片,拍 照终端可以自动调整拍摄参数,以使基于拍照终端的调整后的拍摄参数拍摄的照片的图像质量大于第一预设阈值,进而使得拍照终端可以基于调整后的拍摄参数可以重新拍摄出用户感兴趣的、呈现出当前拍摄场景的照片。
在步骤S205中,基于调整后的拍摄参数重新拍摄候选照片。
进一步地,可以返回步骤S201。
进一步地,在一个拍摄场景中如果重复拍摄了多次照片的图像质量均小于第一预设阈值,则往往说明在该拍摄场景中不适合拍摄照片,为了节省拍照终端的拍摄资源,可以不再继续在该拍摄场景中继续拍摄照片。
如此,在本申请另一实施例中,可以统计在当前拍摄场景下重新拍摄候选照片的累计拍摄次数。如果累计拍摄次数小于预设次数,则再基于调整后的拍摄参数重新拍摄候选照片。如果累计拍摄次数大于或等于预设次数,则结束流程。
其中,预设次数可以为拍照终端的使用者事先在拍照终端中设置的,预设次数可以为3、4、5或6等,本申请对此不加以限定。
进一步地,参见图3,在步骤S103之后,该方法还包括:
在步骤S301中,确定候选照片是否存在运动模糊。
在本步骤中,可以获取候选照片中的SIFT(Scale-invariant feature transform,尺度不变特征变换)特征点在候选照片中的第一位置。其中,拍照终端可以连续不断地拍摄照片,从而使得相邻的照片非常相似,拍照终端连续拍摄的多张照片中,确定与候选照片相邻且拍摄顺序位于候选照片之前的参考照片。确定参考照片中的SIFT特征点的在参考照片中第二位置。确定第一位置与第二位置之间的位置差异。如果位置差异大于第三预设阈值,则确定候选照片存在运动模糊。如果位置差异小于或等于第三预设阈值,则确定候选照片不存在运动模糊。
如果候选照片不存在运动模糊,则执行步骤S104:保存候选照片。
在申请中,拍照终端在拍摄候选照片时有时候是用户在走动的时候拍摄的,因此,可能会导致候选照片存在运动模糊,例如,候选照片中的有些地方虚化不清晰等。
通常情况下,广大人群对存在运动模糊的照片都不感兴趣,如此,即使拍照终端的使用者对候选照片呈现的场景感兴趣,则可能也会由于候选照片存在运动模糊而对候选照片不感兴趣,从而导致候选照片为废片,仍旧会提高照片的废片率,因此,为了降低照片的废片率,需要确定候选照片是否存在运动模糊,如果候选照片不存在运动模糊,则说明拍照终端的使用者对候选照片感兴趣的可能性较大,此时再保存候选照片可以降低照片的废片率。
如果候选照片存在运动模糊,在步骤S302中,丢弃候选照片。
如果候选照片存在运动模糊,则拍照终端的使用者候选照片可能不感兴趣,也即,因此,为了节省拍照终端的存储空间,可以丢弃候选照片,然后执行步骤S303。
在步骤S303中,调整拍照终端的拍摄参数,以使基于拍照终端的调整后的拍摄参数拍摄的照片不存在运动模糊。
拍照终端拍摄的照片是否存在运动模糊受拍照终端的拍摄参数的影响,拍摄参数包括曝光亮度和/或曝光时长。例如,当前环境亮度较暗,拍照终端的曝光量较低, 导致拍摄到的照片虚化不清晰,或者,拍照终端的曝光时长较长,导致拍摄到的照片虚化不清晰。
因此,为了在用户感兴趣的当前拍摄场景中能够拍摄出用户感兴趣的照片,拍照终端可以自动调整拍摄参数,例如提高拍照终端的曝光亮度和/或降低拍照终端的曝光时长以使基于拍照终端的调整后的拍摄参数拍摄的照片的图像质量大于第一预设阈值,进而使得拍照终端可以基于调整后的拍摄参数可以重新拍摄出用户感兴趣的、呈现出当前拍摄场景的照片。
在步骤S304中,基于调整后的拍摄参数重新拍摄候选照片。
进一步地,可以返回步骤S201。
进一步地,在一个拍摄场景中如果重复拍摄了多次照片的图像质量均小于第一预设阈值,则往往说明在该拍摄场景中不适合拍摄照片,为了节省拍照终端的拍摄资源,可以不再继续在该拍摄场景中继续拍摄照片。
如此,在本申请另一实施例中,可以统计在当前拍摄场景下重新拍摄候选照片的累计拍摄次数。如果累计拍摄次数小于预设次数,则再基于调整后的拍摄参数重新拍摄候选照片。如果累计拍摄次数大于或等于预设次数,则结束流程。
其中,预设次数可以为拍照终端的使用者事先在拍照终端中设置的,预设次数可以为3、4、5或6等,本申请对此不加以限定。
进一步地,参见图4,在步骤S103之后,该方法还包括:
在步骤S401中,确定候选照片的美学质量。
在本申请中,事先可以获取样本图像集,样本图像集中包括至少一个标注有美学质量的样本图像,可以使用样本图像集中的样本图像对预设的神经网络模型进行训练,直至预设的神经网络模型中的权重均收敛,从而得到基于神经网络的美学质量确定模型。预设的神经网络模型包括CNN或LSTM等,本申请对此不加以限定。
样本图像的美学质量可以是专业的摄影师对样本图像标注的。
如此,在本步骤中,可以使用基于神经网络的美学质量确定模型确定候选照片的美学质量。例如,将候选照片输入至基于神经网络的美学质量中,得到基于神经网络的美学质量输出的美学质量,从而得到候选照片的美学质量。
在步骤S402中,确定美学质量是否大于第二预设阈值。
如果美学质量大于第二预设阈值,则执行步骤S104:保存候选照片。
通常情况下,专业的摄影师对美学质量较低的照片不感兴趣,而对美学质量较高的照片感兴趣。
如此,即使拍照终端的使用者对候选照片呈现的场景感兴趣,则可能也会由于候选照片美学质量较低而对候选照片不感兴趣,从而导致候选照片为废片,仍旧会提高照片的废片率,因此,为了降低照片的废片率,需要确定候选照片的美学质量,如果美学质量大于第二预设阈值,则保存候选照片。
如果美学质量大于第二预设阈值,则说明专业的摄影师可能对候选照片感兴趣,由于普通人对照片的审美技术往往低于专业的摄影师对照片的审美技术,如此当专业的摄影师对某一照片感兴趣时,往往普通人也对该照片感兴趣。
因此,如果美学质量大于第二预设阈值,拍照终端的使用者对候选照片感兴趣 的可能性较大,从而可以降低照片的废片率。
如果美学质量小于或等于第二预设阈值,在步骤S403中,丢弃候选照片。
如果候选照片的美学质量小于或等于第二预设阈值,则拍照终端的使用者候选照片可能不感兴趣,也即,因此,为了节省拍照终端的存储空间,可以丢弃候选照片。
在本申请中,有时候在一个场景中拍照终端可能会拍摄多张照片,如果多张照片都是相似的,拍照终端的使用者之后往往也只会使用其中的一张照片。
因此,如果将拍摄的多张照片都保存在拍照终端中,则会浪费拍照终端的存储资源。
所以,进一步地,为了节省拍照终端的存储资源,在本申请另一实施例中,参见图5,在步骤S103之后,该方法还包括:
在步骤S501中,在已保存的照片中,检测是否存在与候选照片之间的相似度大于预设相似度的存储照片。
其中,可以通过现有技术中的任意一种相似度计算方法来计算候选照片与已保存的照片之间的相似度,本申请对相似度计算不做限定。
如果不存在存储照片,则执行步骤S104:保存候选照片。
如果存在存储照片,在步骤S502中,丢弃候选照片。
通过本申请的方法,在拍照终端连续拍摄到多张相似的照片中,可以仅保存一个照片,从而可以节省拍照终端的存储资源。
在本申请中,有时候在一个场景中拍照终端可能会拍摄多张照片,如果多张照片都是相似的,拍照终端的使用者之后往往也只会使用其中的一张照片。
因此,如果将拍摄的多张照片都保存在拍照终端中,则会浪费拍照终端的存储资源。
所以,进一步地,为了节省拍照终端的存储资源,在本申请另一实施例中,参见图6,在步骤S103之后,该方法还包括:
在步骤S601中,在已保存的照片中,检测是否存在与候选照片之间的相似度大于预设相似度的存储照片。
如果不存在存储照片,则执行步骤S104:保存候选照片。
如果存在存储照片,在步骤S602中,确定存储照片的美学质量是否小于候选照片的美学质量。
如果存储照片的美学质量小于候选照片的美学质量,在步骤S603中,删除存储照片,然后执行步骤S104:保存候选照片。
如果存储照片的美学质量大于或等于候选照片的美学质量,在步骤S604中,丢弃候选照片。
通过本申请的方法,在拍照终端连续拍摄到多张相似的照片中,可以仅保存一个照片,从而可以节省拍照终端的存储资源,其次,保存的照片还是拍摄的多张照片中的美学质量最高的照片,从而使得拍照终端的使用者之后可 以使用美学质量最高的照片,从而可以提高拍照终端的使用者的体验。
在一个实施例中,拍照终端中包括惯性测量单元IMU、传感器以及硬件时钟;该方法还包括:使用硬件时钟同步IMU采集信息的频率和拍照终端使用传感器拍摄照片的频率。如此,拍摄候选照片之后,还可以获取拍照终端的转向角度;获取IMU的测量角度;确定转向角度与测量角度之间的角度差异;如果角度差异小于第四预设阈值,则保存候选照片。
需要说明的是,对于方法实施例,为了简单描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本申请并不受所描述的动作顺序的限制,因为依据本申请,某些步骤可以采用其他顺序或者同时进行。其次,本领域技术人员也应该知悉,说明书中所描述的实施例均属于可选实施例,所涉及的动作并不一定是本申请所必须的。
参照图7,示出了本申请的一种拍照终端的结构框图,该拍照终端应用于飞行器,该拍照终端具体可以包括:处理器1111和拍照镜头1212;
所述处理器11用于确定当前拍摄场景;确定所述拍照终端的使用者对当前拍摄场景的兴趣度;
所述拍照镜头12用于如果所述兴趣度大于预设兴趣度,则拍摄候选照片;
所述处理器11还用于保存所述候选照片。
在一个可选的实现方式中,所述处理器11还用于确定所述候选照片的图像质量;如果所述图像质量大于第一预设阈值,则保存所述候选照片。
在一个可选的实现方式中,所述处理器11还用于如果所述图像质量小于或等于所述第一预设阈值,则丢弃所述候选照片;调整所述拍照终端的拍摄参数,以使基于所述拍照终端的调整后的拍摄参数拍摄的照片的图像质量大于所述第一预设阈值;
所述拍照镜头12还用于基于调整后的拍摄参数重新拍摄候选照片。
在一个可选的实现方式中,所述处理器11还用于确定所述候选照片是否存在运动模糊;如果候选照片不存在运动模糊,则保存所述候选照片。
在一个可选的实现方式中,所述处理器11还用于如果候选照片存在运动模糊,则丢弃所述候选照片;调整所述拍照终端的拍摄参数,以使基于所述拍照终端的调整后的拍摄参数拍摄的照片不存在运动模糊;
所述拍照镜头12还用于基于调整后的拍摄参数重新拍摄候选照片。
在一个可选的实现方式中,所述拍摄参数包括曝光亮度和/或曝光时长;
所述处理器11还用于提高所述拍照终端的曝光亮度和/或降低所述拍照终端的曝光时长。
在一个可选的实现方式中,所述处理器11还用于确定所述候选照片的美学质量;如果美学质量大于第二预设阈值,则保存所述候选照片。
在一个可选的实现方式中,所述处理器11还用于如果所述美学质量小于或等于所述第二预设阈值,则丢弃所述候选照片。
在一个可选的实现方式中,所述处理器11还用于在已保存的照片中,检测是否存在与所述候选照片之间的相似度大于预设相似度的存储照片;如果不存在所述存储照片,则保存所述候选照片;如果存在所述存储照片,则丢弃所述候选照片。
在一个可选的实现方式中,所述处理器11还用于在已保存的照片中,检测是否存 在与所述候选照片之间的相似度大于预设相似度的存储照片;如果存在所述存储照片,则确定所述存储照片的美学质量是否小于所述候选照片的美学质量;如果所述存储照片的美学质量小于所述候选照片的美学质量,则删除所述存储照片,并保存所述候选照片;如果所述存储照片的美学质量大于或等于所述候选照片的美学质量,则丢弃所述候选照片。
在一个可选的实现方式中,所述处理器11还用于统计在所述当前拍摄场景下重新拍摄候选照片的累计拍摄次数;
所述拍照镜头12还用于如果所述累计拍摄次数小于预设次数,则基于调整后的拍摄参数重新拍摄候选照片。
在一个可选的实现方式中,所述处理器11还用于拍摄场景图片;使用基于神经网络的场景分类模型确定所述场景图片所呈现的场景,并作为所述当前拍摄场景。
在一个可选的实现方式中,所述处理器11还用于获取样本图像集,所述样本图像集中包括至少一个标注有场景的样本图像;使用所述样本图像集中的样本图像对预设的神经网络模型进行训练,直至所述预设的神经网络模型中的权重均收敛,得到所述基于神经网络的场景分类模型。
在一个可选的实现方式中,所述处理器11还用于确定事先在拍摄终端中设置的、拍摄场景与所述使用者对拍摄场景的兴趣度之间的对应关系;在所述对应关系中查找与所述当前拍摄场景相对应的兴趣度。
在一个可选的实现方式中,所述处理器11还用于使用基于神经网络的兴趣度确定模型确定所述用户对所述当前拍摄场景的兴趣度。
在一个可选的实现方式中,所述处理器11还用于获取样本图像集,所述样本图像集中包括至少一个标注有场景以及所述使用者的对标注的场景的兴趣度的样本图像;使用所述样本图像集中的样本图像对预设的神经网络模型进行训练,直至所述预设的神经网络模型中的权重均收敛,得到所述基于神经网络的兴趣度确定模型。
在一个可选的实现方式中,所述处理器11还用于获取所述候选照片的自动对焦统计信息;获取所述候选照片的自动曝光统计信息;获取所述候选照片的自动白平衡统计信息;根据所述自动对焦统计信息、所述自动曝光统计信息以及所述自动白平衡统计信息获取所述图像质量。
在一个可选的实现方式中,所述处理器11还用于获取所述候选照片的对比度信息;计算所述对比度信息与预设对比度信息之间的差异信息,并作为所述自动对焦统计信息。
在一个可选的实现方式中,所述处理器11还用于统计候选照片中像素值小于第一预设像素值的像素点的第一数量;统计候选照片中像素值大于第二预设像素值的像素点的第二数量;计算所述第一数量与所述第二数量之和,得到所述自动曝光统计信息。
在一个可选的实现方式中,所述处理器11还用于获取所述候选照片的色温信息;根据所述色温信息确定目标红色增益和目标蓝色增益;获取所述候选照片的当前红色增益和当前蓝色增益;根据所述目标红色增益、所述目标蓝色增益、所述当前红色增益以及所述当前蓝色增益计算所述自动白平衡统计信息。
在一个可选的实现方式中,所述处理器11还用于计算所述当前红色增益与所述目标红色增益之间的第一比值;计算所述当前蓝色增益与所述目标蓝色增益之间的第二比值;计算所述第一比值与所述第二比值之和,得到所述自动白平衡统计信息。
在一个可选的实现方式中,所述处理器11还用于计算第一预设系数与所述自动对焦统计信息之间的第一乘积;计算第二预设系数与所述自动曝光统计信息之间的第二乘积;计算第三预设系数与所述自动白平衡统计信息之间的第三乘积;计算所述第一乘积、所述第二乘积以及所述第三乘积之间的和值;将所述和值的倒数确定为所述图像质量。
在一个可选的实现方式中,所述处理器11还用于获取所述候选照片中的尺度不变特征变换SIFT特征点在所述候选照片中的第一位置;在所述拍照终端连续拍摄的多张照片中,确定与所述候选照片相邻且拍摄顺序位于所述候选照片之前的参考照片;确定所述参考照片中的SIFT特征点的在所述参考照片中第二位置;确定所述第一位置与所述第二位置之间的位置差异;如果位置差异大于第三预设阈值,则确定所述候选照片存在运动模糊;如果位置差异小于或等于第三预设阈值,则确定所述候选照片不存在运动模糊。
在一个可选的实现方式中,所述处理器11还用于使用基于神经网络的美学质量确定模型确定所述候选照片的美学质量。
在一个可选的实现方式中,所述处理器11还用于获取样本图像集,所述样本图像集中包括至少一个标注有美学质量的样本图像;使用所述样本图像集中的样本图像对预设的神经网络模型进行训练,直至所述预设的神经网络模型中的权重均收敛,得到所述基于神经网络的美学质量确定模型。
在一个可选的实现方式中,所述拍照终端中包括惯性测量单元IMU、传感器以及硬件时钟;
所述处理器11还用于使用所述硬件时钟同步所述IMU采集信息的频率和所述拍照终端使用所述传感器拍摄照片的频率。
在一个可选的实现方式中,所述处理器11还用于获取所述拍照终端的转向角度;获取IMU的测量角度;确定所述转向角度与所述测量角度之间的角度差异;如果所述角度差异小于第四预设阈值,则保存所述候选照片。
在本申请中,可以确定当前拍摄场景,确定拍照终端的使用者对当前拍摄场景的兴趣度,如果该兴趣度大于预设兴趣度,则拍摄候选照片,保存候选照片。通过本申请,拍照终端可以在无需人工参与的情况下,自动拍摄出拍照终端的使用者对呈现的场景感兴趣的照片,从而可以降低照片的废片率。
对于拍照终端实施例而言,由于其与方法实施例基本相似,所以描述的比较简单,相关之处参见方法实施例的部分说明即可。
图8为实现本发明各个实施例的一种拍照终端的硬件结构示意图,该拍照终端600包括但不限于:射频单元601、网络模块602、音频输出单元603、输入单元604、传感器605、显示单元606、用户输入单元607、接口单元608、存储器609、处理器610、以及电源611等部件。本领域技术人员可以理解,图8中示出的拍照终端结构并不构成对拍照终端的限定,拍照终端可以包括比图示更多或更少的部件,或者组合某些部件,或 者不同的部件布置。在本发明实施例中,拍照终端包括但不限于手机、平板电脑、笔记本电脑、掌上电脑、车载终端、可穿戴设备、以及计步器等。
应理解的是,本发明实施例中,射频单元601可用于收发信息或通话过程中,信号的接收和发送,具体的,将来自基站的下行数据接收后,给处理器610处理;另外,将上行的数据发送给基站。通常,射频单元601包括但不限于天线、至少一个放大器、收发信机、耦合器、低噪声放大器、双工器等。此外,射频单元601还可以通过无线通信系统与网络和其他设备通信。
拍照终端通过网络模块602为用户提供了无线的宽带互联网访问,如帮助用户收发电子邮件、浏览网页和访问流式媒体等。
音频输出单元603可以将射频单元601或网络模块602接收的或者在存储器609中存储的音频数据转换成音频信号并且输出为声音。而且,音频输出单元603还可以提供与拍照终端600执行的特定功能相关的音频输出(例如,呼叫信号接收声音、消息接收声音等等)。音频输出单元603包括扬声器、蜂鸣器以及受话器等。
输入单元604用于接收音频或视频信号。输入单元604可以包括图形处理器(Graphics Processing Unit,GPU)6041和麦克风6042,图形处理器6041对在视频捕获模式或图像捕获模式中由图像捕获拍照终端(如摄像头)获得的静态图片或视频的图像数据进行处理。处理后的图像帧可以显示在显示单元606上。经图形处理器6041处理后的图像帧可以存储在存储器609(或其它存储介质)中或者经由射频单元601或网络模块602进行发送。麦克风6042可以接收声音,并且能够将这样的声音处理为音频数据。处理后的音频数据可以在电话通话模式的情况下转换为可经由射频单元601发送到移动通信基站的格式输出。
拍照终端600还包括至少一种传感器605,比如光传感器、运动传感器以及其他传感器。具体地,光传感器包括环境光传感器及接近传感器,其中,环境光传感器可根据环境光线的明暗来调节显示面板6061的亮度,接近传感器可在拍照终端600移动到耳边时,关闭显示面板6061和/或背光。作为运动传感器的一种,加速计传感器可检测各个方向上(一般为三轴)加速度的大小,静止时可检测出重力的大小及方向,可用于识别拍照终端姿态(比如横竖屏切换、相关游戏、磁力计姿态校准)、振动识别相关功能(比如计步器、敲击)等;传感器605还可以包括指纹传感器、压力传感器、虹膜传感器、分子传感器、陀螺仪、气压计、湿度计、温度计、红外线传感器等,在此不再赘述。
显示单元606用于显示由用户输入的信息或提供给用户的信息。显示单元606可包括显示面板6061,可以采用液晶显示器(Liquid Crystal Display,LCD)、有机发光二极管(Organic Light-Emitting Diode,OLED)等形式来配置显示面板6061。
用户输入单元607可用于接收输入的数字或字符信息,以及产生与拍照终端的用户设置以及功能控制有关的键信号输入。具体地,用户输入单元607包括触控面板6071以及其他输入设备6072。触控面板6071,也称为触摸屏,可收集用户在其上或附近的触摸操作(比如用户使用手指、触笔等任何适合的物体或附件在触控面板6071上或在触控面板6071附近的操作)。触控面板6071可包括触摸检测拍照终端和触摸控制器两个部分。其中,触摸检测拍照终端检测用户的触摸方位,并检测触摸操作带来的信号,将信号传送给触摸控制器;触摸控制器从触摸检测拍照终端上接收触摸信息,并将它转换成触点 坐标,再送给处理器610,接收处理器610发来的命令并加以执行。此外,可以采用电阻式、电容式、红外线以及表面声波等多种类型实现触控面板6071。除了触控面板6071,用户输入单元607还可以包括其他输入设备6072。具体地,其他输入设备6072可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆,在此不再赘述。
进一步的,触控面板6071可覆盖在显示面板6061上,当触控面板6071检测到在其上或附近的触摸操作后,传送给处理器610以确定触摸事件的类型,随后处理器610根据触摸事件的类型在显示面板6061上提供相应的视觉输出。虽然在图7中,触控面板6071与显示面板6061是作为两个独立的部件来实现拍照终端的输入和输出功能,但是在某些实施例中,可以将触控面板6071与显示面板6061集成而实现拍照终端的输入和输出功能,具体此处不做限定。
接口单元608为外部拍照终端与拍照终端600连接的接口。例如,外部拍照终端可以包括有线或无线头戴式耳机端口、外部电源(或电池充电器)端口、有线或无线数据端口、存储卡端口、用于连接具有识别模块的拍照终端的端口、音频输入/输出(I/O)端口、视频I/O端口、耳机端口等等。接口单元608可以用于接收来自外部拍照终端的输入(例如,数据信息、电力等等)并且将接收到的输入传输到拍照终端600内的一个或多个元件或者可以用于在拍照终端600和外部拍照终端之间传输数据。
存储器609可用于存储软件程序以及各种数据。存储器609可主要包括存储程序区和存储数据区,其中,存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等;存储数据区可存储根据手机的使用所创建的数据(比如音频数据、电话本等)等。此外,存储器609可以包括高速随机存取存储器,还可以包括非易失性存储器,例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
处理器610是拍照终端的控制中心,利用各种接口和线路连接整个拍照终端的各个部分,通过运行或执行存储在存储器609内的软件程序和/或模块,以及调用存储在存储器609内的数据,执行拍照终端的各种功能和处理数据,从而对拍照终端进行整体监控。处理器610可包括一个或多个处理单元;优选的,处理器610可集成应用处理器和调制解调处理器,其中,应用处理器主要处理操作系统、用户界面和应用程序等,调制解调处理器主要处理无线通信。可以理解的是,上述调制解调处理器也可以不集成到处理器610中。
拍照终端600还可以包括给各个部件供电的电源611(比如电池),优选的,电源611可以通过电源管理系统与处理器610逻辑相连,从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。
另外,拍照终端600包括一些未示出的功能模块,在此不再赘述。
优选的,本发明实施例还提供一种拍照终端,包括处理器610,存储器609,存储在存储器609上并可在所述处理器610上运行的计算机程序,该计算机程序被处理器610执行时实现上述拍照方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
本发明实施例还提供一种计算机可读存储介质,计算机可读存储介质上存储有计算 机程序,该计算机程序被处理器执行时实现上述拍照方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。其中,所述的计算机可读存储介质,如只读存储器(Read-Only Memory,简称ROM)、随机存取存储器(Random Access Memory,简称RAM)、磁碟或者光盘等。
本说明书中的各个实施例均采用递进的方式描述,每个实施例重点说明的都是与其他实施例的不同之处,各个实施例之间相同相似的部分互相参见即可。
本领域内的技术人员应明白,本申请的实施例可提供为方法、拍照终端、或计算机程序产品。因此,本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请的方法、终端设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理终端设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理终端设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的拍照终端。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理终端设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令拍照终端的制造品,该指令拍照终端实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理终端设备上,使得在计算机或其他可编程终端设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程终端设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本申请的优选实施例,但本领域内的技术人员一旦得知了基本创造性概念,则可对这些实施例做出另外的变更和修改。所以,所附权利要求意欲解释为包括优选实施例以及落入本申请范围的所有变更和修改。
最后,还需要说明的是,在本文中,诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来,而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者终端设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者终端设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、物品或者终端设备中还存在另外的相同要素。
以上对本申请所提供的一种拍照方法及拍照终端,进行了详细介绍,本文中应用了具体个例对本申请的原理及实施方式进行了阐述,以上实施例的说明只是用于帮助理解 本申请的方法及其核心思想;同时,对于本领域的一般技术人员,依据本申请的思想,在具体实施方式及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本申请的限制。

Claims (54)

  1. 一种拍照方法,其特征在于,应用于拍照终端,所述方法包括:
    确定当前拍摄场景;
    确定所述拍照终端的使用者对当前拍摄场景的兴趣度;
    如果所述兴趣度大于预设兴趣度,则拍摄候选照片;
    保存所述候选照片。
  2. 根据权利要求1所述的方法,其特征在于,所述拍摄候选照片之后,还包括:
    确定所述候选照片的图像质量;
    如果所述图像质量大于第一预设阈值,则执行所述保存所述候选照片的步骤。
  3. 根据权利要求2所述的方法,其特征在于,所述方法还包括:
    如果所述图像质量小于或等于所述第一预设阈值,则丢弃所述候选照片;
    调整所述拍照终端的拍摄参数,以使基于所述拍照终端的调整后的拍摄参数拍摄的照片的图像质量大于所述第一预设阈值;
    基于调整后的拍摄参数重新拍摄候选照片。
  4. 根据权利要求1所述的方法,其特征在于,所述拍摄候选照片之后,还包括:
    确定所述候选照片是否存在运动模糊;
    如果候选照片不存在运动模糊,则执行所述保存所述候选照片的步骤。
  5. 根据权利要求4所述的方法,其特征在于,所述方法还包括:
    如果候选照片存在运动模糊,则丢弃所述候选照片;
    调整所述拍照终端的拍摄参数,以使基于所述拍照终端的调整后的拍摄参数拍摄的照片不存在运动模糊;
    基于调整后的拍摄参数重新拍摄候选照片。
  6. 根据权利要求5所述的方法,其特征在于,所述拍摄参数包括曝光亮度和/或曝光时长;
    所述调整所述拍照终端的拍摄参数,包括:
    提高所述拍照终端的曝光亮度和/或降低所述拍照终端的曝光时长。
  7. 根据权利要求1所述的方法,其特征在于,所述拍摄候选照片之后,还包括:
    确定所述候选照片的美学质量;
    如果美学质量大于第二预设阈值,则执行所述保存所述候选照片的步骤。
  8. 根据权利要求7所述的方法,其特征在于,所述方法还包括:
    如果所述美学质量小于或等于所述第二预设阈值,则丢弃所述候选照片。
  9. 根据权利要求1所述的方法,其特征在于,所述拍摄候选照片之后,还包括:
    在已保存的照片中,检测是否存在与所述候选照片之间的相似度大于预设相似度的存储照片;
    如果不存在所述存储照片,则执行所述保存所述候选照片的步骤;
    如果存在所述存储照片,则丢弃所述候选照片。
  10. 根据权利要求7所述的方法,其特征在于,所述拍摄候选照片之后,还包 括:
    在已保存的照片中,检测是否存在与所述候选照片之间的相似度大于预设相似度的存储照片;
    如果存在所述存储照片,则确定所述存储照片的美学质量是否小于所述候选照片的美学质量;
    如果所述存储照片的美学质量小于所述候选照片的美学质量,则删除所述存储照片,并执行所述保存所述候选照片的步骤;
    如果所述存储照片的美学质量大于或等于所述候选照片的美学质量,则丢弃所述候选照片。
  11. 根据权利要求3或5所述的方法,其特征在于,所述方法还包括:
    统计在所述当前拍摄场景下重新拍摄候选照片的累计拍摄次数;
    如果所述累计拍摄次数小于预设次数,则执行所述基于调整后的拍摄参数重新拍摄候选照片的步骤。
  12. 根据权利要求1所述的方法,其特征在于,所述确定当前拍摄场景,包括:
    拍摄场景图片;
    使用基于神经网络的场景分类模型确定所述场景图片所呈现的场景,并作为所述当前拍摄场景。
  13. 根据权利要求12所述的方法,其特征在于,所述方法还包括:
    获取样本图像集,所述样本图像集中包括至少一个标注有场景的样本图像;
    使用所述样本图像集中的样本图像对预设的神经网络模型进行训练,直至所述预设的神经网络模型中的权重均收敛,得到所述基于神经网络的场景分类模型。
  14. 根据权利要求1所述的方法,其特征在于,所述确定所述拍照终端的使用者对当前拍摄场景的兴趣度,包括:
    确定事先在拍摄终端中设置的、拍摄场景与所述使用者对拍摄场景的兴趣度之间的对应关系;
    在所述对应关系中查找与所述当前拍摄场景相对应的兴趣度。
  15. 根据权利要求1所述的方法,其特征在于,所述确定所述拍照终端的使用者对当前拍摄场景的兴趣度,包括:
    使用基于神经网络的兴趣度确定模型确定所述用户对所述当前拍摄场景的兴趣度。
  16. 根据权利要求15所述的方法,其特征在于,所述方法还包括:
    获取样本图像集,所述样本图像集中包括至少一个标注有场景以及所述使用者的对标注的场景的兴趣度的样本图像;
    使用所述样本图像集中的样本图像对预设的神经网络模型进行训练,直至所述预设的神经网络模型中的权重均收敛,得到所述基于神经网络的兴趣度确定模型。
  17. 根据权利要求2所述的方法,其特征在于,所述确定所述候选照片的图像质量,包括:
    获取所述候选照片的自动对焦统计信息;
    获取所述候选照片的自动曝光统计信息;
    获取所述候选照片的自动白平衡统计信息;
    根据所述自动对焦统计信息、所述自动曝光统计信息以及所述自动白平衡统计信息获取所述图像质量。
  18. 根据权利要求17所述的方法,其特征在于,所述获取所述候选照片的自动对焦统计信息,包括:
    获取所述候选照片的对比度信息;
    计算所述对比度信息与预设对比度信息之间的差异信息,并作为所述自动对焦统计信息。
  19. 根据权利要求17所述的方法,其特征在于,所述获取所述候选照片的自动曝光统计信息,包括:
    统计候选照片中像素值小于第一预设像素值的像素点的第一数量;
    统计候选照片中像素值大于第二预设像素值的像素点的第二数量;
    计算所述第一数量与所述第二数量之和,得到所述自动曝光统计信息。
  20. 根据权利要求17所述的方法,其特征在于,所述获取所述候选照片的自动白平衡统计信息,包括:
    获取所述候选照片的色温信息;
    根据所述色温信息确定目标红色增益和目标蓝色增益;
    获取所述候选照片的当前红色增益和当前蓝色增益;
    根据所述目标红色增益、所述目标蓝色增益、所述当前红色增益以及所述当前蓝色增益计算所述自动白平衡统计信息。
  21. 根据权利要求20所述的方法,其特征在于,所述根据所述目标红色增益、所述目标蓝色增益、所述当前红色增益以及所述当前蓝色增益计算所述自动白平衡统计信息,包括:
    计算所述当前红色增益与所述目标红色增益之间的第一比值;
    计算所述当前蓝色增益与所述目标蓝色增益之间的第二比值;
    计算所述第一比值与所述第二比值之和,得到所述自动白平衡统计信息。
  22. 根据权利要求17所述的方法,其特征在于,所述根据所述自动对焦统计信息、所述自动曝光统计信息以及所述自动白平衡统计信息获取所述图像质量,包括:
    计算第一预设系数与所述自动对焦统计信息之间的第一乘积;
    计算第二预设系数与所述自动曝光统计信息之间的第二乘积;
    计算第三预设系数与所述自动白平衡统计信息之间的第三乘积;
    计算所述第一乘积、所述第二乘积以及所述第三乘积之间的和值;
    将所述和值的倒数确定为所述图像质量。
  23. 根据权利要求4所述的方法,其特征在于,所述确定所述候选照片是否存在运动模糊,包括:
    获取所述候选照片中的尺度不变特征变换SIFT特征点在所述候选照片中的第一位置;
    在所述拍照终端连续拍摄的多张照片中,确定与所述候选照片相邻且拍摄顺序位于所述候选照片之前的参考照片;
    确定所述参考照片中的SIFT特征点的在所述参考照片中第二位置;
    确定所述第一位置与所述第二位置之间的位置差异;
    如果位置差异大于第三预设阈值,则确定所述候选照片存在运动模糊;
    如果位置差异小于或等于第三预设阈值,则确定所述候选照片不存在运动模糊。
  24. 根据权利要求7所述的方法,其特征在于,所述确定所述候选照片的美学质量,包括:
    使用基于神经网络的美学质量确定模型确定所述候选照片的美学质量。
  25. 根据权利要求24所述的方法,其特征在于,所述方法还包括:
    获取样本图像集,所述样本图像集中包括至少一个标注有美学质量的样本图像;
    使用所述样本图像集中的样本图像对预设的神经网络模型进行训练,直至所述预设的神经网络模型中的权重均收敛,得到所述基于神经网络的美学质量确定模型。
  26. 根据权利要求1所述的方法,其特征在于,所述拍照终端中包括惯性测量单元IMU、传感器以及硬件时钟;
    所述方法还包括:
    使用所述硬件时钟同步所述IMU采集信息的频率和所述拍照终端使用所述传感器拍摄照片的频率。
  27. 根据权利要求26所述的方法,其特征在于,所述拍摄候选照片之后,还包括:
    获取所述拍照终端的转向角度;
    获取IMU的测量角度;
    确定所述转向角度与所述测量角度之间的角度差异;
    如果所述角度差异小于第四预设阈值,则执行所述保存所述候选照片的步骤。
  28. 一种拍照终端,其特征在于,所述拍照终端包括:处理器和拍照镜头;
    所述处理器用于确定当前拍摄场景;确定所述拍照终端的使用者对当前拍摄场景的兴趣度;
    所述拍照镜头用于如果所述兴趣度大于预设兴趣度,则拍摄候选照片;
    所述处理器还用于保存所述候选照片。
  29. 根据权利要求28所述的拍照终端,其特征在于,所述处理器还用于确定所述候选照片的图像质量;如果所述图像质量大于第一预设阈值,则保存所述候选照片。
  30. 根据权利要求29所述的拍照终端,其特征在于,所述处理器还用于如果所述图像质量小于或等于所述第一预设阈值,则丢弃所述候选照片;调整所述拍照终端的拍摄参数,以使基于所述拍照终端的调整后的拍摄参数拍摄的照片的图像质量大 于所述第一预设阈值;
    所述拍照镜头还用于基于调整后的拍摄参数重新拍摄候选照片。
  31. 根据权利要求28所述的拍照终端,其特征在于,所述处理器还用于确定所述候选照片是否存在运动模糊;如果候选照片不存在运动模糊,则保存所述候选照片。
  32. 根据权利要求31所述的拍照终端,其特征在于,所述处理器还用于如果候选照片存在运动模糊,则丢弃所述候选照片;调整所述拍照终端的拍摄参数,以使基于所述拍照终端的调整后的拍摄参数拍摄的照片不存在运动模糊;
    所述拍照镜头还用于基于调整后的拍摄参数重新拍摄候选照片。
  33. 根据权利要求32所述的拍照终端,其特征在于,所述拍摄参数包括曝光亮度和/或曝光时长;
    所述处理器还用于提高所述拍照终端的曝光亮度和/或降低所述拍照终端的曝光时长。
  34. 根据权利要求28所述的拍照终端,其特征在于,所述处理器还用于确定所述候选照片的美学质量;如果美学质量大于第二预设阈值,则保存所述候选照片。
  35. 根据权利要求34所述的拍照终端,其特征在于,所述处理器还用于如果所述美学质量小于或等于所述第二预设阈值,则丢弃所述候选照片。
  36. 根据权利要求28所述的拍照终端,其特征在于,所述处理器还用于在已保存的照片中,检测是否存在与所述候选照片之间的相似度大于预设相似度的存储照片;如果不存在所述存储照片,则保存所述候选照片;如果存在所述存储照片,则丢弃所述候选照片。
  37. 根据权利要求34所述的拍照终端,其特征在于,所述处理器还用于在已保存的照片中,检测是否存在与所述候选照片之间的相似度大于预设相似度的存储照片;如果存在所述存储照片,则确定所述存储照片的美学质量是否小于所述候选照片的美学质量;如果所述存储照片的美学质量小于所述候选照片的美学质量,则删除所述存储照片,并保存所述候选照片;如果所述存储照片的美学质量大于或等于所述候选照片的美学质量,则丢弃所述候选照片。
  38. 根据权利要求30或32所述的拍照终端,其特征在于,所述处理器还用于统计在所述当前拍摄场景下重新拍摄候选照片的累计拍摄次数;
    所述拍照镜头还用于如果所述累计拍摄次数小于预设次数,则基于调整后的拍摄参数重新拍摄候选照片。
  39. 根据权利要求28所述的拍照终端,其特征在于,所述处理器还用于拍摄场景图片;使用基于神经网络的场景分类模型确定所述场景图片所呈现的场景,并作为所述当前拍摄场景。
  40. 根据权利要求39所述的拍照终端,其特征在于,所述处理器还用于获取样本图像集,所述样本图像集中包括至少一个标注有场景的样本图像;使用所述样本图像集中的样本图像对预设的神经网络模型进行训练,直至所述预设的神经网络模 型中的权重均收敛,得到所述基于神经网络的场景分类模型。
  41. 根据权利要求28所述的拍照终端,其特征在于,所述处理器还用于确定事先在拍摄终端中设置的、拍摄场景与所述使用者对拍摄场景的兴趣度之间的对应关系;在所述对应关系中查找与所述当前拍摄场景相对应的兴趣度。
  42. 根据权利要求28所述的拍照终端,其特征在于,所述处理器还用于使用基于神经网络的兴趣度确定模型确定所述用户对所述当前拍摄场景的兴趣度。
  43. 根据权利要求42所述的拍照终端,其特征在于,所述处理器还用于获取样本图像集,所述样本图像集中包括至少一个标注有场景以及所述使用者的对标注的场景的兴趣度的样本图像;使用所述样本图像集中的样本图像对预设的神经网络模型进行训练,直至所述预设的神经网络模型中的权重均收敛,得到所述基于神经网络的兴趣度确定模型。
  44. 根据权利要求29所述的拍照终端,其特征在于,所述处理器还用于获取所述候选照片的自动对焦统计信息;获取所述候选照片的自动曝光统计信息;获取所述候选照片的自动白平衡统计信息;根据所述自动对焦统计信息、所述自动曝光统计信息以及所述自动白平衡统计信息获取所述图像质量。
  45. 根据权利要求44所述的拍照终端,其特征在于,所述处理器还用于获取所述候选照片的对比度信息;计算所述对比度信息与预设对比度信息之间的差异信息,并作为所述自动对焦统计信息。
  46. 根据权利要求44所述的拍照终端,其特征在于,所述处理器还用于统计候选照片中像素值小于第一预设像素值的像素点的第一数量;统计候选照片中像素值大于第二预设像素值的像素点的第二数量;计算所述第一数量与所述第二数量之和,得到所述自动曝光统计信息。
  47. 根据权利要求44所述的拍照终端,其特征在于,所述处理器还用于获取所述候选照片的色温信息;根据所述色温信息确定目标红色增益和目标蓝色增益;获取所述候选照片的当前红色增益和当前蓝色增益;根据所述目标红色增益、所述目标蓝色增益、所述当前红色增益以及所述当前蓝色增益计算所述自动白平衡统计信息。
  48. 根据权利要求47所述的拍照终端,其特征在于,所述处理器还用于计算所述当前红色增益与所述目标红色增益之间的第一比值;计算所述当前蓝色增益与所述目标蓝色增益之间的第二比值;计算所述第一比值与所述第二比值之和,得到所述自动白平衡统计信息。
  49. 根据权利要求44所述的拍照终端,其特征在于,所述处理器还用于计算第一预设系数与所述自动对焦统计信息之间的第一乘积;计算第二预设系数与所述自动曝光统计信息之间的第二乘积;计算第三预设系数与所述自动白平衡统计信息之间的第三乘积;计算所述第一乘积、所述第二乘积以及所述第三乘积之间的和值;将所述和值的倒数确定为所述图像质量。
  50. 根据权利要求31所述的拍照终端,其特征在于,所述处理器还用于获取所 述候选照片中的尺度不变特征变换SIFT特征点在所述候选照片中的第一位置;在所述拍照终端连续拍摄的多张照片中,确定与所述候选照片相邻且拍摄顺序位于所述候选照片之前的参考照片;确定所述参考照片中的SIFT特征点的在所述参考照片中第二位置;确定所述第一位置与所述第二位置之间的位置差异;如果位置差异大于第三预设阈值,则确定所述候选照片存在运动模糊;如果位置差异小于或等于第三预设阈值,则确定所述候选照片不存在运动模糊。
  51. 根据权利要求34所述的拍照终端,其特征在于,所述处理器还用于使用基于神经网络的美学质量确定模型确定所述候选照片的美学质量。
  52. 根据权利要求51所述的拍照终端,其特征在于,所述处理器还用于获取样本图像集,所述样本图像集中包括至少一个标注有美学质量的样本图像;使用所述样本图像集中的样本图像对预设的神经网络模型进行训练,直至所述预设的神经网络模型中的权重均收敛,得到所述基于神经网络的美学质量确定模型。
  53. 根据权利要求28所述的拍照终端,其特征在于,所述拍照终端中包括惯性测量单元IMU、传感器以及硬件时钟;
    所述处理器还用于使用所述硬件时钟同步所述IMU采集信息的频率和所述拍照终端使用所述传感器拍摄照片的频率。
  54. 根据权利要求53所述的拍照终端,其特征在于,所述处理器还用于获取所述拍照终端的转向角度;获取IMU的测量角度;确定所述转向角度与所述测量角度之间的角度差异;如果所述角度差异小于第四预设阈值,则保存所述候选照片。
PCT/CN2018/125603 2018-12-29 2018-12-29 拍照方法及拍照终端 Ceased WO2020133409A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2018/125603 WO2020133409A1 (zh) 2018-12-29 2018-12-29 拍照方法及拍照终端
CN201880068096.1A CN111247787A (zh) 2018-12-29 2018-12-29 拍照方法及拍照终端

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/125603 WO2020133409A1 (zh) 2018-12-29 2018-12-29 拍照方法及拍照终端

Publications (1)

Publication Number Publication Date
WO2020133409A1 true WO2020133409A1 (zh) 2020-07-02

Family

ID=70877313

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/125603 Ceased WO2020133409A1 (zh) 2018-12-29 2018-12-29 拍照方法及拍照终端

Country Status (2)

Country Link
CN (1) CN111247787A (zh)
WO (1) WO2020133409A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112911058A (zh) * 2021-01-20 2021-06-04 惠州Tcl移动通信有限公司 一种拍照控制方法、装置、移动终端及存储介质
CN114138014A (zh) * 2021-11-19 2022-03-04 浙江远望土地勘测规划设计有限公司 一种用于土地勘测的无人机控制方法、装置、设备及存储介质
CN118088963A (zh) * 2024-03-07 2024-05-28 广东艾罗智能光电股份有限公司 一种可自动追光的智能照明控制方法及装置

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113315910A (zh) * 2021-05-19 2021-08-27 闻泰通讯股份有限公司 拍摄方法、装置、计算机设备和存储介质
CN113256668A (zh) * 2021-06-13 2021-08-13 中科云尚(南京)智能技术有限公司 图像分割方法以及装置

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1510903A (zh) * 2002-11-25 2004-07-07 ��˹���´﹫˾ 成像方法与系统
CN105393153A (zh) * 2013-04-24 2016-03-09 微软技术许可有限责任公司 运动模糊避免
US20160127641A1 (en) * 2014-11-03 2016-05-05 Robert John Gove Autonomous media capturing
CN106954051A (zh) * 2017-03-16 2017-07-14 广东欧珀移动通信有限公司 一种图像处理方法及移动终端
US9836484B1 (en) * 2015-12-30 2017-12-05 Google Llc Systems and methods that leverage deep learning to selectively store images at a mobile image capture device
CN108234870A (zh) * 2017-12-27 2018-06-29 广东欧珀移动通信有限公司 图像处理方法、装置、终端及存储介质
CN109063778A (zh) * 2018-08-09 2018-12-21 中共中央办公厅电子科技学院 一种图像美学质量确定方法及系统

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7855743B2 (en) * 2006-09-08 2010-12-21 Sony Corporation Image capturing and displaying apparatus and image capturing and displaying method
CN107231520A (zh) * 2017-04-27 2017-10-03 歌尔科技有限公司 相机拍摄方法、装置及相机
CN108898174A (zh) * 2018-06-25 2018-11-27 Oppo(重庆)智能科技有限公司 一种场景数据采集方法、场景数据采集装置及电子设备

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1510903A (zh) * 2002-11-25 2004-07-07 ��˹���´﹫˾ 成像方法与系统
CN105393153A (zh) * 2013-04-24 2016-03-09 微软技术许可有限责任公司 运动模糊避免
US20160127641A1 (en) * 2014-11-03 2016-05-05 Robert John Gove Autonomous media capturing
US9836484B1 (en) * 2015-12-30 2017-12-05 Google Llc Systems and methods that leverage deep learning to selectively store images at a mobile image capture device
CN106954051A (zh) * 2017-03-16 2017-07-14 广东欧珀移动通信有限公司 一种图像处理方法及移动终端
CN108234870A (zh) * 2017-12-27 2018-06-29 广东欧珀移动通信有限公司 图像处理方法、装置、终端及存储介质
CN109063778A (zh) * 2018-08-09 2018-12-21 中共中央办公厅电子科技学院 一种图像美学质量确定方法及系统

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112911058A (zh) * 2021-01-20 2021-06-04 惠州Tcl移动通信有限公司 一种拍照控制方法、装置、移动终端及存储介质
CN112911058B (zh) * 2021-01-20 2022-07-15 惠州Tcl移动通信有限公司 一种拍照控制方法、装置、移动终端及存储介质
CN114138014A (zh) * 2021-11-19 2022-03-04 浙江远望土地勘测规划设计有限公司 一种用于土地勘测的无人机控制方法、装置、设备及存储介质
CN114138014B (zh) * 2021-11-19 2023-09-01 浙江远望土地勘测规划设计有限公司 一种用于土地勘测的无人机控制方法、装置、设备及存储介质
CN118088963A (zh) * 2024-03-07 2024-05-28 广东艾罗智能光电股份有限公司 一种可自动追光的智能照明控制方法及装置

Also Published As

Publication number Publication date
CN111247787A (zh) 2020-06-05

Similar Documents

Publication Publication Date Title
CN107566529B (zh) 一种拍照方法、移动终端及云端服务器
CN109361865B (zh) 一种拍摄方法及终端
CN107580184B (zh) 一种拍摄方法及移动终端
CN107592466B (zh) 一种拍照方法及移动终端
CN108540724A (zh) 一种拍摄方法及移动终端
CN107592468B (zh) 一种拍摄参数调整方法及移动终端
CN109688322B (zh) 一种生成高动态范围图像的方法、装置及移动终端
CN107820011A (zh) 拍照方法和拍照装置
CN107835364A (zh) 一种拍照辅助方法及移动终端
CN108605085B (zh) 一种获取拍摄参考数据的方法、移动终端
CN107734251A (zh) 一种拍照方法和移动终端
CN107770438A (zh) 一种拍照方法及移动终端
CN111064895B (zh) 一种虚化拍摄方法和电子设备
CN106937039A (zh) 一种基于双摄像头的成像方法、移动终端及存储介质
WO2019129020A1 (zh) 一种摄像头自动调焦方法、存储设备及移动终端
CN108419008B (zh) 一种拍摄方法、终端及计算机可读存储介质
CN111247787A (zh) 拍照方法及拍照终端
WO2020020134A1 (zh) 拍摄方法及移动终端
CN110266957B (zh) 影像拍摄方法及移动终端
CN110602384A (zh) 曝光控制方法及电子设备
CN107948516A (zh) 一种图像处理方法、装置及移动终端
CN109104564B (zh) 一种拍摄提示方法及终端设备
CN113347372A (zh) 拍摄补光方法、移动终端及可读存储介质
CN107888833A (zh) 一种图像拍摄方法及移动终端
CN108184052A (zh) 一种视频录制的方法、移动终端及计算机可读存储介质

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: 18945056

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: 18945056

Country of ref document: EP

Kind code of ref document: A1